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/skills/docs-audit-dispatch/SKILL.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/skills/computersaysnull/claude-delegate-local-mcp/docs-audit-dispatch)<a href="https://agentmods.dev/skills/computersaysnull/claude-delegate-local-mcp/docs-audit-dispatch"><img src="https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/docs-audit-dispatch/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/computersaysnull/claude-delegate-local-mcp/docs-audit-dispatch"><img src="https://agentmods.dev/badge/skills/computersaysnull/claude-delegate-local-mcp/docs-audit-dispatch.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 | $0.00074 | $0.02137 |
| Opus 5 | $0.00037 | $0.01069 |
| Sonnet 5 | $0.00015 | $0.00427 |
| Haiku 4.5 | $0.00007 | $0.00214 |
Grade A, and why
docs-audit-dispatch 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 yesterday.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation audit runbook
Thirteen passes complete one audit. Running the same thirteen every time is what makes two audits comparable, so run them all and record the ones you skipped.
Audit progress:
- [ ] 1 STALE docs/ARCHITECTURE.md vs context, admission, slots
- [ ] 2 STALE docs/ARCHITECTURE.md vs transcript, server
- [ ] 3 STALE docs/DISPATCH.md vs loop, turn and history sections
- [ ] 4 STALE docs/DISPATCH.md vs backends, wire and retry sections
- [ ] 5 STALE docs/AGENTS.md
- [ ] 6 STALE docs/MODELS.md + docs/TROUBLESHOOTING.md
- [ ] 7 TOO VERBOSE project plane
- [ ] 8 TOO VERBOSE product plane
- [ ] 9 WRONG DOCUMENT every document
- [ ] 10 CROSS-PLANE LEAK every document
- [ ] 11 MISSING every document
- [ ] 12 CLAIMS every document
- [ ] 13 ESCAPE ABUSE history only
Before you start
- Run
python scripts/docs_gate.py --mode pre-commitand keep the output. A pass cannot obtain it — the sandbox denies both the gate and shelled git — so paste it into every task. - Note the commit count the gate reports. It goes in the record's opening line.
The passes
Dispatch with delegate_to_agent_readonly, agent docs-audit-local, and pass project as
the repository root or the agent is not found. Generated documents (docs/CONFIGURATION.md,
docs/TOOLS.md) are never audited — a generator already guarantees them.
| # | Class | Prefetch in files[] |
Effort |
|---|---|---|---|
| 1 | STALE | docs/ARCHITECTURE.md + context.py, admission.py, slots.py |
high |
| 2 | STALE | docs/ARCHITECTURE.md + transcript.py, server.py |
high |
| 3 | STALE | docs/DISPATCH.md, the turn and history sections + loop.py |
high |
| 4 | STALE | docs/DISPATCH.md, the wire and retry sections + backends/*.py |
high |
| 5 | STALE | docs/AGENTS.md + agents.py, paths.py, sandbox.py |
high |
| 6 | STALE | docs/MODELS.md, docs/TROUBLESHOOTING.md + registry.py, doctor.py |
high |
| 7 | TOO VERBOSE | CLAUDE.md, CONTRIBUTING.md, README.md |
high |
| 8 | TOO VERBOSE | every hand-written docs/*.md |
high |
| 9 | WRONG DOCUMENT | every document, plus config.py |
high |
| 10 | CROSS-PLANE LEAK | every document | high |
| 11 | MISSING | every document, plus PLAN.md and archive/PLAN-milestones.md |
high |
| 12 | CLAIMS | every document, plus DECISIONS.md and JOURNAL.md |
high |
| 13 | ESCAPE ABUSE | nothing | low |
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.
- yesterday First seen · 161 lines · 74 tokens per session scan A e8184d7e61c9
docs-audit-dispatch is a skill published in the GitHub repository ComputerSaysNull/claude-delegate-local-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 2,137 once invoked, about $0.0004 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 2026-09-11.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
magpie-security-issue-import-from-md
Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.