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/releasenpx skills add johnnichev/selectools --skill releasegit 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 | $0.00022 | $0.01994 |
| Opus 5 | $0.00011 | $0.00997 |
| Sonnet 5 | $0.00004 | $0.00399 |
| Haiku 4.5 | $0.00002 | $0.00199 |
Grade A, and why
release 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Process
Preparing release version: $ARGUMENTS
Live Project State
- Current version: !
grep -m1 __version__ src/selectools/__init__.py - pyproject.toml version: !
grep -m1 "version" pyproject.toml - Tests: !
pytest tests/ --collect-only -q 2>/dev/null | tail -1 - Examples: !
ls examples/*.py | wc -l | tr -d ' ' - Models: !
grep -c "ModelInfo(" src/selectools/models.py - StepTypes: !
python3 -c "from selectools.trace import StepType; print(len(StepType))" 2>/dev/null - 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 - Last example: !
ls examples/*.py | tail -1
CRITICAL: Git Workflow Rules
- Never push without explicit user approval — commit locally, then ask
- Always use PRs — never push directly to main
- Keep feature work on one branch — don't merge WIP to main
- No co-author lines in commits
Phase 1: Quality Gate — Lint, Tests, E2E
Run /lint (fix mode) to auto-format and check code quality. ALL must pass
(the repo uses ruff + mypy + bandit — NOT black/isort/flake8):
ruff check src/ tests/(lint; isort+flake8 replacement)ruff format src/ tests/ --check(format; black replacement)mypy src/bandit -c pyproject.toml -r src/
Then run the full test suite (use the project venv, e.g. .venv/bin/python -m pytest):
pytest tests/ -q # full suite — do NOT shortcut to a subset
E2E hard gate (real API, before tagging). Per feedback_evals_before_release,
real-LLM e2e tests must run before every release — mock tests passed while a real
SYSTEM-role bug shipped. Run the named gate files with whatever provider keys are
set (each provider's tests skip if its key is absent):
python -u -m pytest tests/test_orchestration_evals.py tests/test_orchestration_e2e.py --run-e2e -v
Tip: do NOT pipe through tail (it block-buffers and hides progress); use -u
and read the output file. If only one provider key is available, a scoped
-k <provider> run validates that provider's real path quickly.
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 · 225 lines · 22 tokens per session scan A bb574321623d
release is a skill published in the GitHub repository johnnichev/selectools (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,994 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.