fix: correct mgrep misattribution in Everything Claude Code evaluation
Issue: - Incorrectly claimed Everything Claude Code contained "mgrep (50% token reduction)" tool - No such tool exists in affaan-m/everything-claude-code (verified via WebFetch + repo search) - Confused mgrep (mixedbread-ai semantic search) with non-existent token reduction tool Files corrected: - docs/resource-evaluations/015-everything-claude-code-github-repo.md (14 occurrences removed) - machine-readable/reference.yaml:724 (unique patterns list updated) - guide/ultimate-guide.md:14821 (replaced with verified patterns) - CHANGELOG.md (v3.17.0 and v3.15.0 entries updated) Verified patterns now documented: - hookify (conversational hooks) - pass@k metrics (formal verification) - sandboxed subagents (tool restrictions) - strategic compaction skills (context management) Impact: Maintains guide accuracy, prevents user confusion Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
parent
7957dda29c
commit
34b7376408
4 changed files with 51 additions and 41 deletions
|
|
@ -721,7 +721,7 @@ ecosystem:
|
|||
stars: "31.9k"
|
||||
verified: "2026-01-27"
|
||||
created: "2026-01-18"
|
||||
unique: ["mgrep (50% token reduction)", "hookify (conversational hooks)", "pass@k metrics", "Plugin ecosystem", "Sandboxed subagents"]
|
||||
unique: ["hookify (conversational hooks)", "pass@k metrics", "Plugin ecosystem", "Sandboxed subagents", "Strategic compaction skills"]
|
||||
evaluation: "docs/resource-evaluations/015-everything-claude-code-github-repo.md"
|
||||
score: "5/5 (CRITICAL)"
|
||||
positioning: "Complementary to Ultimate Guide (production configs vs educational content)"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue