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/docsnpx skills add johnnichev/selectools --skill docsgit 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 | $0.00020 | $0.00810 |
| Opus 5 | $0.00010 | $0.00405 |
| Sonnet 5 | $0.00004 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
docs 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 yesterday.
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.
Documentation Writing
Write or update documentation for: $ARGUMENTS
Live Counts (source of truth — update all docs to match)
- Models: !
grep -c "ModelInfo(" src/selectools/models.py - Tests: !
pytest tests/ --collect-only -q 2>/dev/null | tail -1 - Examples: !
ls examples/*.py | wc -l | tr -d ' ' - Module docs: !
ls docs/modules/*.md | wc -l | tr -d ' ' - StepTypes: !
python3 -c "from selectools.trace import StepType; print(len(StepType))" 2>/dev/null - Observer events: !
python3 -c "from selectools.observer import AgentObserver; import inspect; print(len([m for m in dir(AgentObserver) if m.startswith('on_')]))" 2>/dev/null
Documentation Checklist (ALL required for every feature)
1. Module Documentation
Create docs/modules/<FEATURE>.md with:
# Feature Name
**Added in:** vX.Y.Z
**File:** `src/selectools/module.py`
**Classes:** `ClassName`
## Overview
Brief description.
## Quick Start
Minimal working example.
## API Reference
Class/method signatures with parameter tables.
## See Also
Links to related module docs.
2. Navigation Entry
Add to mkdocs.yml nav under the appropriate section:
nav:
- Core: # Agent, Tools, Memory, Sessions, etc.
- Runtime Controls: # Budget, Cancellation, Token Estimation, Model Switching
- Providers: # Overview, Models, Usage
- RAG: # Pipeline, Hybrid Search, Chunking, etc.
- Evaluation: # Eval Framework
- Integration: # MCP Client/Server
- Security: # Guardrails, Audit, Screening
3. Landing Page Update
Update docs/index.md — add to feature table, update counts.
4. Quickstart Update
If user-facing, add a step to docs/QUICKSTART.md.
5. Architecture Update
If it adds a new system component, update docs/ARCHITECTURE.md.
6. Example Script
Create examples/NN_feature_name.py (next available number).
Follow existing style: docstring at top, self-contained, main() function with if __name__ guard.
7. Count Sync
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.
- yesterday First seen · 111 lines · 20 tokens per session scan A bcc46ab39696
docs is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 20 tokens to every session and 810 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.
Content Safety & Filtering
Topic-based content filtering to block harmful or unauthorized content in agent output.
guardrails-docs-access
Access and read guardrails skill documentation, configuration examples, and usage guides at runtime.
Output Security & Secret Scanning
Prevent sensitive data (secrets, credentials, PII) from leaking in agent output.
Policy Configuration Hierarchy
How guardrail policies cascade from organization through team to project level.
Sandbox Isolation
Run untrusted or risky commands in Docker-based sandbox with resource limits and network isolation.