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 | $0.02694 |
| Opus 5.5 | $0.00030 | $0.01078 |
| Sonnet 5.5 | $0.00015 | $0.00539 |
| Haiku 4.5 | $0.00007 | $0.00269 |
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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation audit runbook
Sixteen passes complete one audit. Running the same sixteen every time is what makes two audits comparable, so run them all and record the ones you skipped. Pass 14 is the one you run yourself.
Audit progress:
- [ ] 1 STALE docs/ARCHITECTURE.md vs context, admission, slots
- [ ] 2 STALE docs/ARCHITECTURE.md vs transcript, server, tools
- [ ] 3 STALE docs/DISPATCH.md vs loop, turn and history sections
- [ ] 4 STALE docs/DISPATCH.md vs backends and loop, wire and retry sections
- [ ] 5 STALE docs/AGENTS.md vs agents, paths, sandbox, tools
- [ ] 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
- [ ] 14 FILED ALREADY the hand-off notebook (run by the caller, not delegated)
- [ ] 15 NARRATIVE .claude/ bodies — skills and agents
- [ ] 16 STALE docs/ARCHITECTURE.md vs the viewer
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, tools.py; split it, and also pair sandbox.py + wsl.py, the CLI modules (main.py, init.py, install_skills.py, provision.py, run_task.py), and ledger.py + handles.py + registry.py |
high |
| 3 | STALE | docs/DISPATCH.md, the turn and history sections + loop.py, and backends/base.py, which holds the turn-limit banner |
high |
| 4 | STALE | docs/DISPATCH.md, the wire and retry sections + backends/*.py, and loop.py, which holds the retry |
high |
| 5 | STALE | docs/AGENTS.md + agents.py, paths.py, sandbox.py, tools.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, archive/PLAN-milestones.md and scripts/docs_ownership.toml |
high |
| 12 | CLAIMS | every document; the task names DECISIONS.md, JOURNAL.md and CHANGELOG.md to search, not prefetch |
high |
| 13 | ESCAPE ABUSE | nothing | low |
| 14 | FILED ALREADY | the hand-off notebook — not delegable, see below | — |
| 15 | NARRATIVE | every .claude/agents/*.md, .claude/delegate-agents/*.md, .claude/skills/*/SKILL.md and .claude/skills/*/references/*.md |
high |
| 16 | STALE | docs/ARCHITECTURE.md + src/claude_delegate_local/watch.py |
high |
What ships with it
2 files 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.
- 4d ago Changed 0eb197dea93d
- 23d ago Changed · +4 lines dc1a1aead9e6
- 29d ago Changed 87f49572a587
- 1mo ago Changed · -87 lines 9d2474550b48
- 1mo ago Changed · +1 lines 38d1b53af893
- 1mo ago Changed · +29 lines 96847375e75d
- 1mo ago Changed · +44 lines b4256845ae2a
- 1mo ago Changed · +32 lines c3799076c33d
- 1mo ago 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 2,694 once invoked, about $0.0003 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 2026-09-11.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
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…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.