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/auditnpx skills add johnnichev/selectools --skill auditgit clone --depth 1 https://github.com/johnnichev/selectoolsWhat 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 | $0.00018 | $0.01032 |
| Opus 5 | $0.00009 | $0.00516 |
| Sonnet 5 | $0.00004 | $0.00206 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
audit 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 2d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Reference Audit
Live Counts (source of truth)
- Version (init.py): !
grep -m1 __version__ src/selectools/__init__.py - Version (pyproject.toml): !
grep -m1 "version" pyproject.toml - Tests: !
pytest tests/ --collect-only -q 2>/dev/null | tail -1 - Models: !
grep -c "ModelInfo(" src/selectools/models.py - Examples: !
ls examples/*.py | wc -l | tr -d ' ' - Module docs: !
ls docs/modules/*.md | wc -l | tr -d ' ' - Toolbox tools: !
grep -roh "@tool" src/selectools/toolbox/*.py | wc -l | tr -d ' ' - Observer events (sync): !
python3 -c "from selectools.observer import AgentObserver; print(len([m for m in dir(AgentObserver) if m.startswith('on_')]))" 2>/dev/null - Observer events (async): !
python3 -c "from selectools.observer import AsyncAgentObserver; print(len([m for m in dir(AsyncAgentObserver) if m.startswith('a_on_')]))" 2>/dev/null - StepTypes: !
python3 -c "from selectools.trace import StepType; print(len(StepType))" 2>/dev/null - Knowledge store backends: !
echo "4 (File, SQLite, Redis, Supabase)" - Last example: !
ls examples/*.py | tail -1
Audit Procedure
1. Version Consistency
Verify __init__.py version matches pyproject.toml version.
2. Count Audit
Search each file for hardcoded counts. Report any mismatch against live values.
Test count — check:
README.md,docs/index.md,CLAUDE.md,CONTRIBUTING.md,docs/CONTRIBUTING.md,landing/index.html
Example count — check:
README.md,CLAUDE.md
Model count — check:
README.md,docs/index.md,CLAUDE.md,docs/modules/MODELS.md
Observer event count — check:
CLAUDE.md,docs/modules/AGENT.md,docs/ARCHITECTURE.md,docs/QUICKSTART.md
StepType count — check:
CLAUDE.md,tests/test_phase1_design_patterns.py
3. Content Drift Audit
CLAUDE.md:
- Codebase Structure tree matches actual files (check for missing new files)
- TraceStep Types table has all StepType members
- Current Roadmap matches ROADMAP.md
- Observer counts match
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.
- 2d ago First seen · 111 lines · 18 tokens per session scan A c70b993e094d
audit is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 18 tokens to every session and 1,032 once invoked, about $0.0001 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 2026-08-30.
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.