Cut AI-agent token waste ~90% — query a local SQLite structural index of your JS/TS/CSS codebase with SQL in one round-trip instead of 3–5 file reads. Symbols, imports, calls, components, CSS tokens, coverage, markers. CLI, MCP (21 tools), HTTP, GitHub Action, ESM API. 71 recipes; AST+resolver; SARIF/audit/baselines for CI.
Skill Claude CodeCodex
Full tier assignments, pairing conventions, and authoring checklist for .agents/ rules and skills. Use when creating or reviewing a rule or skill, deciding Tier 1 vs 2 vs 3, or auditing attachment cost.
Skill Claude CodeCodex
Which user-only agent workflow to run — grilling, docs-aware grilling, teaching, or meta authoring help.
Skill Claude CodeCodex
Audit a PR's structural choices against architecture-priming, the repo's own architecture.md, and any nested boundary configs. Use when the user says "audit this PR's architecture", "check the boundaries", "is this PR clean structurally", "post-merge review of.
Skill Claude CodeCodex
Prose depth for comments, JSDoc, and docs — concise comments, preserve existing source comments.
Skill Claude CodeCodex
Query codebase structure via SQLite instead of scanning files. Use when exploring code, finding where symbols are defined, tracing who imports what, listing components / hooks / CSS variables / deprecated symbols, walking dependency or call graphs, or auditing structural changes on a PR.
Skill Claude CodeCodex
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Skill Claude CodeCodex
Repo-wide docs framework — what docs/, docs/plans/, docs/research/, .agents/, or any other doc-bearing surface in this repo looks like, what lifecycle each doc follows, and how to keep cross-references intact when slimming or moving content. Use when authoring or editing any docs/, docs/plans/, docs/research/…
Skill Claude CodeCodex
Operationalises the docs-governance lifecycle on demand — produces a per-file Tier-A (keep verbatim) / Tier-B (slim + keep) / Tier-C (delete + lift) classification with evidence and an executable plan, then carries out the user's chosen actions. Use when the user says "clean up stale docs", "doc sweep", "audit docs…
Skill Claude CodeCodex
Voice, tone, and format for the public Codemap docs (apps/docs, built with Blume). Use when authoring or editing apps/docs prose — landing, guides, concepts, recipes, reference, generated API — or deciding headline grammar, benefit framing, peer framing, or anti-pitch wording.
Skill Claude CodeCodex
Build and sharpen the project's domain terminology inline or via a batch glossary scan. Use when pinning down ubiquitous language, recording a domain decision, grill-with-docs crystallises a term, or refreshing docs/glossary.md.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude CodeCodex
Grill a plan or design and update repo docs as decisions crystallise. Invokes grilling + domain-modeling inline; user-invoked only.
Skill Claude CodeCodex
Relentlessly grill plans until shared understanding. Use when stress-testing a design or another skill delegates grilling.
Skill Claude CodeCodex
Bring a branch to pristine, maximum production readiness without changing PR intent — spawn parallel Task subagents (never inline review), fix in-bounds findings, loop autonomously until clean or pass cap, then report once. Use after a tracer-bullet commit (lite), before PR is done (full), on "harden", "harden-pr"…
Skill Claude CodeCodex
Find deepening opportunities in the codebase, informed by the domain language in docs/glossary.md and the architecture in docs/architecture.md. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
Skill Claude CodeCodex
Triage and fact-check PR review comments against the actual codebase, project rules, and skills. Use when the user asks to address PR comments, respond to reviewer feedback, check if a comment is correct, fact-check a reviewer's claim, decide which comments to push back on, or sort hallucinated suggestions from real…
Skill Claude CodeCodex
The product north-star — four Codemap tenets (structural over semantic, predicate-as-API, local-first / agent-native surfaces, honest scope). Use when making a design, API, or architecture decision, evaluating a trade-off, justifying a feature, or writing/reviewing a docs/plans entry.
Skill Claude CodeCodex
Test-driven development with vertical tracer-bullet slices. Use when building test-first, red-green-refactor, or when the user mentions TDD.
Skill Claude CodeCodex
Structured multi-session teaching — missions, lessons, retrieval practice.
Skill Claude CodeCodex
Codemap feature layers and worked tracer-bullet examples — vertical slices for new source extensions, SQLite schema changes, and CLI flags. Use when planning a feature as a tracer bullet and deciding slice boundaries across CLI/parser/db/test/docs layers.
Skill Claude CodeCodex
Cut AI tells from any writing. Must always apply.
Skill Claude CodeCodex
Keep apps/docs in sync with merged product changes. On each run, audit recently merged PRs against docs content, update only drifted pages, regenerate API MDX when public exports/JSDoc drifted, verify with blume validate/check/build/audit, and open or update a docs/ PR — or report a clean no-op.
Skill Claude CodeCodex
Delta-driven dependency upgrades — a script gathers the evidence, you read the artifact and judge. Use when the user asks to upgrade, bump, or CVE-audit dependencies.
Skill Claude CodeCodex
Per-file verification checklist — lint-staged and package.json scripts after each milestone.