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/andr-ca/agentharnessWrote 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/andr-ca/agentharness/code-review)<a href="https://agentmods.dev/rules/andr-ca/agentharness/code-review"><img src="https://agentmods.dev/badge/rules/andr-ca/agentharness/code-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/rules/andr-ca/agentharness/code-review"><img src="https://agentmods.dev/badge/rules/andr-ca/agentharness/code-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 | $0.00053 | $0.04828 |
| Opus 5.5 | $0.00021 | $0.01931 |
| Sonnet 5.5 | $0.00011 | $0.00966 |
| Haiku 4.5 | $0.00005 | $0.00483 |
Grade A, and why
code-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.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
A systematic approach to reviewing diffs and pull requests. Work through the categories below in order — correctness first, style last.
Pre-read checklist
Before reading the diff:
- Read the PR description. Does it explain why the change is needed? If the description is missing or just "fixes stuff", ask for one before reviewing — the diff alone won't tell you whether the approach is right.
- Check the linked issue or ticket if there is one.
- Note the rigor tier (
patterns/profiles/or.agentharness-profile) — the coverage and testing requirements differ.
1. Correctness
The most important category. Ask: "Can this code produce wrong results?"
- Does the logic match the stated goal?
- Are there off-by-one errors, wrong comparisons, or incorrect assumptions about the data?
- Are all inputs validated before use?
- Are edge cases handled: empty collections, zero, null/None/undefined, negative numbers, max values, concurrent access?
- Does error handling actually handle the error, or does it swallow it silently?
- Are exceptions caught at the right level (not too broad, not too narrow)?
- Are resources (files, connections, locks) released even on exception?
# Swallowed error — caller sees success, wrong data silently used
try:
value = parse_config(raw)
except Exception:
pass # WRONG: value is now unset or stale
# RIGHT: propagate or at minimum log + re-raise
try:
value = parse_config(raw)
except ConfigError as e:
logger.error("config parse failed", error=e)
raise
2. Security
Run through the relevant items from the security-review skill (load it
for the full checklist). The most common PR-level findings:
- Secrets or API keys hardcoded or logged.
- SQL/shell/HTML built via string formatting with user input.
- Missing ownership/permission checks on resource access.
- New dependency with known CVEs (
npm audit/pip-auditnot run).
3. Test coverage
At Production tier, new code must have tests. Check:
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 · 263 lines · 53 tokens per session scan A 5e0eb8c51bef
code-review is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 4,828 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 cursor rules, from other repositories
hunch
Hunch engineering memory — consult the hunch MCP tools before editing.
shipwright
Shipwright harbour inspection and fitting-out checklist.
gjalla-review
Master-spec, rules, and production-readiness review with gjalla.
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.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.