agentleFS
proffesor-for-testingproffesor-for-testing/agentic-qe/.claude/skills/strict-tdd/SKILL.md

strict-tdd

Skill524 starsChanged 36 days agoMITView on GitHub

Use when enforcing TDD discipline — blocks writing production code unless a failing test exists first. Activate with /strict-tdd to enable session-scoped Red-Green-Refactor guardrail.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    Distinctive

    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:

    When activated, this skill registers a session-scoped hook that enforces Red-Green-Refactor discipline.

    line 9
  2. Distinctive:

    Only blocks src/ files — test files and config files are always writable

    line 69
  3. Distinctive:

    If test runner isn't installed, hook will error — ensure jest/vitest is available

    line 71

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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
SKILL.md

Strict TDD Mode

When activated, this skill registers a session-scoped hook that enforces Red-Green-Refactor discipline.

What It Does

Blocks writes to src/ (production code) unless:

  1. A test file exists that covers the target module
  2. That test has at least one failing assertion (Red phase confirmed)

This prevents the common agent failure of writing test + implementation simultaneously.

Activation

/strict-tdd

Remains active for the current session only.

Hook Configuration

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Write|Edit",
        "hook": ".claude/skills/strict-tdd/scripts/enforce-red-phase.sh",
        "condition": "file matches src/**/*.{ts,js} AND NOT src/**/*.test.{ts,js}"
      }
    ]
  }
}

Enforcement Logic

#!/bin/bash
# enforce-red-phase.sh
# Called before any Write/Edit to src/ files

TARGET_FILE="$1"
TEST_FILE="${TARGET_FILE%.ts}.test.ts"

if [ ! -f "$TEST_FILE" ]; then
  echo "BLOCKED: No test file found at $TEST_FILE"
  echo "Write a failing test first (Red phase), then implement."
  exit 1
fi

# Check if tests are currently failing (Red phase)
npx jest "$TEST_FILE" --passWithNoTests 2>/dev/null
if [ $? -eq 0 ]; then
  echo "WARNING: Tests are passing. Are you in Green/Refactor phase?"
  echo "If adding new behavior, write a failing test first."
fi

Gotchas

  • Only blocks src/ files — test files and config files are always writable
  • During Refactor phase, tests should still pass — this is expected, don't treat as violation
  • If test runner isn't installed, hook will error — ensure jest/vitest is available
  • Agent may try to write to a different path to bypass — the hook should match all production code paths

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.