CHANGELOG.md

1.0.0 (2026-03-05)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• Add comprehensive subprocess security guardrails (fixes #57) (#66) (454b80e)
• Add comprehensive YAML validation to prevent attacks (fixes #56) (#63) (31ecb3a)
• add repository checkout step to Claude Code Action workflow (17aa0cf)
• add uv.lock to recognized lockfiles (#143) (a98dc87), closes #137
• address P1 code quality issues from code review (#36) (5976332)
• address P1 code quality issues from code review (#37) (4be1d5e)
• address P1 code quality issues from code review (#38) (77f2300)
• assessors: FileSizeLimitsAssessor now respects .gitignore (#248) (eaaecc2), closes #245
• assessors: search recursively for OpenAPI specification files (#127) (e2a5778)
• assessors: support project-named directories and test-only repos in standard_layout check (#322) (2fbb733), closes #246 #305
• Check for all official commitlint config file formats (#308) (50588cf)
• ci: add permissions for leaderboard PR comment posting (#276) (33252e4)
• ci: use gh pr view for fork PR number lookup in coverage comment (#253) (1688362)
• cli: check .pre-commit-config.yaml for conventional commit (#310) (61c44d9)
• cli: Honor excluded_attributes from config file (#306) (ffda546), closes #302 #302
• cli: Use removesuffix instead of rstrip for .git URL stripping (#292) (6bd08cf)
• consider renovate for dependency_security check (#317) (35bfbbf)
• correct Assessment field name in demo command (#41) (b48622d), closes #12
• Correct datetime import pattern in RepomixService (#65) (517aa6e)
• correct GitHub repository link in site navigation (5492278)
• correct Liquid syntax in developer-guide (elif -> elsif) (75f3b1d)
• Correct pre-commit template path in PrecommitHooksFixer (#269) (c42a3c9)
• Create shared test fixtures and fix Assessment schema issues (#114) (46baa13)
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• Enable workflow_dispatch for leaderboard update and regenerate data (#299) (091d9dd), closes #298
• exclude DEPLOYMENT.md and SETUP_SUMMARY.md from Jekyll build (9611207)
• Improve CLAUDE.md generation prompt and add prompt loading for future LLM integrations #283 (#284) (c0aeae4)
• Improve report metadata display with clean table format (ca361a4)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• metadata: use Windows-compatible strftime token for human timestamp (#291) (faf536d)
• P0 security and logic bugs from code review (2af2346)
• Prevent API key exposure in environment and logs (fixes #55) (#64) (4d1d001)
• Prevent command injection in CommandFix.apply() (fixes #52) (#60) (49be28e)
• Prevent path traversal in LLM cache (fixes #53) (#61) (2bf052d)
• prevent unauthorized message for non-command comments (#262) (84c6f69)
• Prevent XSS in HTML reports (fixes #54) (#62) (7c60c69)
• properly indent multi-line fix previews in align output (#289) (4e36cb5), closes #285
• remove incorrect dbasunag/opendatahub-tests submission (#321) (e6aecf8), closes #301
• rename research report in data directory (b8ddfdc)
• replace all remaining elif with elsif in developer-guide (73f16fc)
• Resolve 35 pytest failures through model validation and path sanitization improvements (#115) (4fbfee0)
• resolve all broken links failing CI lychee check (#288) (4412c27)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• Resolve merge conflicts in CLI main module (#59) (9e0bf2d)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• Sanitize sensitive data in HTML reports (fixes #58) (#67) (6fbac76)
• schema backwards compat for attributes_skipped key (#277) (841bcc4)
• schema: allow assessments with excluded attributes (#312) (81b999f), closes #301 #309
• security: replace pull_request_target with pull_request trigger (#328) (3c5d31b), closes #324
• set correct baseurl for GitHub Pages subdirectory deployment (c4db765)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• Update Claude workflow to trigger on @claude mentions (#35) (a8a3fab)
• Use GitHub URL instead of local one (#297) (5abc7c2)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add agentready-dev Claude agent specification (#44) (0f61f5c)
• add ambient-code/agentready to leaderboard (#148) (621152e)
• Add automated demo command for AgentReady (#24) (f4e89d9), closes #1 #25 hi#quality hi#scoring
• add Claude Code GitHub Action for @claude mentions (3e7224d)
• Add comprehensive unit tests for utility modules (privacy.py and subprocess_utils.py) (#111) (9d3dece)
• Add customizable HTML report themes with runtime switching (#46) (7eeaf84), closes hi#contrast #10
• add dbasunag/opendatahub-tests to leaderboard (#301) (be7a55f)
• add dgutride/odh-dashboard to leaderboard (#268) (f4911b2)
• Add Doubleagent - specialized AgentReady development agent (#30) (0ab54cb)
• add feast-dev/feast to leaderboard (#293) (c894ce9)
• add GitHub organization scanning to assess-batch command (#118) (e306314)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• Add Interactive Dashboard backlog item (adfc4c8)
• add interactive heatmap visualization for batch assessments (#136) (4d44fc3)
• Add interactive HTML report generation (18664ea)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add opendatahub-io/opendatahub-tests to leaderboard (#314) (7a52466)
• add quay/quay to leaderboard (#162) (d6e8df0)
• add Red-Hat-AI-Innovation-Team/sdg_hub to leaderboard (#279) (5b71392)
• add release pipeline coldstart prompt (#19) (9a3880c), closes #18
• Add Repomix integration for AI-friendly repository context generation (#29) (92bdde1), closes #24 #1 #25 hi#quality hi#scoring
• add report header with repository metadata (#28) (7a8b34a)
• Add research report management CLI commands (#45) (e1be488), closes #7
• Add security & quality improvements from code review (#40) (13cd3ca)
• Add security & quality improvements from code review (#49) (889d6ed)
• Add SWE-bench experiment system for validating AgentReady impact (#124) (15edbba)
• Add weekly research update skill and automation (#145) (7ba17a6)
• assessors: implement File Size Limits assessor (Tier 2) (#141) (248467f)
• assessors: support AGENTS.md and @ references in CLAUDEmdAssessor (#265) (450ec25), closes #244
• Auto-sync CLAUDE.md during semantic-release (#101) (36b48cb)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• Batch Report Enhancements + Bootstrap Template Inheritance (Phase 2 Task 5) (#133) (7762b23)
• centralize Claude instructions via AGENTS.md and add init redirect tests (#273) (92c8f3f)
• Community Leaderboard for AgentReady Scores (#146) (fea0b3e)
• Complete Phases 5-7 - Markdown reports, testing, and polish (7659623)
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178
• Implement AgentReady MVP with scoring engine (54a96cb)
• Implement align subcommand for automated remediation (Issue #14) (#34) (06f04dc)
• Implement ArchitectureDecisionsAssessor (fixes #81) (#89) (9e782e5)
• implement automated semantic release pipeline (#20) (b579235)
• implement bootstrap command for GitHub infrastructure (0af06c4), closes #2
• Implement BranchProtectionAssessor stub (fixes #86) (#98) (44c4b17)
• Implement CICDPipelineVisibilityAssessor (fixes #85) (#91) (e68285c)
• Implement CodeSmellsAssessor stub (fixes #87) (#99) (f06b2a8)
• Implement ConciseDocumentationAssessor (fixes #76) (#93) (c356cd5)
• Implement InlineDocumentationAssessor (fixes #77) (#94) (e56e570)
• Implement IssuePRTemplatesAssessor (fixes #84) (#90) (819d7b7)
• Implement multi-repository batch assessment (Phase 1 of issue #68) (#74) (befc0d5)
• Implement OneCommandSetupAssessor (fixes #75) (#88) (668ba1b)
• Implement OpenAPISpecsAssessor (fixes #80) (#97) (45ae36e)
• implement Phase 2 multi-repository assessment reporting (#117) (8da56c2), closes #69
• implement report schema versioning (#43) (4c4752c)
• Implement SemanticNamingAssessor (fixes #82) (#95) (d87a280)
• Implement SeparationOfConcernsAssessor (fixes #78) (#92) (99bfe28)
• Implement StructuredLoggingAssessor (fixes #79) (#96) (2b87ca7)
• integrate ACL file with Claude Code Action allowed_users (#261) (fe52489)
• Phase 1 Task 1 - Consolidate Security Validation Patterns (#129) (8580c45), closes #122 #122 #122
• Phase 1 Tasks 2-3 - Consolidate Reporter Base & Assessor Factory (#131) (8e12bf9), closes #122 #122 #122 #122
• Phase 2 Task 4 - Replace manual config validation with Pydantic (#134) (d83cf58)
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• redesign HTML report with dark theme and larger fonts (#39) (59f6702), closes #8b5cf6 #XX
• Rename 'learn' command to 'extract-skills' for clarity (#125) (64d6563), closes hi#scoring #123
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Standardize on Python 3.12+ with forward compatibility for 3.13 (#132) (84f2c46)
• submit: add --gh flag for gh CLI-based submission (#278) (48bb624)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

