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 agentmods add rules/jketreno/clare/skill-reviewgit clone --depth 1 https://github.com/jketreno/clareWrote 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/jketreno/clare/skill-review)<a href="https://agentmods.dev/rules/jketreno/clare/skill-review"><img src="https://agentmods.dev/badge/rules/jketreno/clare/skill-review.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 | $0.00006 | $0.04745 |
| Opus 5 | $0.00003 | $0.02372 |
| Sonnet 5 | $0.00001 | $0.00949 |
| Haiku 4.5 | $0.00001 | $0.00475 |
Grade A, and why
skill-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: review description: "Code review for correctness, KISS/DRY/YAGNI/SOLID, security, language BKMs, tests, and docs" mode: agent
Review Diff vs. Base Ref
Scope and Baseline
Review all changes on the current branch against an appropriate base ref — as if performing a thorough pull-request code review. Do not guess at correctness; read the actual diff and the relevant file context.
Step 1 — Determine the Base Ref
Resolve the base ref in priority order. Use the first one that succeeds:
- User-specified — if the user says "review vs main", "against origin/staging", etc., use that ref.
- Upstream tracking branch —
git rev-parse --verify "upstream/$(git symbolic-ref --short HEAD 2>/dev/null)" 2>/dev/null - Origin tracking branch (same name) —
git rev-parse --verify "origin/$(git symbolic-ref --short HEAD 2>/dev/null)" 2>/dev/null origin/main—git rev-parse --verify origin/main 2>/dev/nullorigin/master—git rev-parse --verify origin/master 2>/dev/null- Local
main—git rev-parse --verify main 2>/dev/null - Ask — if none resolve, say: "I couldn't determine a base branch. What should I diff against?"
Step 2 — Gather the Diff
# Unified diff from merge base (PR semantics — use triple-dot)
git diff <BASE_REF>...HEAD
# File summary (what changed at a glance)
git diff --stat <BASE_REF>...HEAD
# Untracked new files not yet committed
git status --short
Read the complete diff before beginning the review. Do not review hunks in isolation.
Step 3 — Load File Context
For every file that appears in the diff, read the full file — not just the changed hunks. This is required to:
- Detect misuse of a new or changed API by its callers
- Verify that error handling is consistent with the rest of the file
- Identify invariants that the changed code may break
- Confirm that imports, exports, and type signatures are consistent
Review Checklist
Apply every category below to every changed file. Do not skip a category because the change looks small — subtle bugs hide in small diffs.
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 First seen · 290 lines · 6 tokens per session scan A 9bdce5057c6a
skill-review is a cursor rule published in the GitHub repository jketreno/clare (5 stars, last pushed 1mo ago), licensed MIT. It adds 6 tokens to every session and 4,745 once invoked, about $0.0000 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.