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/lintnpx skills add johnnichev/selectools --skill lintgit 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 | $0.00464 |
| Opus 5 | $0.00011 | $0.00232 |
| Sonnet 5 | $0.00004 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
lint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Code Quality Pipeline
The repo migrated off black/isort/flake8 to ruff (format + lint) plus mypy
and bandit. These are exactly what the pre-commit hooks and CI enforce, so
matching them here keeps /release from tripping at commit time.
Mode
If "$ARGUMENTS" contains "check" or "check-only", run in check mode (no modifications). Otherwise, run in fix mode (auto-format and auto-fix, then verify).
Fix Mode (default)
Run these in sequence, stopping on first failure:
ruff check src/ tests/ --fix(lint + autofix; replaces flake8 + isort)ruff format src/ tests/(format; replaces black)mypy src/bandit -c pyproject.toml -r src/
Check Mode
Read-only, no modifications:
ruff check src/ tests/ruff format src/ tests/ --checkmypy src/bandit -c pyproject.toml -r src/
On Failure
- ruff check failure: Report the violations with file paths and line numbers. Fix them — do not blanket-suppress with
# noqa. - ruff format failure (check mode): Report which files need formatting. Offer to re-run in fix mode.
- mypy failure: Report the type errors. Fix them — do not use
# type: ignoreunless truly unavoidable, and always give it an explicit error code (# type: ignore[code]) plus a comment explaining why. - bandit failure: Report the finding. Fix it, or justify with a scoped
# nosec <ID>and a comment.
Success
When all four pass, report: "All clean — ruff check, ruff format, mypy, bandit passed."
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 · 46 lines · 22 tokens per session scan A 1f06f3b8e70e
lint 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 464 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.