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/andr-ca/agentharness/code-review-apigit clone --depth 1 https://github.com/andr-ca/agentharnessWhat 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 | $0.00051 | $0.01034 |
| Opus 5 | $0.00026 | $0.00517 |
| Sonnet 5 | $0.00010 | $0.00207 |
| Haiku 4.5 | $0.00005 | $0.00103 |
Grade A, and why
code-review-api 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — REST / HTTP API Layer
Focus on correctness, consistency, and safety at the HTTP boundary.
HTTP Semantics
- Correct status codes —
201 Createdfor POST that creates;200 OKfor updates;204 No Contentfor DELETE;400 Bad Requestfor invalid input;404 Not Foundfor missing resources;409 Conflictfor duplicate creation;422 Unprocessable Entityfor validation failures;500 Internal Server Errorfor unhandled exceptions. - Non-idempotent PUT — PUT must be idempotent (same request = same result). If the operation has side effects that shouldn't repeat, it should be a POST.
- DELETE returns a body — RFC 7231 allows it, but clients often discard it. Prefer
204 No Contentunless returning the deleted resource is explicitly needed. - Wrong method for the operation — using GET for state-changing operations (no caching, logging of query params); using POST when PUT/PATCH is more appropriate.
Input Validation & Error Shapes
- Missing input validation — user-supplied fields used directly without type/range/pattern validation. Every boundary input must be validated before use.
- Inconsistent error shape — some errors return
{"error": "..."}, others{"message": "..."}. The API should follow one schema (RFC 9457 Problem Details recommended). - Stack trace in production response — never send exception stack traces to clients. Log server-side; return a stable error code.
- Leaking internal IDs — returning auto-increment integer IDs exposes row count; prefer UUIDs or opaque tokens.
Authentication & Authorization
- Auth happens after the operation — authorization must be checked before the DB query, not after loading the resource.
- Missing ownership check — user can access
/orders/123even if order 123 belongs to another user. Every resource access needs an ownership/permission check. - Token in URL — never put auth tokens in query strings (they appear in logs, referrer headers, browser history). Use
Authorizationheader. - Missing rate limiting — unauthenticated endpoints or auth endpoints (login, signup) with no rate limit are trivially brute-forced or scraped.
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.
- 2d ago First seen · 55 lines · 51 tokens per session scan A 74ce82fe9e96
code-review-api is a cursor rule published in the GitHub repository andr-ca/agentharness (1 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 1,034 once invoked, about $0.0003 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
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
handoff
Export a Waybill Bundle by default, or import one when explicitly requested.
cursorrules
This repo has a GraphPilot structural code-graph available via MCP. Use it before grep on structural questions.
ui-motion-workflow
Orchestrate motion-aware UI work by sequencing direction, provider choice, implementation, and browser validation.
frontend
UI/component conventions. Apply when building or changing user-facing frontend code.
lemoncrow.execute
LemonCrow execute mode reference for Cursor.