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-fix/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-fix)<a href="https://agentmods.dev/skills/stbenjam/skillsaw/skillsaw-fix"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-fix/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-fix"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-fix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to high
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 →
- high Prompt Injection · line 83 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 120 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium MCP Rug Pull · line 4 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 23 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 24 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- low Excessive Agency · line 15 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00057 | $0.02074 |
| Opus 5 | $0.00028 | $0.01037 |
| Sonnet 5 | $0.00011 | $0.00415 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
skillsaw-fix 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 11d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillsaw Fix
Review and fix skillsaw lint violations in this repo. skillsaw lints agentic contextual building blocks (CLAUDE.md, skills, plugins, agents, hooks, etc.). The tool applies deterministic fixes itself; handle everything else yourself — read the violation, load the rule's how-to-fix guidance, and make a targeted edit.
Follow the steps in order. Report progress to the user at each stage.
Step 1: Install and locate skillsaw
Run skillsaw --version. If the command is missing, use uvx skillsaw as the
prefix for every command below (or pip install skillsaw if uvx is
unavailable).
Step 2: Run the lint and build an inventory
Run skillsaw (lint) from the repo root and capture the output. Each
violation line includes the severity, file path, line number, message, and
rule ID — read them all.
If the lint exits 0 with no violations, tell the user the repo is clean and stop.
Build an inventory: group the violations by rule ID and check how many files each rule touches. Review this summary with the user before making changes.
Step 3: Run deterministic autofixes
Run skillsaw fix. This applies safe, structural fixes (missing frontmatter, kebab-case names, plugin registration, and similar).
Then run skillsaw fix --suggest --dry-run to preview the suggested tier.
Suggested fixes (e.g. updating stale references after a rename) are
mechanically derived but may over-match, so review each hunk in the diff
individually: for a stale-reference rewrite, check whether the flagged text
is really a reference to the skill or just the same word used generically —
"the data-parser skill" is a reference; "our data parser" is not. If every
hunk is correct, run skillsaw fix --suggest to apply the tier. If any hunk is
wrong, skip the tier entirely, handle those violations manually in Step 5, and
keep only the edits you judged correct.
Re-run skillsaw and report how many violations the autofixer resolved.
Step 4: Read fix guidance for each remaining rule
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.
- 11d ago First seen · 192 lines · 57 tokens per session scan A fc17f646938f
skillsaw-fix is a skill published in the GitHub repository stbenjam/skillsaw (66 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 2,074 once invoked, about $0.0003 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.