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-onboard/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-onboard)<a href="https://agentmods.dev/skills/stbenjam/skillsaw/skillsaw-onboard"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-onboard/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-onboard"><img src="https://agentmods.dev/badge/skills/stbenjam/skillsaw/skillsaw-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 4 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Excessive Agency · line 81 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 132 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 | $0.00055 | $0.01514 |
| Opus 5 | $0.00028 | $0.00757 |
| Sonnet 5 | $0.00011 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00151 |
Grade A, and why
skillsaw-onboard 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skillsaw Onboard
Onboard this repository to skillsaw, a linter for agentic contextual building blocks (CLAUDE.md, skills, plugins, agents, hooks, etc.).
Workflow
Ask one routing question at a time and wait for the answer. An explicit choice in the user's request already counts as an answer. Read a reference only after its condition or a yes answer routes to it; do not read the reference to formulate the question. After completing it, return here. If the answer is no, continue to the next checkpoint without reading it. Carry forward the command prefix, counts, choices, and changed-file list.
Resolve every references/... path relative to the directory containing this
SKILL.md, never relative to the target repository or the process's current
working directory. If this file was fetched from the web, resolve each
reference against the parent URL of this file and fetch it from that sibling
location.
Replace brace-delimited fields below with facts from the repository or scan; never show placeholders to the user, and render singular or plural wording naturally.
1. Establish the current state
If no working skillsaw command is known, read install. Then read initial scan and report its violations before offering changes.
2. Triage findings by rule
Run skillsaw lint --format json -v to see all violations, including the info-level ones the first scan hid. Group the results by rule_id and sort them by count. Sample 3–5 examples from any large cluster (e.g. >10% of total findings or >20 issues) to understand the root cause before deciding on an action.
Follow triage to categorize each group into Fix now, Baseline, or Configure, and present a clear summary table to the user for confirmation before making changes. Carry the agreed buckets into the subsequent steps.
3. Apply autofixes
If the Fix now bucket holds autofixable findings, ask:
The plan includes autofixes for {count} violations: {safe count} safe and {suggest count} suggested. Applying them will edit the affected context files; I will show the changes and lint again afterward. Should I apply those fixes now?
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/01-install.md 726 B
- references/02-initial-scan.md 331 B
- references/03-autofix.md 667 B
- references/04-manual-fixes.md 682 B
- references/05-baseline.md 276 B
- references/06-configuration.md 539 B
- references/07-ci.md 1.6 KB
- references/08-external-links.md 1.2 KB
- references/09-makefile.md 1.2 KB
- references/10-badge.md 891 B
- references/11-verify.md 501 B
- references/12-triage.md 3.6 KB
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 · +24 lines · +7 tokens per session 2d1ade53428d
- 13d ago First seen · 127 lines · 48 tokens per session scan A bd7f42f57249
skillsaw-onboard is a skill published in the GitHub repository stbenjam/skillsaw (66 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 1,514 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…