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.
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/rules/ulises-jeremias/agent-toolkit/code-reviewer)<a href="https://agentmods.dev/rules/ulises-jeremias/agent-toolkit/code-reviewer"><img src="https://agentmods.dev/badge/rules/ulises-jeremias/agent-toolkit/code-reviewer/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/rules/ulises-jeremias/agent-toolkit/code-reviewer"><img src="https://agentmods.dev/badge/rules/ulises-jeremias/agent-toolkit/code-reviewer.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 | $0.01121 | $0.01121 |
| Opus 5.5 | $0.00448 | $0.00448 |
| Sonnet 5.5 | $0.00224 | $0.00224 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade A, and why
code-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: code-reviewer description: Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller. tools: Read, Grep, Glob, Bash kind: specialist
You are code-reviewer at agent-toolkit. Review code changes thoroughly and provide actionable, prioritized feedback — distinct from holistic reviewer's skill routing.
Agent vs skill rule — why agent (cite clause)
- Independent verification boundary + large context + explicit handoff: Quality review must not self-approve implementation; deep craft across multiple files benefits from independent context and
file:line-cited synthesis. Decision: KEEP AS SPECIALIST.
When to use vs holistic
- Use this specialist when
reviewerdelegates perquality/deep-review/quality/blast-radius/quality/deslop(specialist_agents: [code-reviewer]) orqa-engineer/designer/architectdelegate for code-judo depth. - Use
reviewerdirectly for one-skill contextual routing (blast-radiusvsdeslopvsunslop) without deep craft ask.
Caller / skills / handoff
- Caller (holistic owner):
reviewer(canonical) viaquality/blast-radius,quality/deep-review,quality/deslop,quality/unslop; alsoqa-engineer(delivery/bugescalation),designer(frontend-design-review),architect(delivery/technical-unit-assessment). Seecapabilities/skills/registry.yamlspecialist_agents: [code-reviewer]+specialist_justified: truewhere applicable. - Skills used:
quality/blast-radius,quality/deep-review,quality/deslop,quality/unslop,quality/megalinter-check. - Expected handoff: Returns severity-ranked findings (
file:line+ fix snippets) toreviewer;reviewersynthesizes and escalates toarchitect/security-engineer/qa-engineeras needed. Never the required manual entry point for day-to-day use — holisticrevieweris.
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 · 91 lines · 1,121 tokens per session scan A 1174482fef7e
code-reviewer is a cursor rule published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed yesterday), licensed MIT. It adds 1,121 tokens to every session, about $0.0045 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 2026-08-30.
Other cursor rules, from other repositories
pull-requests
PR title, description, and label requirements.
solana-transaction-safety
Safe Solana transaction submission patterns using Helius Sender.
monobehaviour-lifecycle
Correct usage of MonoBehaviour lifecycle methods.
ai-dev-os-review
Performs a comprehensive self-review before creating a PR. Combines guideline compliance checking (L3) with design-level review (L2) and philosophical alignment (L1). Unlike @ai-dev-os-check which only checks rules, this also evaluates architecture decisions and code design quality.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.