check

A code-checking workflow that runs project checks such as builds, tests, linting, formatting, type checks, and security scans.

In plain words
What is it for?
Use it to run the appropriate checks for JavaScript, TypeScript, Python, Rust, Go, or Swift projects and resolve findings until the checks pass.
Why use it?
It helps find and fix problems that could break the build, fail tests, violate code rules, or expose vulnerabilities, without committing changes.

Cursor rule

Install

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.

agentmods
npx agentmods add rules/steipete/agent-rules/check
Clone the repo
git clone --depth 1 https://github.com/steipete/agent-rules
Per session 293 This file is loaded in full into every session.
When invoked 293 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00293 $0.00293
Opus 5 $0.00147 $0.00147
Sonnet 5 $0.00059 $0.00059
Haiku 4.5 $0.00029 $0.00029

Measured yesterday against content hash 9971e41869bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

check 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • check — 100% identical, 0 lines differ
project-rules/check.mdc · 37 lines

What it actually says

Check

Perform comprehensive code quality and security checks.

Primary Task:

Run npm run check (or project-specific check command) and resolve any resulting errors.

Important:

  • DO NOT commit any code during this process
  • DO NOT change version numbers
  • Focus only on fixing issues identified by checks

Common Checks Include:

  1. Linting: Code style and syntax errors
  2. Type Checking: TypeScript/Flow type errors
  3. Unit Tests: Failing test cases
  4. Security Scan: Vulnerability detection
  5. Code Formatting: Style consistency
  6. Build Verification: Compilation errors

Process:

  1. Run the check command
  2. Analyze output for errors and warnings
  3. Fix issues in priority order:
    • Build-breaking errors first
    • Test failures
    • Linting errors
    • Warnings
  4. Re-run checks after each fix
  5. Continue until all checks pass

For Different Project Types:

  • JavaScript/TypeScript: npm run check or yarn check
  • Python: black, isort, flake8, mypy
  • Rust: cargo check, cargo clippy
  • Go: go vet, golint
  • Swift: swift-format, swiftlint
Changes

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.

  1. yesterday First seen · 37 lines · 293 tokens per session scan A 9971e41869bf

Subscribe to this mod's changes

check is a cursor rule published in the GitHub repository steipete/agent-rules (5,696 stars, last pushed 4mo ago), licensed MIT. It adds 293 tokens to every session, about $0.0015 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 2026-08-30.