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 skills add akira993/doc-audit-harness --skill initgit clone --depth 1 https://github.com/akira993/doc-audit-harnessWrote 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/akira993/doc-audit-harness/init)<a href="https://agentmods.dev/skills/akira993/doc-audit-harness/init"><img src="https://agentmods.dev/badge/skills/akira993/doc-audit-harness/init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/akira993/doc-audit-harness/init"><img src="https://agentmods.dev/badge/skills/akira993/doc-audit-harness/init.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00101 | $0.04986 |
| Opus 5.5 | $0.00040 | $0.01994 |
| Sonnet 5.5 | $0.00020 | $0.00997 |
| Haiku 4.5 | $0.00010 | $0.00499 |
Grade A, and why
init 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 1mo 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.
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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docaudit:init — bootstrap a repo's doc-audit adapter
Creates ${CLAUDE_PROJECT_DIR}/.claude/doc-audit.json for a repo that has none.
Generative but additive: you may CREATE new config/state files; you must NOT edit
or rewrite any existing doc. Always propose the draft and get explicit user approval
before writing. SD="${CLAUDE_SKILL_DIR%/init}/audit" (the audit skill dir holding
the shared scripts).
If .claude/doc-audit.json already exists, normally stop and tell the user (offer
/docaudit:audit instead) — do not overwrite it. Exceptions: with --harness, continue through
Step 1 and change only harness and, when required, docAuditCommands; with
--import-audit-scope, follow only the import flow below. Preserve every other config key.
--refresh is valid only with --harness and is delegated to
scaffold.py --harness --refresh. --reask forces the harness choice even when harness is
already configured. Without --reask, never ask again for an existing harness key. If its
state is installed, --harness may create missing generated files; for any other configured
state, explain the state and require --reask before changing the decision.
With --import-audit-scope, an existing config is permitted. Bind AUDIT_SCOPE_PATH from config auditScope.path, defaulting to .claude/audit-scope.json, then run AUDIT_SCOPE_CHECK="$(python3 "$SD/scripts/import-audit-scope.py" --repo-root "$CLAUDE_PROJECT_DIR" --config "$CFG" --scope "$AUDIT_SCOPE_PATH" --check --json)". Show diff.missing, diff.extra, translated, skippedNoImpact, configSha, and scopeSha, then ask with AskUserQuestion. Only after approval bind CONFIG_SHA="$(python3 -c 'import json,sys; print(json.loads(sys.argv[1])["configSha"])' "$AUDIT_SCOPE_CHECK")" and SCOPE_SHA="$(python3 -c 'import json,sys; print(json.loads(sys.argv[1])["scopeSha"])' "$AUDIT_SCOPE_CHECK")", then run python3 "$SD/scripts/import-audit-scope.py" --repo-root "$CLAUDE_PROJECT_DIR" --config "$CFG" --scope "$AUDIT_SCOPE_PATH" --write --expect-config-sha "$CONFIG_SHA" --expect-scope-sha "$SCOPE_SHA". Do not write without approval.
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.
- 1mo ago Changed · +12 lines c4820e180520
- 1mo ago First seen · 227 lines · 101 tokens per session scan A 74f9f6430527
init is a skill published in the GitHub repository akira993/doc-audit-harness (3 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 4,986 once invoked, about $0.0004 per session on Opus 5.5. 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
stale-docs
Use when a stale-docs hook or /stale-docs audit reports documentation referencing code that was just changed. Repairs the affected docs against the current source, from a one-word patch up to a full rewrite, staged in the same commit as the code change.
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or…
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
chief-revenue-officer
Owns the revenue engine end to end: sales, monetization, pricing, customer success, retention, and partnerships. Use this for pricing and packaging decisions, sales strategy and coverage, forecast and pipeline health, churn and expansion, partner and channel strategy, or when marketing-sourced demand is not…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…