Borrowing it
Nothing to install: this file belongs to stbenjam/skillsaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stbenjam/skillsaw/main/.agents/skills/skillsaw-lint/SKILL.mdgit clone --depth 1 https://github.com/stbenjam/skillsawWrote 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/stbenjam/skillsaw/skillsaw-lint)<a href="https://agentmods.dev/skills/stbenjam/skillsaw/skillsaw-lint"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-lint/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stbenjam/skillsaw/skillsaw-lint"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 30 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 31 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 5.1 | $0.00185 | $0.01030 |
| Opus 5 | $0.00093 | $0.00515 |
| Sonnet 5 | $0.00037 | $0.00206 |
| Haiku 4.5 | $0.00018 | $0.00103 |
Grade A, and why
skillsaw-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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillsaw Lint
You just authored or edited agentic context — a skill, slash command, agent,
hook, plugin, marketplace, or instruction file (CLAUDE.md, AGENTS.md,
GEMINI.md, Cursor/Copilot/Cline/Kiro rules), or the configuration that
loads it (an OpenCode opencode.json). That content feeds an agent's
context window, and defects in it — weak language, contradictions,
placeholder text, instructions buried in attention dead zones — degrade
every future session that loads it. Lint it with skillsaw and improve
it before you report the work as done.
Run the skillsaw CLI for every step below; it is the interface for linting, fixing, and explaining — replace any hand-rolled check with it.
Step 1: Locate skillsaw
Run skillsaw --version. If the command is missing, check the project for a
pinned version before installing — look in the Makefile, pyproject.toml, or
an existing .venv (e.g. .venv/bin/skillsaw --version). Use that version
with uvx skillsaw==<version> as the prefix for every command below (or
pip install skillsaw==<version> if uvx is unavailable).
Step 2: Lint what you wrote
Run the linter scoped to the files or directories you created or edited:
skillsaw lint <path>
Read each violation line: it carries the severity, file path, line number,
message, and rule ID. If the repository defines its own lint entry point (a
Makefile lint target that runs skillsaw, for example), run that instead —
it may pin a version or pass flags like --strict.
If the lint exits 0 with no violations, your work is clean — stop here and report done.
Step 3: Apply deterministic autofixes
skillsaw fix <path>
This applies safe, structural fixes (missing frontmatter, kebab-case names,
and similar). Run skillsaw fix --dry-run first to inspect the diff before
anything is written. Run skillsaw fix --suggest for a second tier of
mechanically derived fixes (stale-reference updates after a rename, for
example) — review each hunk in that tier before applying it.
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.
- 7d ago Changed · +70 tokens per session 30f28a0a77a6
- 12d ago First seen · 92 lines · 115 tokens per session scan A 605380fee35e
skillsaw-lint is a skill published in the GitHub repository stbenjam/skillsaw (66 stars, last pushed today), licensed Apache-2.0. It adds 185 tokens to every session and 1,030 once invoked, about $0.0009 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.