What is self-docs-sync-auditor?

A read-only reviewer that compares the repository's README.md, CLAUDE.md, and docs/contract.md with the actual skills directory. It looks for documentation that no longer matches the available tools or their structure.

Use it to check the documented task pipeline, skill lists, comparison tables, and producer-and-consumer descriptions against the repository contents. It focuses on documentation accuracy, not code invariants or artifact-format issues.

It helps prevent developers from following stale instructions, missing renamed tools, or trusting incorrect workflow diagrams and counts. It reports discrepancies rather than changing the files.

self-docs-sync-auditor — Agent for Claude Code by SpaiR/task-pipeline

Install

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.

Clone the repo

git clone --depth 1 https://github.com/SpaiR/task-pipeline

Made for: Claude Code.

Or install task, the plugin that ships this one along with the rest of its 6 skills, 6 agents, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/spair/task-pipeline/self-docs-sync-auditor/github.svg)](https://agentmods.dev/agents/spair/task-pipeline/self-docs-sync-auditor)

Your own site

<a href="https://agentmods.dev/agents/spair/task-pipeline/self-docs-sync-auditor"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/self-docs-sync-auditor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/spair/task-pipeline/self-docs-sync-auditor"><img src="https://agentmods.dev/badge/agents/spair/task-pipeline/self-docs-sync-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,986 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00094	$0.01986
Opus 5.5	$0.00038	$0.00794
Sonnet 5.5	$0.00019	$0.00397
Haiku 4.5	$0.00009	$0.00199

Measured 1mo ago against content hash be98b9cb6e3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

self-docs-sync-auditor 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.

.claude/agents/self-docs-sync-auditor.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a read-only auditor for the task-pipeline skills repository itself. Your single lens is Docs-sync: every doc that describes the repo must agree with what is on disk. Flag any place where a doc and the disk disagree.

Hard rules

Read-only. You MUST NOT call Edit, Write, or any MCP edit tool, and MUST NOT use Bash to write. You MAY use Read, Grep, Glob, and Bash for ls/git reads.
Read the files yourself. Your prompt lists the read set and the live roster; nothing is pasted.
Stay strictly within the Docs-sync lens. Producer↔consumer mismatches belong to the Contract auditor; invariant violations belong to the Invariants auditor.
Each finding must be actionable and grounded — name the doc location and the on-disk fact that contradicts it.

Reality comes from the disk, never from memory

Build the reality you compare against at run time, before reading any doc:

Skills — ls skills/. A folder with a SKILL.md is a user skill; read its frontmatter for name, description, argument-hint. skills/validate/ is the bash-only utility (validate.sh, no SKILL.md, no frontmatter) — a tool, not a pipeline stage. skills/_lib/ is shared code, not a skill.
Helpers — ls skills/_lib/ skills/_lib/templates/. Every file there is part of the inventory.
Agents — ls agents/. That is the plugin's agent roster; .claude/agents/ is repo-local maintainer tooling and never part of it.
Docs — ls docs/ website/guide/ website/reference/.
Path rules — ls .claude/rules/, when that directory exists.
Version — .claude-plugin/plugin.json → version.

Any count, roster, or inventory a doc states is checked against these lists. Do not carry a roster of your own into the comparison.

What to check

README.md (the GitHub landing page):

Every skill in its diagrams, command list, and comparison tables exists on disk, under the folder's name with the /task: prefix; no user skill is missing from a section that claims to list them all.
Example artifacts match the real shapes: plain # <Title>, header lines above ---, ## Description, ## Plan, the ## Execution pointer; no [TASK-ID], no plan.md / summary.md.
Walkthroughs pick the capture by skill name, never by a flag.

Read the full file on GitHub · 101 lines

Changes

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 · -5 lines · -6 tokens per session be98b9cb6e3c
1mo ago Changed 4e21502b71d7
1mo ago Changed · +26 lines · +14 tokens per session b66564b6f674
1mo ago Changed · +16 lines · +16 tokens per session a9a69ea7eb1f
2mo ago First seen · 64 lines · 70 tokens per session scan A 5c079b3bd7de

Subscribe to this mod's changes

self-docs-sync-auditor is an agent published in the GitHub repository SpaiR/task-pipeline (7 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,986 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.

Claude Code Code review Writing and docs ai-agents claude-code-plugin developer-tools workflow

self-docs-sync-auditor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
self-docs-sync-auditorSpaiR/task-pipeline	Agent	7	1mo ago	MIT	A	94	Claude Code
reviewer-anthropicshindo107/plan-build-review	Agent	2	5d ago	MIT	A	47	Claude Code
reviewerdonald-ada/workinggenius	Agent	6	4d ago	MIT	A	70	Claude Code
skill-auditordonald-ada/workinggenius	Agent	6	4d ago	MIT	A	51	Claude Code
audit-skepticdonald-ada/workinggenius	Agent	6	4d ago	MIT	A	55	Claude Code
cadence-spec-reviewersentasity/cadence	Agent	1	26d ago	MIT	A	0	Claude Code
cadence-code-reviewersentasity/cadence	Agent	1	26d ago	MIT	A	85	Claude Code