BREAKING CHANGES

• Users must update scripts from 'agentready learn' to 'agentready extract-skills'. All flags and options remain identical.

2.29.5 (2026-03-03)

Bug Fixes

• security: replace pull_request_target with pull_request trigger (#328) (3c5d31b), closes #324

2.29.4 (2026-02-24)

Bug Fixes

• consider renovate for dependency_security check (#317) (35bfbbf)

2.29.3 (2026-02-24)

Bug Fixes

• schema: allow assessments with excluded attributes (#312) (81b999f), closes #301 #309 #309

2.29.2 (2026-02-23)

Bug Fixes

• cli: check .pre-commit-config.yaml for conventional commit (#310) (61c44d9)
• remove incorrect dbasunag/opendatahub-tests submission (#321) (e6aecf8), closes #301

2.29.1 (2026-02-20)

Bug Fixes

• Check for all official commitlint config file formats (#308) (50588cf)

2.29.0 (2026-02-20)

Features

• add dbasunag/opendatahub-tests to leaderboard (#301) (be7a55f)
• add opendatahub-io/opendatahub-tests to leaderboard (#314) (7a52466)

2.28.2 (2026-02-19)

Bug Fixes

• cli: Honor excluded_attributes from config file (#306) (ffda546), closes #302 #302

2.28.1 (2026-02-18)

Bug Fixes

• Enable workflow_dispatch for leaderboard update and regenerate data (#299) (091d9dd), closes #298

2.28.0 (2026-02-18)

Bug Fixes

• Use GitHub URL instead of local one (#297) (5abc7c2)

Features

• add feast-dev/feast to leaderboard (#293) (c894ce9)

2.27.5 (2026-02-17)

Bug Fixes

• cli: Use removesuffix instead of rstrip for .git URL stripping (#292) (6bd08cf)

2.27.4 (2026-02-17)

Bug Fixes

• properly indent multi-line fix previews in align output (#289) (4e36cb5), closes #285

2.27.3 (2026-02-16)

Bug Fixes

• metadata: use Windows-compatible strftime token for human timestamp (#291) (faf536d)

2.27.2 (2026-02-16)

Bug Fixes

• Improve CLAUDE.md generation prompt and add prompt loading for future LLM integrations #283 (#284) (c0aeae4)

2.27.1 (2026-02-12)

Bug Fixes

• resolve all broken links failing CI lychee check (#288) (4412c27)

2.27.0 (2026-02-09)

Features

• add Red-Hat-AI-Innovation-Team/sdg_hub to leaderboard (#279) (5b71392)
• submit: add --gh flag for gh CLI-based submission (#278) (48bb624)

2.26.0 (2026-02-09)

