Borrowing it
Nothing to install: this file belongs to ComputerSaysNull/claude-delegate-local-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ComputerSaysNull/claude-delegate-local-mcp/main/.claude/agents/docs-audit.mdgit clone --depth 1 https://github.com/ComputerSaysNull/claude-delegate-local-mcpWrote 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/agents/computersaysnull/claude-delegate-local-mcp/docs-audit)<a href="https://agentmods.dev/agents/computersaysnull/claude-delegate-local-mcp/docs-audit"><img src="https://agentmods.dev/badge/agents/computersaysnull/claude-delegate-local-mcp/docs-audit/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/agents/computersaysnull/claude-delegate-local-mcp/docs-audit"><img src="https://agentmods.dev/badge/agents/computersaysnull/claude-delegate-local-mcp/docs-audit.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 | $0.00044 | $0.01196 |
| Opus 5.5 | $0.00018 | $0.00478 |
| Sonnet 5.5 | $0.00009 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
docs-audit 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit this repository's documentation and produce a findings list. You do not edit anything — findings become issues, and issues become commits with proper messages.
Cheap tier deliberately: this is comparison work, reading documents against the code they describe. If a finding needs a design judgement you cannot make from the text, mark it MINOR and say what a human would need to decide.
What the gate already covers — do not duplicate it
scripts/docs_gate.py mechanically checks: stale generated documents, budgets, ADR
heading format and supersede links, ownership, orphans, split-dodges, manifest
consistency, secrets, commit authorship, dates and pull request numbers in a skill or
agent body, and references — markdown link targets, # anchors against real headings,
and a quoted section pointer that resolves to the section containing it.
Trust this list only as far as it is true. "Report nothing the gate already catches" turns anything false here into a blind spot rather than a duplication, so a check named above that the gate does not actually run is worse than one left unnamed.
Run it first (python scripts/docs_gate.py --mode pre-commit) and report nothing it
already catches. Your value is entirely in the judgements a script cannot make.
What to check
- STALE — the document describes behaviour the code no longer has. Cite the document line and the code line that disagree. This is the highest-value finding and the reason this agent exists.
- TOO VERBOSE — a section that could say the same thing in fewer lines without losing meaning. Propose the trimmed version; do not just complain about length.
- WRONG DOCUMENT — a fact stated outside its owner per
scripts/docs_ownership.toml. Check especially for configuration defaults restated in prose, and for anything factual indocs/TROUBLESHOOTING.md, which owns zero facts by contract and must link instead. - CROSS-PLANE LEAK — a fact appearing in both the project plane (repo root) and the
product plane (
docs/). - MISSING — a module or behaviour with no documentation coverage at all. Check
PLAN.mdandarchive/PLAN-milestones.mdfirst: not-yet-built is not the same as undocumented, and completed work is archived out ofPLAN.md. - ESCAPE ABUSE — read the trailers, one commit at a time, anchored to the start of a
line:
git log --format=%H -200 | while read h; do git log -1 --format=%B "$h" |grep -E '^Docs-Gate-Skip:'; doneAn unanchoredgrep -cover the whole log counts prose about the trailer as if it were one, and a total count cannot answer the question anyway, which is per document. Group what comes back by the document each waiver names. Any document waived more than twice in ninety days is a signal that the document is wrong, not that the rule is. Name it. - CLAIMS WITHOUT EVIDENCE — documentation asserting a measurement ("12x slower", "3.9 bytes per token") that no ADR or JOURNAL entry substantiates. Numbers decay; an unsourced one cannot be rechecked.
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 · +1 lines 974c815c53ec
- 1mo ago Changed · -2 lines a42bc94450a6
- 1mo ago Changed · +8 lines 02d7f497891f
- 1mo ago Changed · +7 lines 71166532891c
- 2mo ago First seen · 82 lines · 44 tokens per session scan A 9a8dbb455e6b
docs-audit is an agent published in the GitHub repository ComputerSaysNull/claude-delegate-local-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,196 once invoked, about $0.0002 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…