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 MuhammedZohaib/patchman --skill query-reviewgit clone --depth 1 https://github.com/MuhammedZohaib/patchmanWrote 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/muhammedzohaib/patchman/query-review)<a href="https://agentmods.dev/skills/muhammedzohaib/patchman/query-review"><img src="https://agentmods.dev/badge/skills/muhammedzohaib/patchman/query-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/muhammedzohaib/patchman/query-review"><img src="https://agentmods.dev/badge/skills/muhammedzohaib/patchman/query-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 | $0.00049 | $0.00138 |
| Opus 5.5 | $0.00020 | $0.00055 |
| Sonnet 5.5 | $0.00010 | $0.00028 |
| Haiku 4.5 | $0.00005 | $0.00014 |
Grade A, and why
query-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 1mo 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
Query Review
Focus
- missing tenant scopes
- authorization after broad fetches
- raw SQL without parameter binding
- N+1 patterns that become availability or side-channel issues
- eager loads that overexpose sensitive associations
- cache keys missing tenant or role context
Heuristic
Treat data-access issues as security-relevant when they change scope, leak metadata, or undermine availability controls.
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.
- 1mo ago First seen · 20 lines · 49 tokens per session scan A f88ae239e267
query-review is a skill published in the GitHub repository MuhammedZohaib/patchman (3 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 138 once invoked, about $0.0002 per session on Opus 5.5. 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
configuration-identity-stores
Configure local, LDAP or SQLite password identity stores, trusted SQLite administration, realms, databases, binds, TLS trust and group mappings. Delegates static local entries to configuration-users.
API Security Testing
Comprehensive API security testing based on OWASP API Security Top 10 including broken authentication, injection attacks, rate limiting, BOLA/BFLA vulnerabilities, and automated security scanning with ZAP and custom scripts.
Supabase RLS Policy Review
Detects tables created without ROW LEVEL SECURITY enabled, over-permissive policies (USING (true) / WITH CHECK (true) without owner conditions), and servicerole key exposure in client code.
laravel-docs
Laravel 13.x — routing, Eloquent ORM, Blade, middleware, queues, broadcasting, auth, testing, Artisan, packages.
audit-schema-design
Database schema design checklist (indexes, foreign keys, constraints). Use when reviewing migrations, new tables or columns, slow queries, missing indexes, foreign-key and ON DELETE behavior, or integrity rules enforced only in app code.
audit-nplus1
Query-amplification (N+1) checklist. Use when code loads related data inside a loop over a collection, or when reviewing ORM-heavy read paths for performance.