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 skills/johnnichev/selectools/doc-audit-skillnpx skills add johnnichev/selectools --skill doc-audit-skillgit clone --depth 1 https://github.com/johnnichev/selectoolsWrote 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/johnnichev/selectools/doc-audit-skill)<a href="https://agentmods.dev/skills/johnnichev/selectools/doc-audit-skill"><img src="https://agentmods.dev/badge/skills/johnnichev/selectools/doc-audit-skill.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 | $0.00000 | $0.00764 |
| Opus 5 | $0.00000 | $0.00382 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
doc-audit-skill 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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Audit
Deploy parallel QA sub-agents to find documentation inconsistencies, stale counts, missing references, and improvement opportunities. Then fix everything found.
Resolve Scope
all→ deploy 4 agents (one per category below)counts→ 1 agent: stale numbers across all docscontent→ 1 agent: missing features, examples, outdated descriptionslinks→ 1 agent: broken links, missing nav entries, dead referencesquality→ 1 agent: unclear writing, missing code examples, incomplete sections
Agent Template
Each agent reads ALL documentation files and cross-references against the actual codebase.
Agent 1: Count Consistency
Verify these numbers match reality across ALL docs (README.md, CLAUDE.md, docs/index.md, CHANGELOG.md, CONTRIBUTING.md, landing/index.html, docs/ARCHITECTURE.md, docs/QUICKSTART.md):
- Test count (run
pytest --co -qto get actual) - Example count (run
ls examples/*.py | wc -l) - Model count (grep MODELS_BY_ID or count ModelInfo)
- StepType count (count enum members)
- Observer event count (count methods on AgentObserver/AsyncAgentObserver)
- Tool count (count toolbox tools)
- Evaluator count
- Provider count
Agent 2: Content Completeness
For EVERY feature in the codebase, verify it's mentioned in:
- README.md "What's Included" / "Why Selectools" / feature table
- README.md examples section (all 61 examples should be referenced or at least the count)
- docs/index.md feature table
- docs/QUICKSTART.md (if user-facing)
- CLAUDE.md codebase structure (every source file)
Check specifically:
- Are Pipeline, @step, parallel(), branch() in README feature table?
- Are all 61 examples listed or counted?
- Are v0.18.0 features (orchestration + pipelines) prominently featured?
- Is the Apache-2.0 license mentioned everywhere it should be?
- Are all providers mentioned (OpenAI, Anthropic, Gemini, Ollama, Fallback)?
Agent 3: Link & Navigation Audit
- Run
mkdocs buildand report ALL warnings - Check every
[link](path)in README.md resolves - Check mkdocs.yml nav covers all docs/modules/*.md files
- Check CHANGELOG.md is synced with docs/CHANGELOG.md
- Check CONTRIBUTING.md is synced with docs/CONTRIBUTING.md
- Verify GitHub URLs point to correct repo
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.
- 3d ago First seen · 84 lines · 0 tokens per session scan A 3cf14c7c94a0
doc-audit-skill is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 764 tokens. 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 2026-08-30.
Other skills, from other repositories
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
guardrails-docs-access
Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.
Policy Configuration Hierarchy
How guardrail policies cascade from organization through team to project level.
Content Safety & Filtering
Topic-based content filtering to block harmful or unauthorized content in agent output.
Output Security & Secret Scanning
Prevent sensitive data (secrets, credentials, PII) from leaking in agent output.
Sandbox Isolation
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.