Features

• centralize Claude instructions via AGENTS.md and add init redirect tests (#273) (92c8f3f)

2.25.2 (2026-02-06)

Bug Fixes

• schema backwards compat for attributes_skipped key (#277) (841bcc4)

2.25.1 (2026-02-06)

Bug Fixes

• ci: add permissions for leaderboard PR comment posting (#276) (33252e4)

2.25.0 (2026-02-04)

Features

• add dgutride/odh-dashboard to leaderboard (#268) (f4911b2)

2.24.1 (2026-01-30)

Bug Fixes

• Correct pre-commit template path in PrecommitHooksFixer (#269) (c42a3c9)

2.24.0 (2026-01-30)

Features

• integrate ACL file with Claude Code Action allowed_users (#261) (fe52489)

2.23.0 (2026-01-16)

Features

• assessors: support AGENTS.md and @ references in CLAUDEmdAssessor (#265) (450ec25), closes #244

2.22.3 (2026-01-16)

Bug Fixes

• prevent unauthorized message for non-command comments (#262) (84c6f69)

2.22.2 (2026-01-15)

Bug Fixes

• ci: use gh pr view for fork PR number lookup in coverage comment (#253) (1688362)

2.22.1 (2026-01-15)

Bug Fixes

• assessors: FileSizeLimitsAssessor now respects .gitignore (#248) (eaaecc2), closes #245

2.22.0 (2025-12-16)

Bug Fixes

• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• workflows: add comment posting for @agentready-dev agent (5dff614)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: remove if:always() to test step execution (ff0bb12)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)
• workflows: simplify post-comment step condition (1bbf40a)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: ensure post-comment step runs after Claude Code Action (b087e5c)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: handle all event types in agentready-dev workflow (9b942bf)
• workflows: improve error handling and logging for comment posting (9ea1e6b)
• workflows: improve issue number extraction and add debug step (ecd896b)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: handle all event types in agentready-dev workflow (9b942bf)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171
• workflows: add comment posting for @agentready-dev agent (5dff614)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.10.0 (2025-12-16)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• downgrade docker/metadata-action to v5 and fix shellcheck warnings (12f5509)
• enable Harbor task filtering for smoketest support (#222) (f780188)
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192
• rename research report in data directory (b8ddfdc)
• resolve all test suite failures - achieve zero failures (#180) (990fa2d), closes #148 #147 #145
• resolve broken links and workflow failures (#160) (fbf5cf7)
• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)
• resolve YAML syntax error in update-docs workflow and add actionlint (#173) (97b06af)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)
• update --version flag to show correct version and research report date (#221) (5a85abb)
• workflows: handle all event types in agentready-dev workflow (9b942bf)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)
• add Memory MCP server allow list to repository settings (#203) (41d87bb)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish
• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221
• container support (#171) (c6874ea)
• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191
• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178
• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187
• replace markdown-link-check with lychee for link validation (#177) (f1a4545)
• Terminal-Bench eval harness (MVP Phase 1) (#178) (d06bab4), closes #171

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.21.0 (2025-12-15)

Features

• consolidate GitHub Actions workflows by purpose (#217) (717ca6b), closes #221

2.20.3 (2025-12-15)

Bug Fixes

• enable Harbor task filtering for smoketest support (#222) (f780188)

2.20.2 (2025-12-12)

Bug Fixes

• update --version flag to show correct version and research report date (#221) (5a85abb)

2.20.1 (2025-12-12)

Bug Fixes

• rename research report in data directory (b8ddfdc)

2.20.0 (2025-12-11)

Features

• convert AgentReady assessment to on-demand workflow (#213) (b5a1ce0), closes #191

2.19.1 (2025-12-10)

Bug Fixes

• add bounded retry logic for LLM rate limit handling (#205) (6ecb786), closes #104
• make E2E test timeouts configurable and add sensitive directory test (#206) (27e87e5), closes #104 #192

2.19.0 (2025-12-10)

Features

• add Memory MCP server allow list to repository settings (#203) (41d87bb)

