Cursor rule Cursor
Dry-run the add-feature workflow for a proposed feature — friction report and per-phase readiness score, without writing code.
not rated 3 yesterday A 23 tokens
original Apache-2.0
Cursor rule Cursor
Audit every ai/ file for gaps, stale placeholders, and inconsistencies after cold-start. Produces a prioritized findings report.
not rated 3 yesterday A 25 tokens
original Apache-2.0
Cursor rule Cursor
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
not rated 3 yesterday A 41 tokens
original Apache-2.0
Cursor rule Cursor
Review a completed change against its spec in fresh context — evidence-based checks, severity-ranked findings, a written verdict for the human's merge decision.
not rated 3 yesterday A 29 tokens
original Apache-2.0
Cursor rule Cursor
Holistic assessment of the AI knowledge layer on a 5-level maturity scale; flags agent-blocking gaps.
not rated 3 yesterday A 22 tokens
original Apache-2.0
add-feature
30Command GitHub Copilot
Implement a feature using the knowledge layer — spec first, surgical diffs, tests before done, knowledge updated after.
not rated 3 yesterday A 23 tokens
original Apache-2.0
Command GitHub Copilot
Deep, judgement-based adversarial code audit — hunts for stale cross-references, unescaped interpolation, platform gaps, generated-file ownership conflicts, and cross-module consistency rot that no mechanical check can catch. Read-only; writes a dated findings report.
not rated 3 yesterday A 49 tokens
original Apache-2.0
check-drift
32Command GitHub Copilot
Run verification and drift checks on the AI knowledge-base to identify missing documentation or stale references.
not rated 3 yesterday A 18 tokens
original Apache-2.0
cold-start
33Command GitHub Copilot
Bootstrap the ai/guide maps and diagrams (the cold-start pass). Drafts everything as [inferred] for a human to audit.
not rated 3 yesterday A 28 tokens
original Apache-2.0
Command GitHub Copilot
Deep-mine the source code to discover implemented features; writes ai/analysis/FEATURECATALOG.md.
not rated 3 yesterday A 21 tokens
original Apache-2.0
fix-bug
35Command GitHub Copilot
Fix a bug using the knowledge layer — reproduce first, failing regression test, root cause, surgical fix, review and ledger entry after.
not rated 3 yesterday A 27 tokens
original Apache-2.0
Command GitHub Copilot
Dry-run the add-feature workflow for a proposed feature — friction report and per-phase readiness score, without writing code.
not rated 3 yesterday A 23 tokens
original Apache-2.0
Command GitHub Copilot
Audit every ai/ file for gaps, stale placeholders, and inconsistencies after cold-start. Produces a prioritized findings report.
not rated 3 yesterday A 25 tokens
original Apache-2.0
Command GitHub Copilot
Diagnostic gate that checks CLAUDE.md and AGENTS.md for completeness, consistency, and stale artifacts — run right after /cold-start and before /add-feature. Read-only; produces a findings report.
not rated 3 yesterday A 41 tokens
original Apache-2.0
Command GitHub Copilot
Review a completed change against its spec in fresh context — evidence-based checks, severity-ranked findings, a written verdict for the human's merge decision.
not rated 3 yesterday A 29 tokens
original Apache-2.0
Command GitHub Copilot
Holistic assessment of the AI knowledge layer on a 5-level maturity scale; flags agent-blocking gaps.
not rated 3 yesterday A 22 tokens
original Apache-2.0
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: