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/nicograef/handbook/verify-docsnpx skills add nicograef/handbook --skill verify-docsgit clone --depth 1 https://github.com/nicograef/handbookWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nicograef/handbook/verify-docs)<a href="https://agentmods.dev/skills/nicograef/handbook/verify-docs"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/verify-docs.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00112 | $0.02677 |
| Opus 5 | $0.00056 | $0.01339 |
| Sonnet 5 | $0.00022 | $0.00535 |
| Haiku 4.5 | $0.00011 | $0.00268 |
Grade A, and why
verify-docs scanned grade A with 0 findings 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 today.
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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Docs
Decide whether each documented claim is true, and fix the ones that are not.
Why this runs in its own session
The session that just rewrote the docs is its worst auditor:
- Anchored on its own dispositions.
- Removal-biased — its context went to what to cut, not to what is true.
- Survivorship — it reads a surviving line as verified because it chose to keep it.
So this skill starts from a commit, not a conversation. Its only inputs:
- The files on disk.
- The sources those files describe.
- The handoff commit message.
- Nothing else — what it cannot re-derive from those does not exist for it.
sources.md holds the ground-truth classes, the evidence rule, lane precedence, and the anti-patterns. Read it before step 2 — the lane taxonomy is needed to extract claims, not just to verify them.
Workflow
1. Scope and baseline
Arguments: $ARGUMENTS.
| Argument | Effect |
|---|---|
path ... |
Narrows the corpus |
since <ref> |
Limits it to docs touched since that ref |
report-only |
Skips step 6 and the commit in step 7 |
- Require a clean working tree —
git status --porcelainmust be empty. - If the tree is dirty, stop and say so.
- That guarantees the corpus is committed, and leaves the fixes as a diff of their own.
- Record the HEAD sha. The report cites the exact state that was audited.
- Run the repo's own checks now —
make check, a link linter, a docs build. - They mechanize dead relative links and index-vs-disk comparison far better than a reading pass.
- Running them first stops step 2 extracting as claims what a passing script already settled.
- Keep the output; it is the artifact.
- Read the handoff commit message. A
/distillrun lists its unsettled claims (FLAGs) in the commit body. - Those are this run's highest-priority claims — a prior session already suspected them.
- They set priority, never scope.
- Carry the list to step 7: an inherited FLAG is always reported by name, whatever it resolves to.
- Enumerate the corpus —
git ls-files '*.md' '*.mdx' '*.rst', plus the comment-bearing sources and configs in scope. - Record its total line count.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -3 lines 254e396a206c
- 4d ago First seen · 239 lines · 112 tokens per session scan A 6a29ab004344
verify-docs is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 2,677 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…