2.18.0 (2025-12-10)

Features

• add Harbor Terminal-Bench comparison for agent effectiveness (#199) (a56e318)

2.17.0 (2025-12-10)

Features

• enhance assessors with multi-language support and security (#200) (85712f2), closes #10
• Harbor framework integration for Terminal-Bench evaluations (#202) (d73a8c8), closes #4 #178 #178

2.16.0 (2025-12-10)

Features

• Redesign homepage features with two-column layout and research links (#189) (570087d), closes #187

2.15.0 (2025-12-09)

Bug Fixes

• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish
• leaderboard workflow and SSH URL support (#147) (de28cd0)
• resolve 45 test failures across CLI, services, and assessors (#4) (3405142), closes #178 #178
• resolve broken links and workflow failures (#160) (fbf5cf7)
• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)
• add quay/quay to leaderboard (#162) (d6e8df0)
• Add weekly research update skill and automation (#145) (7ba17a6)
• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.14.1 (2025-12-05)

Bug Fixes

• resolve YAML syntax error in continuous-learning workflow (#172) (3d40fcc)

2.14.0 (2025-12-05)

Features

• container support (#171) (c6874ea)

2.13.0 (2025-12-04)

Features

• add quay/quay to leaderboard (#162) (d6e8df0)

2.12.3 (2025-12-04)

Bug Fixes

• skip PR comments for external forks to prevent permission errors (#163) (2a29fb8)

2.12.2 (2025-12-04)

Bug Fixes

• resolve broken links and workflow failures (#160) (fbf5cf7)

2.12.1 (2025-12-04)

Bug Fixes

• disable attestations for Test PyPI to avoid conflict (#155) (a33e3cd), closes pypa/#action-pypi-publish

2.12.0 (2025-12-04)

Features

• automate PyPI publishing with trusted publishing (OIDC) (#154) (71f4632), closes pypa/#action-pypi-publish

2.11.1 (2025-12-04)

Performance Improvements

• implement lazy loading for heavy CLI commands (#151) (6a7cd4e)

2.11.0 (2025-12-03)

Features

• Add weekly research update skill and automation (#145) (7ba17a6)

2.10.1 (2025-12-03)

Bug Fixes

• leaderboard workflow and SSH URL support (#147) (de28cd0)

2.10.0 (2025-12-03)

Features

• add ambient-code/agentready to leaderboard (#148) (621152e)

2.9.0 (2025-12-03)

Features

• Community Leaderboard for AgentReady Scores (#146) (fea0b3e)

2.8.1 (2025-11-25)

Bug Fixes

• add uv.lock to recognized lockfiles (#143) (a98dc87), closes #137

2.8.0 (2025-11-25)

Features

• assessors: implement File Size Limits assessor (Tier 2) (#141) (248467f)

2.7.1 (2025-11-24)

Bug Fixes

• assessors: search recursively for OpenAPI specification files (#127) (e2a5778)

2.7.0 (2025-11-24)

Features

• add interactive heatmap visualization for batch assessments (#136) (4d44fc3)

2.6.0 (2025-11-24)

Features

• Add SWE-bench experiment system for validating AgentReady impact (#124) (15edbba)

2.5.0 (2025-11-24)

Features

• Batch Report Enhancements + Bootstrap Template Inheritance (Phase 2 Task 5) (#133) (7762b23)

2.4.0 (2025-11-24)

Features

• Phase 2 Task 4 - Replace manual config validation with Pydantic (#134) (d83cf58)

2.3.0 (2025-11-24)

Features

• Standardize on Python 3.12+ with forward compatibility for 3.13 (#132) (84f2c46)

2.2.0 (2025-11-24)

Features

• Phase 1 Tasks 2-3 - Consolidate Reporter Base & Assessor Factory (#131) (8e12bf9), closes #122 #122 #122 #122 #122 #122 #122 #122

2.1.0 (2025-11-24)

Features

• Phase 1 Task 1 - Consolidate Security Validation Patterns (#129) (8580c45), closes #122 #122 #122 #122 #122 #122

2.0.0 (2025-11-24)

Features

• Rename 'learn' command to 'extract-skills' for clarity (#125) (64d6563), closes hi#scoring #123

BREAKING CHANGES

• Users must update scripts from 'agentready learn' to 'agentready extract-skills'. All flags and options remain identical.

