feat: vendor scoring with structured storage and audit trail#147
Closed
tractorjuice wants to merge 4 commits intomainfrom
Closed
feat: vendor scoring with structured storage and audit trail#147tractorjuice wants to merge 4 commits intomainfrom
tractorjuice wants to merge 4 commits intomainfrom
Conversation
Add /arckit:search for keyword, type, and requirement ID search across all project artifacts. Includes pre-processing hook that builds a search index on invocation — no persistent index needed. - search-scan.mjs: UserPromptSubmit hook extracts document metadata - search.md: Command with ranked results and filter syntax - Supports --type, --project, --id filters and combinations Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Run converter to generate Codex/OpenCode/Gemini extension formats - Copy guide to plugin directory (arckit-claude/docs/guides/) - Update DEPENDENCY-MATRIX.md (58 commands, utility exclusion note) - Update README.md, docs/README.md (command count, table entries) - Update commands.html and index.html (command count, table row) - Update CHANGELOG.md with search command entry - Update command counts (57→58) across all extensions, plugin, guides, marketplace.json, and getting-started.html Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add /arckit:score for persistent, auditable vendor scoring:
- score vendor: Score against EVAL criteria with 0-3 rubric
- compare: Side-by-side weighted comparison with sensitivity analysis
- audit: Chronological scoring history for governance
Scores stored in projects/{id}/vendors/scores.json for structured
querying. Includes PreToolUse validator for score integrity.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Cherry-picked from PR #145 with fixes: - Use parseHookInput() instead of manual stdin parsing - Add evidence non-empty validation to score-validator - Merge score-validator into existing Write matcher block - Run converter for Codex/OpenCode/Gemini extension formats - Copy guide to plugin directory - Update DEPENDENCY-MATRIX.md (59 commands, Tier 5 Procurement) - Update all docs and command counts (58→59) - Add CHANGELOG entry Supersedes #145. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
6 tasks
7 tasks
Owner
Author
|
Merged into daily branch — see #148 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds
/arckit:scorefor persistent, auditable vendor scoring — completing the procurement workflow chain (evaluate → score → compare → sow).Cherry-picked from #145 with code fixes and complete documentation.
Code fixes from review
parseHookInput()from hook-utils.mjs (consistent with all other hooks)evidencenon-empty validation to score-validatorDeliverables added
Supersedes #145 (fork PR). Depends on #146 (search command) merging first.
Test plan
🤖 Generated with Claude Code