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 vasuag09/harness-claude --skill reviewgit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/review)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/review"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/review/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/vasuag09/harness-claude/review"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/review.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 | $0.00045 | $0.00462 |
| Opus 5 | $0.00023 | $0.00231 |
| Sonnet 5 | $0.00009 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
review 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 10d 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.
What it actually says
/review — code quality & correctness
Goal: catch bugs and quality issues before they merge.
Do this
- Delegate to
harness-claude:code-reviewerwith the diff in scope (git diff,git diff --staged, or the files named). - The reviewer checks correctness, edge cases, error handling, naming, complexity,
duplication, adherence to harness rules, and test coverage — reporting
file:linewith severity. - Triage findings:
- Critical → block, fix now.
- High → fix before merge.
- Medium/Low → fix when reasonable / note.
- Apply fixes, then re-review the changed lines if Critical/High were found.
Common rationalizations (don't accept these from yourself)
| Excuse | Reality |
|---|---|
| "The diff is tiny — review would be ceremony" | Small diffs cause outsized breakage precisely because nobody looks. The reviewer is cheap; the regression isn't. |
| "I just wrote it, so I know it's correct" | The author is the worst-placed reviewer. That's the whole reason this gate delegates to a fresh-context agent. |
| "It's only a High, and the user is waiting" | High means fix before merge. Speed pressure is when gates earn their keep. |
| "I'll batch the findings with the next change" | Deferred findings become permanent. Fix now while the context is loaded. |
Red flags — stop and re-check
- You summarized the diff to the reviewer instead of giving it the actual diff.
- The review returned zero findings on a non-trivial change (suspicious, not reassuring).
- Critical/High fixes landed but the changed lines were never re-reviewed.
Exit criterion
No Critical or High findings outstanding. Then /harness-claude:security-review (or run both in
parallel if the change is security-sensitive).
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.
- 10d ago First seen · 39 lines · 45 tokens per session scan A fd9230c76145
review is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 462 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 2026-08-31.
Other skills, from other repositories
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
review-plan
Structured plan review across 4 axes before writing any code (inspired by Garry Tan's workflow).
design-patterns
Detect, suggest, and evaluate GoF design patterns in TypeScript/JavaScript codebases. Use when refactoring code, applying singleton/factory/observer/strategy patterns, reviewing pattern quality, or finding stack-native alternatives for React, Angular, NestJS, and Vue.