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 skills add blackblue-labs/skill2 --skill skill2-auditgit clone --depth 1 https://github.com/blackblue-labs/skill2Wrote 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/blackblue-labs/skill2/skill2-audit)<a href="https://agentmods.dev/skills/blackblue-labs/skill2/skill2-audit"><img src="https://agentmods.dev/badge/skills/blackblue-labs/skill2/skill2-audit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.00489 |
| Opus 5 | $0.00015 | $0.00244 |
| Sonnet 5 | $0.00006 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
skill2-audit 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Skill Libraries
Find evidence-backed defects without changing the library.
Scope
| Target | Checks |
|---|---|
| One Skill | Frontmatter, description, links, resources, scripts, secrets, local paths, size |
| Skill Library | Every single-Skill check plus duplicate names, ownership, scope, and static trigger overlap |
Ownership
- Audit owns static structure, safety, references, metadata, and trigger overlap.
- Test owns live activation and outcome behavior.
- Visualize owns inventory/usage/test evidence and conservative lifecycle review candidates.
- Create owns applying approved structural changes.
Method
- Run
uv run --script <skill-dir>/scripts/run -- lint <target> --jsonfirst for a single Skill or a library. Save and use its static findings as evidence. - Manually review what CLI cannot prove: description semantics, ownership, scope, and trigger overlap.
- If CLI is unavailable or fails: state limitation /
inconclusive. Never claim clean. - Do not execute scripts. Do not auto-fix.
Checks
- Missing or invalid
SKILL.mdand frontmatter - Directory/name mismatch
- Workflow summaries or ambiguous triggers in
description - Broken relative links and unused resources
- Non-executable or risky scripts
- Secrets and accidental machine-local paths
- Oversized bodies that should use progressive disclosure
- Static trigger overlap across sibling skills
- Project-only instructions inside a global package
Severity
| Level | Meaning |
|---|---|
| P0 | Install or execution breaks |
| P1 | Triggering or ownership is wrong |
| P2 | Safety or maintenance risk |
| P3 | Cleanup or style debt |
Output
Return severity, file, evidence, impact, and smallest suggested change. Do not apply fixes unless requested.
uv run --script <skill-dir>/scripts/run -- lint skills/<name> --json
uv run --script <skill-dir>/scripts/run -- lint skills --json
uv run --script <skill-dir>/scripts/run -- scan skills/<name> --json
uv run --script <skill-dir>/scripts/run -- scan skills --json
What ships with it
7 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.
- scripts/_runtime/skill2/__init__.py 22 B runs code
- scripts/_runtime/skill2/cli.py 13 KB runs code
- scripts/_runtime/skill2/lint.py 3.6 KB runs code
- scripts/_runtime/skill2/models.py 6.5 KB runs code
- scripts/_runtime/skill2/scan.py 7.3 KB runs code
- scripts/.runtime-manifest.json 942 B
- scripts/run 901 B
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 First seen · 62 lines · 30 tokens per session scan A 7186f0d853a6
skill2-audit is a skill published in the GitHub repository blackblue-labs/skill2 (33 stars, last pushed 23d ago), licensed MIT. It adds 30 tokens to every session and 489 once invoked, about $0.0002 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
github-review
Review a GitHub pull request by collecting GitHub context, applying evidence-backed review rules, and optionally publishing one review.
ghx
Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.
github-pr-fix
Fix a GitHub pull request by addressing feedback or CI failures, pushing changes, and publishing replies.
github-issue-solve
Solve a GitHub issue by collecting context, implementing a fix, and opening or updating a pull request.
session-summary
You summarise ONE work-burst of a developer's coding-agent session. The goal is to capture what the developer actually worked on, and why it mattered, so that a PM, a teammate, or the developer themselves can immediately understand the purpose and the outcome at a glance — without reading the transcript.
reduce
Use when asked to simplify, clean up, tidy, or refactor code for clarity without changing what it does, or when the user says "simplify this", "clean this up", "make it readable", "reduce the complexity", or "tidy this". Behavior-preserving only; not a bug or security audit (use bug-hunt or security-sweep for those).