fix-broken-tests

fix-broken-tests is a command for Claude Code from e0ipso/drupal-bridge-mcp. It costs 8 tokens per session (293 once invoked), scanned A, original, MIT.

A command for finding and fixing all failing tests by correcting the underlying source-code problems. Tests are checks that software behaves as expected.

In plain words
What is it for?
Use it after a change breaks tests to run the test suite, investigate failures, repair the source code, and verify the complete suite.
Why use it?
It keeps test results meaningful by forbidding skipped tests, weakened assertions, and other workarounds. The goal is for tests to pass because the actual bugs are fixed.

Command for Claude Code

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 commands/e0ipso/drupal-bridge-mcp/fix-broken-tests
Clone the repo
git clone --depth 1 https://github.com/e0ipso/drupal-bridge-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for fix-broken-tests

README.md
[![agentmods](https://agentmods.dev/badge/commands/e0ipso/drupal-bridge-mcp/fix-broken-tests.svg)](https://agentmods.dev/commands/e0ipso/drupal-bridge-mcp/fix-broken-tests)
Your own site
<a href="https://agentmods.dev/commands/e0ipso/drupal-bridge-mcp/fix-broken-tests"><img src="https://agentmods.dev/badge/commands/e0ipso/drupal-bridge-mcp/fix-broken-tests.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 293 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00008 $0.00293
Opus 5 $0.00004 $0.00147
Sonnet 5 $0.00002 $0.00059
Haiku 4.5 $0.00001 $0.00029

Measured 4d ago against content hash 1fd2992bd046, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-broken-tests 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 4d 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.

.claude/commands/tasks/fix-broken-tests.md · 39 lines

What it actually says

Fix all failing tests in this repository. Think harder and use tools.

Execute this command to run the tests:

If the test command is empty, read CLAUDE.md for test execution instructions.

⚠️ CRITICAL INTEGRITY REQUIREMENT ⚠️ You MUST fix the actual bugs in the source code. Green tests are worthless if achieved through cheating.

This is CHEATING (absolutely forbidden):

  • Skipping tests with conditionals
  • Modifying test assertions to pass
  • Adding test-environment-specific code to source
  • Disabling or commenting out tests
  • ANY workaround that doesn't fix the real bug

This is THE RIGHT WAY:

  • Find the root cause in the source code
  • Fix the actual bug
  • Ensure tests pass because the code truly works

Process:

  1. Run all tests to identify failures
  2. Fix EVERY failing test iteratively
  3. Verify all tests pass legitimately

DO NOT STOP after fixing some tests - fix ALL of them.

Remember: The entire point of tests is to ensure code robustness. If you cheat in ANY way, the tests become meaningless and I cannot trust that the code actually works.

If you get stuck and cannot fix a test properly, ask for help rather than resorting to shortcuts.

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. 4d ago First seen · 39 lines · 8 tokens per session scan A 1fd2992bd046

Subscribe to this mod's changes

fix-broken-tests is a command published in the GitHub repository e0ipso/drupal-bridge-mcp (5 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 293 once invoked, about $0.0000 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.