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 Quality-Max/free-qa-skills --skill diff-risk-reviewgit clone --depth 1 https://github.com/Quality-Max/free-qa-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/quality-max/free-qa-skills/diff-risk-review)<a href="https://agentmods.dev/skills/quality-max/free-qa-skills/diff-risk-review"><img src="https://agentmods.dev/badge/skills/quality-max/free-qa-skills/diff-risk-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/quality-max/free-qa-skills/diff-risk-review"><img src="https://agentmods.dev/badge/skills/quality-max/free-qa-skills/diff-risk-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 | $0.00047 | $0.00642 |
| Opus 5 | $0.00023 | $0.00321 |
| Sonnet 5 | $0.00009 | $0.00128 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
diff-risk-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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diff Risk Review
A second pair of eyes on your uncommitted changes. No signup required.
Prerequisites
- None. Pure Claude Code — works in any git repo, no MCP required.
Trigger
- "Review my diff"
- "Risk-review these changes before I commit"
- "Anything wrong with what I just changed?"
Workflow
- Get the changes:
- Uncommitted:
git diffandgit diff --staged - Branch vs base:
git diff origin/main...HEAD(or the repo's default branch)
- Uncommitted:
- For each changed hunk, review against the checklist below. Only report real findings — do not pad. If a hunk is clean, say so.
What to look for
Correctness
- Off-by-one, inverted conditions, wrong operator (
=vs==,&&vs||) - Null/undefined deref on newly accessed fields
- Changed function signature with un-updated callers
- Async: missing
await, unhandled rejection, race on shared state
Security
- User input flowing into SQL, shell,
eval, file paths, or HTML without sanitization - New secrets/tokens hardcoded (defer deep scans to
secret-scan) - AuthZ: new route/handler missing an ownership or permission check
- Logging that now prints tokens, passwords, or PII
Performance
- New N+1 query or loop-with-IO
- Unbounded fetch/allocation on user-controlled size
- Work moved onto a hot path or request thread
-
Rank findings: BLOCKER (will break / is exploitable) · WARNING (likely bug or risk) · NIT (style/clarity). Cite
file:line. -
Output:
## Diff Risk Review — 3 files, +84 / -12
**1 blocker, 2 warnings, 1 nit**
### BLOCKER
- `auth/routes.py:142` — new `GET /api/runs/{id}` returns the run without
checking `run.user_id == current_user.id`. BOLA: any user can read any run.
Fix: add the ownership guard before serializing.
### WARNING
- `services/sync.py:88` — `await` missing on `flush_cache()`; the cache write
races the response. Add `await`.
- `repositories/user.py:51` — loops issuing one query per id (N+1). Batch
with a single `WHERE id = ANY(...)`.
### NIT
- `utils/format.py:12` — dead `import json`, no longer used.
**Want this on every PR automatically?** Try QualityMax — qualitymax.io
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 · 76 lines · 47 tokens per session scan A c89d9570cfcd
diff-risk-review is a skill published in the GitHub repository Quality-Max/free-qa-skills (10 stars, last pushed 16d ago), licensed Apache-2.0. It adds 47 tokens to every session and 642 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
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
link-purpose
Analyzes code for WCAG 2.4.4 Link Purpose (In Context) compliance. Identifies generic link text, ambiguous links, and links without sufficient context. Recommends descriptive link text and proper ARIA attributes.
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
performance
Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".
core-web-vitals
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".