1.29.0 (2025-11-23)

Features

• add GitHub organization scanning to assess-batch command (#118) (e306314)

1.28.0 (2025-11-23)

Features

• implement Phase 2 multi-repository assessment reporting (#117) (8da56c2), closes #69

1.27.2 (2025-11-23)

Bug Fixes

• Resolve 35 pytest failures through model validation and path sanitization improvements (#115) (4fbfee0)

1.27.1 (2025-11-23)

Bug Fixes

• Create shared test fixtures and fix Assessment schema issues (#114) (46baa13)

1.27.0 (2025-11-23)

Features

• Add comprehensive unit tests for utility modules (privacy.py and subprocess_utils.py) (#111) (9d3dece)

1.26.0 (2025-11-23)

Features

• Implement multi-repository batch assessment (Phase 1 of issue #68) (#74) (befc0d5)

1.25.0 (2025-11-23)

Features

• Auto-sync CLAUDE.md during semantic-release (#101) (36b48cb)

1.24.0 (2025-11-23)

Features

• Implement CodeSmellsAssessor stub (fixes #87) (#99) (f06b2a8)

1.23.0 (2025-11-23)

Features

• Implement BranchProtectionAssessor stub (fixes #86) (#98) (44c4b17)

1.22.0 (2025-11-23)

Features

• Implement OpenAPISpecsAssessor (fixes #80) (#97) (45ae36e)

1.21.0 (2025-11-23)

Features

• Implement StructuredLoggingAssessor (fixes #79) (#96) (2b87ca7)

1.20.0 (2025-11-23)

Features

• Implement SemanticNamingAssessor (fixes #82) (#95) (d87a280)

1.19.0 (2025-11-23)

Features

• Implement InlineDocumentationAssessor (fixes #77) (#94) (e56e570)

1.18.0 (2025-11-23)

Features

• Implement ConciseDocumentationAssessor (fixes #76) (#93) (c356cd5)

1.17.0 (2025-11-23)

Features

• Implement SeparationOfConcernsAssessor (fixes #78) (#92) (99bfe28)

1.16.0 (2025-11-23)

Features

• Implement CICDPipelineVisibilityAssessor (fixes #85) (#91) (e68285c)

1.15.0 (2025-11-23)

Features

• Implement IssuePRTemplatesAssessor (fixes #84) (#90) (819d7b7)

1.14.0 (2025-11-22)

Features

• Implement ArchitectureDecisionsAssessor (fixes #81) (#89) (9e782e5)

1.13.0 (2025-11-22)

Features

• Implement OneCommandSetupAssessor (fixes #75) (#88) (668ba1b)

1.12.4 (2025-11-22)

Bug Fixes

• Sanitize sensitive data in HTML reports (fixes #58) (#67) (6fbac76)

1.12.3 (2025-11-22)

Bug Fixes

• Add comprehensive subprocess security guardrails (fixes #57) (#66) (454b80e)

1.12.2 (2025-11-22)

Bug Fixes

• Add comprehensive YAML validation to prevent attacks (fixes #56) (#63) (31ecb3a)
• Correct datetime import pattern in RepomixService (#65) (517aa6e)
• Prevent API key exposure in environment and logs (fixes #55) (#64) (4d1d001)
• Prevent command injection in CommandFix.apply() (fixes #52) (#60) (49be28e)
• Prevent path traversal in LLM cache (fixes #53) (#61) (2bf052d)
• Prevent XSS in HTML reports (fixes #54) (#62) (7c60c69)

1.12.1 (2025-11-22)

