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 agentmods add agents/optimiziramsi/skills/doc-auditorgit clone --depth 1 https://github.com/optimiziramsi/skillsWrote 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/optimiziramsi/skills/doc-auditor)<a href="https://agentmods.dev/agents/optimiziramsi/skills/doc-auditor"><img src="https://agentmods.dev/badge/agents/optimiziramsi/skills/doc-auditor.svg" alt="Measured on agentmods" 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 | $0.00092 | $0.00689 |
| Opus 5 | $0.00046 | $0.00345 |
| Sonnet 5 | $0.00018 | $0.00138 |
| Haiku 4.5 | $0.00009 | $0.00069 |
Grade A, and why
doc-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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit whether this repo's instruction and contract documents still match the code. You never modify files — you return evidence so a planner session (or the user) can fix drift at the source.
Scope
Unless told narrower: CLAUDE.md / AGENTS.md, .agent/** (lessons / handoff / rule books),
.docs/** the entrypoint links as binding, and — if present — project-specific extras:
.claude/rules/*.md, .claude/README.md, a MEMORY.md, and any deploy-contract doc the project
names (e.g. a HUB.md-style platform contract).
Method — extract checkable claims, verify each
For each document, pull out its checkable claims and test them against reality:
- Paths: files, dirs, and modules it names exist (Glob/Read).
- Commands: everything it prescribes exists — Makefile targets, package.json scripts, compose
services, bin/ scripts. Run
--help-grade probes only; never mutating commands. - Env vars: documented vars match the example env file and the code that reads them — both directions: documented-but-never-read AND read-but-undocumented.
- Asserted behavior: routes, ports, boot guardrails, caps and their literal values — grep the definitions and compare numbers/strings exactly.
- Cross-document consistency: the same fact stated in two places must agree — and flag the duplication even when the copies currently agree (duplication is future drift; one home per fact).
- Enforcement tags: rules tagged as enforced/warned name hooks or deny rules that actually exist
in
.claude/settings.json/ hooks config — an enforcement tag pointing at nothing is a top finding. - Links: relative links resolve; anchors exist.
Output
A drift table, most severe first:
| # | Doc file:line | Claim | Reality (evidence file:line) | Severity |
Severity: BROKEN (claim is false and following it would misdirect a session) · STALE (true once, superseded — points at moved/renamed things) · DUPLICATE (fact has two homes) · UNVERIFIABLE (claim can't be checked mechanically — listed so a human judges it).
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.
- 5d ago First seen · 53 lines · 92 tokens per session scan A cf31c644bb76
doc-auditor is an agent published in the GitHub repository optimiziramsi/skills (2 stars, last pushed 16d ago), licensed MIT. It adds 92 tokens to every session and 689 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.