Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/cookys/autopilot/doc-syncnpx skills add cookys/autopilot --skill doc-syncgit clone --depth 1 https://github.com/cookys/autopilotWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00201 | $0.02184 |
| Opus 5 | $0.00101 | $0.01092 |
| Sonnet 5 | $0.00040 | $0.00437 |
| Haiku 4.5 | $0.00020 | $0.00218 |
Grade A, and why
doc-sync scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
!`cat .claude/doc-drift-config.md 2>/dev/null || true` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc-Sync (Doc↔Code Drift Audit)
Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer prose doc alignment over implementation parity).
A dispatcher + methodology for detecting documentation that no longer matches the code. Report-only: it finds drift and grades it; it does not edit. You triage and fix per the policy below. Docs silently rot as code changes — this makes the rot visible on demand.
Project Config (auto-injected)
!cat .claude/doc-drift-config.md 2>/dev/null || true
!cat .claude/dispatch-config.md 2>/dev/null || true
If no doc-drift-config.md above, derive domains on the fly (see Domains) and tell the user
a config would make future runs sharper. Template:
project-config-template/doc-drift-config.md.
Two layers — deterministic gate + LLM discovery
Doc-sync has two layers with different reliability. Use both; don't confuse their roles.
Layer 1 — deterministic gate (RELIABLE; this is the stopping condition). A project-local script of zero-variance checks that always catch their class (links resolve, code-fences balance, version strings agree, every CLI subcommand appears in the docs, roadmap tables don't contradict). Run this FIRST, every time:
<gate_command from .claude/doc-drift-config.md> # e.g. node scripts/doc-drift-gate.js
Green = those classes are genuinely clean. This is gate-able (CI, pre-merge) because it has
no false negatives within its classes. If gate_command isn't configured, see "Bootstrapping
the gate" below.
Layer 2 — LLM sweep (DISCOVERY; NOT a gate). The scoped/full agent sweep below. It finds new drift classes the deterministic gate doesn't cover yet (semantic claims, prose nuance). It is non-deterministic — a "clean" sweep only means this sample found nothing, never that nothing exists.
⚠️ Do not loop the LLM sweep to zero. It does not converge: non-deterministic finders sample a different slice each round (latent errors surface stochastically), and the fixes themselves introduce new drift. Chasing literal-0 burns tokens without terminating. The reliable answer to "are the docs in sync?" is Layer 1 green, not "the sweep found nothing."
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 150 lines · 201 tokens per session scan A 1b28d78eb392
doc-sync is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 201 tokens to every session and 2,184 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…