Bug Fixes

• Resolve merge conflicts in CLI main module (#59) (9e0bf2d)

1.12.0 (2025-11-22)

Features

• Add security & quality improvements from code review (#49) (889d6ed)

1.11.0 (2025-11-22)

Features

• Add research report management CLI commands (#45) (e1be488), closes #7

1.10.0 (2025-11-22)

Features

• Add customizable HTML report themes with runtime switching (#46) (7eeaf84), closes hi#contrast #10

1.9.0 (2025-11-22)

Features

• add agentready-dev Claude agent specification (#44) (0f61f5c)

1.8.0 (2025-11-22)

Features

• implement report schema versioning (#43) (4c4752c)

1.7.1 (2025-11-22)

Bug Fixes

• correct Assessment field name in demo command (#41) (b48622d), closes #12

1.7.0 (2025-11-22)

Bug Fixes

• address P1 code quality issues from code review (#38) (77f2300)

Features

• Add security & quality improvements from code review (#40) (13cd3ca)
• redesign HTML report with dark theme and larger fonts (#39) (59f6702), closes #8b5cf6 #XX

1.6.3 (2025-11-22)

Bug Fixes

• address P1 code quality issues from code review (#37) (4be1d5e)

1.6.2 (2025-11-22)

Bug Fixes

• address P1 code quality issues from code review (#36) (5976332)

1.6.1 (2025-11-22)

Bug Fixes

• Update Claude workflow to trigger on @claude mentions (#35) (a8a3fab)

1.6.0 (2025-11-22)

Features

• Implement align subcommand for automated remediation (Issue #14) (#34) (06f04dc)

1.5.0 (2025-11-21)

Features

• Add Doubleagent - specialized AgentReady development agent (#30) (0ab54cb)

1.4.0 (2025-11-21)

Features

• Add Repomix integration for AI-friendly repository context generation (#29) (92bdde1), closes #24 #1 #25 hi#quality hi#scoring

1.3.0 (2025-11-21)

Features

• add report header with repository metadata (#28) (7a8b34a)

1.2.0 (2025-11-21)

Features

• Add automated demo command for AgentReady (#24) (f4e89d9), closes #1 #25 hi#quality hi#scoring

1.1.2 (2025-11-21)

Bug Fixes

• correct GitHub repository link in site navigation (5492278)

1.1.1 (2025-11-21)

Bug Fixes

• add repository checkout step to Claude Code Action workflow (17aa0cf)

1.1.0 (2025-11-21)

Features

• add Claude Code GitHub Action for @claude mentions (3e7224d)

1.0.4 (2025-11-21)

Bug Fixes

• set correct baseurl for GitHub Pages subdirectory deployment (c4db765)

1.0.3 (2025-11-21)

Bug Fixes

• exclude DEPLOYMENT.md and SETUP_SUMMARY.md from Jekyll build (9611207)

1.0.2 (2025-11-21)

Bug Fixes

• replace all remaining elif with elsif in developer-guide (73f16fc)

1.0.1 (2025-11-21)

Bug Fixes

• correct Liquid syntax in developer-guide (elif -> elsif) (75f3b1d)

1.0.0 (2025-11-21)

Bug Fixes

• Improve report metadata display with clean table format (ca361a4)
• P0 security and logic bugs from code review (2af2346)

Features

• Add Interactive Dashboard backlog item (adfc4c8)
• Add interactive HTML report generation (18664ea)
• add release pipeline coldstart prompt (#19) (9a3880c), closes #18
• Complete Phases 5-7 - Markdown reports, testing, and polish (7659623)
• Implement AgentReady MVP with scoring engine (54a96cb)
• implement automated semantic release pipeline (#20) (b579235)
• implement bootstrap command for GitHub infrastructure (0af06c4), closes #2

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[Unreleased]

Added

• Automated semantic release pipeline with conventional commits
• Release process documentation
• CHANGELOG generation from commit messages

---

This changelog is automatically generated by semantic-release