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 cukas/patrol --skill review-gategit clone --depth 1 https://github.com/cukas/patrolWrote 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/cukas/patrol/review-gate)<a href="https://agentmods.dev/skills/cukas/patrol/review-gate"><img src="https://agentmods.dev/badge/skills/cukas/patrol/review-gate.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 | $0.00029 | $0.00626 |
| Opus 5 | $0.00015 | $0.00313 |
| Sonnet 5 | $0.00006 | $0.00125 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
review-gate 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review-Gate
Structured post-implementation review. Nothing passes without evidence.
1. Trace affected code paths
Use Read, Grep, and Glob to trace the call chain from each changed function to its callers and dependents. For changes that touch multiple files or cross API boundaries, trace both directions.
2. Bug pattern scan
Check every changed file for:
- Null safety: optional chaining gaps, unchecked nullable values, NonNullable casts without guards
- Async errors: missing await, unhandled promise rejections, race conditions
- Stale data: old values in caches, persisted state, or UI that survive restarts
- Off-by-one: index boundaries, array length vs last index, loop bounds
- Import errors: missing imports, circular dependencies, wrong paths
- Security: unsanitized input, eval usage, SQL/command injection, hardcoded secrets
- Error handling: swallowed exceptions, missing catch blocks, generic error responses
3. Build verification
Discover and run the project's build command:
- Check
package.jsonscripts,Makefile,Cargo.toml,pyproject.toml, or README - Run the build — confirm it succeeds
- If multiple build targets exist (e.g., plugin + shared types), rebuild all
4. Type and test verification
- Run the type checker (e.g.,
npx tsc --noEmit,pyright,cargo check) - Run the test suite (e.g.,
npm test,pytest,cargo test) - Fix all failures before proceeding
- If no type checker or test suite exists: state this explicitly in the report
5. Architectural check
Find 2-3 examples of the same pattern used elsewhere in the codebase. Confirm the change is consistent with them. Flag if:
- The change introduces a pattern not used anywhere else
- A simpler approach already exists in the codebase
- Unnecessary abstractions or over-engineering were added
6. Report
Present findings in this format:
## Review-Gate Report
| Check | Status | Notes |
|-------|--------|-------|
| Code path trace | PASS/FAIL | [what was traced] |
| Bug pattern scan | PASS/FAIL | [issues found or clean] |
| Build | PASS/FAIL | [command run + result] |
| Type check | PASS/FAIL/SKIP | [command run + result] |
| Tests | PASS/FAIL/SKIP | [command run + result] |
| Architecture | PASS/FAIL | [consistency notes] |
### Issues Found
- [list each issue and the fix applied, or "None"]
### Final Status: PASS / FAIL
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 · 69 lines · 29 tokens per session scan A ac9527769c9a
review-gate is a skill published in the GitHub repository cukas/patrol (3 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 626 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
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
pr-feedback
Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.
code-hygiene
Codebase health analysis: dead code, test quality, duplicates, complexity, security, architecture mapping. Tool-first, structured storage, forge integration.
review-pr
Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…