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 toverux/cantrips --skill review-gategit clone --depth 1 https://github.com/toverux/cantripsWrote 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/toverux/cantrips/review-gate)<a href="https://agentmods.dev/skills/toverux/cantrips/review-gate"><img src="https://agentmods.dev/badge/skills/toverux/cantrips/review-gate/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/toverux/cantrips/review-gate"><img src="https://agentmods.dev/badge/skills/toverux/cantrips/review-gate.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 | $0.00032 | $0.03140 |
| Opus 5 | $0.00016 | $0.01570 |
| Sonnet 5 | $0.00006 | $0.00628 |
| Haiku 4.5 | $0.00003 | $0.00314 |
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 4d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review the working diff (or the changes since a fixed point) through independent finder angles, judge every candidate with an independent verifier, and report a ranked, capped findings list. Finders find and verifiers judge — a finder never drops a candidate it half-believes; silently dropped candidates bypass verification and are the dominant cause of missed bugs.
Arguments
The effort level is whichever of low, medium, or high appears among the arguments; default medium.
--fix, anywhere in the arguments, enables apply mode (see Synthesize and report) on the medium and high pipelines; low and the no-sub-agent fallback report their findings and apply nothing, since neither ran a verifier over them — except under --loop, which re-reviews every batch and reports what ran unverified.
A run handed a --fix it cannot honour says so in its summary, so a report with no applied outcomes never reads as nothing having been worth applying.
--loop, anywhere in the arguments, implies --fix and drives that apply mode to a defined green state instead of reporting once — read LOOP.md before Scope and run the whole gate under its rules.
What remains once the level and the flags are taken out is the fixed point.
| Level | Pipeline | Bias | Findings cap |
|---|---|---|---|
low |
1 inline diff pass, no sub-agents | precision, hunk-only | ≤4 |
medium |
4 correctness + 2 quality finders → verify | precision — every finding one a maintainer would act on | ≤8 |
high |
6 correctness + 5 quality finders → verify → sweep → verify | recall — a missed bug ships; err on the side of surfacing | ≤15 |
What ships with it
4 files 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.
- 4d ago Changed · +4 lines e92a665485c5
- 9d ago First seen · 128 lines · 32 tokens per session scan A ecf1432650b9
review-gate is a skill published in the GitHub repository toverux/cantrips (2 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 3,140 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
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
code-that-fits-in-your-head
Software-engineering heuristics based on Mark Seemann's Code That Fits in Your Head (2021), updated for agent-driven development. Use when writing or reviewing code, refactoring accidental complexity or a Big Ball of Mud, controlling technical or architectural debt in generated code, designing APIs and invariants…
code-remediate
Apply selected review fixes; bare PR targets use current online items, while PR +review adds the latest matching artifact.