agentleFS
2389-research2389-research/fresh-eyes-review/CLAUDE.md

fresh-eyes-review

CLAUDE.md6 starsChanged 12 months agoMITView on GitHub

This plugin enforces a mandatory final quality gate before code ships. It catches security vulnerabilities, logic errors, and bugs that slip through despite passing tests. Trigger keywords: commit, PR, done, complete, finished, ship, deploy, push When to use: - ALWAYS before git commit - ALWAYS before creating pull request - ALWAYS before declaring work complete - After all tests pass but before shipping What it does: 1. Announces "Starting fresh-eyes review of [N] files. This will take 2-5 minutes." 2.…

The file

We split this CLAUDE.md into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Trigger keywords: commit, PR, done, complete, finished, ship, deploy, push

    line 11
  2. Distinctive:

    ALWAYS before git commit

    line 14
  3. Distinctive:

    ALWAYS before creating pull request

    line 15
  4. Distinctive:

    ALWAYS before declaring work complete

    line 16
  5. Distinctive:

    After all tests pass but before shipping

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Fresh-Eyes Review Plugin

Overview

This plugin enforces a mandatory final quality gate before code ships. It catches security vulnerabilities, logic errors, and bugs that slip through despite passing tests.

Skill Included

fresh-eyes-review

Trigger keywords: commit, PR, done, complete, finished, ship, deploy, push

When to use:

  • ALWAYS before git commit
  • ALWAYS before creating pull request
  • ALWAYS before declaring work complete
  • After all tests pass but before shipping

What it does:

  1. Announces "Starting fresh-eyes review of [N] files. This will take 2-5 minutes."
  2. Systematically checks for:
    • Security vulnerabilities (SQL injection, XSS, path traversal, command injection)
    • Logic errors (off-by-one, race conditions, null handling)
    • Business rule bugs (calculations match requirements?)
    • Input validation (type, range, format checks complete?)
    • Performance issues (N+1 queries, unbounded loops)
  3. Fixes issues immediately
  4. Re-runs tests after corrections
  5. Announces results: "Fresh-eyes complete. [N] issues found and fixed."

Time commitment: 2-5 minutes

Core Principle

"NO COMMIT WITHOUT FRESH-EYES REVIEW FIRST"

This is non-negotiable. The discipline applies universally, even without explicit skill activation.

Key Distinctions

  • Testing - Validates expected behavior under controlled conditions
  • Code review - Examines patterns and quality during implementation
  • Fresh-eyes - Catches unexpected issues through deliberate re-reading with psychological distance

The skill emphasizes: "100% test coverage and passing scenarios" can coexist with "critical bugs" waiting discovery.

Resistance Patterns to Reject

The skill explicitly lists rationalizations to ignore:

  • "Tests are comprehensive"
  • "I'm confident it's correct"
  • "Partner is waiting"
  • "Production is blocked"
  • "Senior dev already approved"

These circumstances represent precisely when critical bugs escape into production.

Development Workflow

This skill is a mandatory guard that triggers before shipping:

  1. User completes implementation
  2. All tests pass
  3. Fresh-eyes review runs (this skill)
  4. Issues found and fixed
  5. Tests re-run and pass
  6. Code ships

Auto-Detection

Skill should trigger on:

  • "I'm done" or "finished"
  • "let me commit"
  • "ready to push"
  • "creating PR"
  • "deploying to production"

Common Usage

User: "I'm done implementing the feature, let me commit"
Assistant: [Triggers fresh-eyes-review skill]

Starting fresh-eyes review of 4 files. This will take 2-5 minutes.

[Reviews auth.ts for security]
- Found: Missing input validation on email field
- Fixed: Added email format validation

[Reviews handler.ts for logic]
- Found: Off-by-one error in pagination
- Fixed: Changed < to <= in boundary check

[Reviews db.ts for performance]
- No issues found

[Reviews api.ts for business rules]
- No issues found

Re-running tests... ✓ All tests pass

Fresh-eyes complete. 2 issues found and fixed.

Integration with Other Plugins

Complements all development workflows:

  • scenario-testing: Fresh-eyes runs after scenarios pass
  • building-multiagent-systems: Review orchestrator code before shipping
  • firebase-development: Review before deploying to Firebase

Philosophy

Quality over speed. The 2-5 minutes spent here prevent hours of debugging production issues.

Passing tests prove code works as designed. Fresh-eyes proves the design is correct.

Notes

  • Originated from Harper Reed's personal dotfiles
  • Battle-tested practice from production systems
  • Non-negotiable discipline
  • Explicitly rejects rationalization

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.