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 vosslab/vosslab-skills --skill audit-code-reviewergit clone --depth 1 https://github.com/vosslab/vosslab-skillsWrote 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/vosslab/vosslab-skills/audit-code-reviewer)<a href="https://agentmods.dev/skills/vosslab/vosslab-skills/audit-code-reviewer"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/audit-code-reviewer/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/vosslab/vosslab-skills/audit-code-reviewer"><img src="https://agentmods.dev/badge/skills/vosslab/vosslab-skills/audit-code-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.01973 |
| Opus 5 | $0.00011 | $0.00986 |
| Sonnet 5 | $0.00004 | $0.00395 |
| Haiku 4.5 | $0.00002 | $0.00197 |
Grade A, and why
audit-code-reviewer 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 8d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review code changes
Overview
Use this skill to turn a code-change review into six independent review passes run by separate subagents. The main agent is the review coordinator: gather shared context, launch independent review subagents with separate scopes, wait for their results, then merge their findings into a single concise review.
Required behavior
- Prefer design-level fixes over symptom patches; cite
docs/REPO_STYLE.mdwhen flagging this. - Launch subagents for independent review passes. The purpose of this skill is independent review.
- Treat the main agent as coordinator and integrator, not as the sole reviewer.
- Keep main-agent preflight minimal. Gather only enough context to launch the subagents.
- Send each subagent the raw shared context and its assigned scope, without telling it the expected conclusion.
- Wait for the subagent results before delivering the final review.
- If subagents are unavailable, state that independent review could not be performed and stop with the gathered context plus the reason.
- Do the fixes that make sense. After merging findings, apply obvious low-risk fixes directly; leave blockers, contested fixes, and architecture-level changes for the user.
Workflow
- Gather shared context before launching agents:
- User request and any referenced plan document.
git status --shortand the relevantgit diff.- Repo rule files that exist, especially
AGENTS.md,docs/REPO_STYLE.md,docs/PYTHON_STYLE.md,docs/PYTEST_STYLE.mdwhen present,docs/MARKDOWN_STYLE.md, anddocs/CHANGELOG.md. - Focused test commands already run and their results, if available.
- Launch six independent review subagents in parallel immediately after the minimal shared context is ready. Use the reviewer names below so each pass has a concrete identity and scope. Give each subagent the same shared context plus its specific scope. Ask subagents for findings only, with file and line references when possible.
- While subagents run, prepare the integration shell only: finding severity order, changed-file list, test-evidence list, and documentation-evidence list.
- Wait for all review subagents to return, unless one fails irrecoverably. If a subagent fails, include that missing review pass as residual risk.
- Merge returned findings by severity. Remove duplicates, keep the clearest evidence, and preserve dissent when reviewers disagree.
- Deliver a code-review response: findings first, then open questions or assumptions, then a brief test/documentation summary.
- Do the fixes that make sense. After delivering findings, apply the obvious low-risk fixes (typos, missing comments, stale doc lines, dead imports, fragile pytest deletions flagged by Test auditor). Skip fixes that require design judgment, cross-file coordination, or user input.
What ships with it
1 file 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.
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.
- 8d ago First seen · 191 lines · 22 tokens per session scan A f68aaa6e84af
audit-code-reviewer is a skill published in the GitHub repository vosslab/vosslab-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 1,973 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…