agentmods.dev

issues: Command for Claude Code

.cursor/commands/fix_tests.md

Fix All Tests is a command for Claude Code, Cursor from vepo/issues. It costs 17 tokens per session (399 once invoked), scanned A, original, Apache-2.0.

An automated command for diagnosing and fixing failing Maven tests, with an optional check for frontend tests. Maven is a Java build tool that runs tests and verifies the project.

In plain words
What is it for?
Use it to investigate failed unit or frontend tests, apply direct fixes, rerun individual tests, and finish with a full Maven verification.
Why use it?
It organizes failures by their underlying cause and checks each fix by running the relevant test again. This avoids hiding failures with skipped tests, delays, or ignored errors.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md).

This is vepo/issues's own configuration. It tells Claude Code and Cursor how to work on issues itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything issues configures →

not rated 8repo 3mo ago A scan 17 tokens original Apache-2.0
View source ↗ vepo/issues
Reuse

Borrowing it

Nothing to install: this file belongs to vepo/issues. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vepo/issues/main/.cursor/commands/fix_tests.md
Clone the repo
git clone --depth 1 https://github.com/vepo/issues

Made for: Claude Code, Cursor.

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 All Tests

README.md
[![agentmods](https://agentmods.dev/badge/commands/vepo/issues/fix_tests/github.svg)](https://agentmods.dev/commands/vepo/issues/fix_tests)
Your own site
<a href="https://agentmods.dev/commands/vepo/issues/fix_tests"><img src="https://agentmods.dev/badge/commands/vepo/issues/fix_tests/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Fix All Tests

Your own site · 80×15
<a href="https://agentmods.dev/commands/vepo/issues/fix_tests"><img src="https://agentmods.dev/badge/commands/vepo/issues/fix_tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00017 $0.00399
Opus 5.5 $0.00007 $0.00160
Sonnet 5.5 $0.00003 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 1mo ago against content hash a1732e4aa8e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Fix All 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 1mo 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.

.cursor/commands/fix_tests.md · 41 lines

What it actually says

You are an expert Java developer. Fix all failing tests in the Issues project.

Follow issues-testing.mdc and issues-test-failure-diagnosis.mdc.

Follow this exact loop — do not ask for confirmation and do not invent workarounds.

  1. Discover failures

    mvn test

    If frontend may be affected, also run:

    cd src/main/webui && npm test -- --no-watch --browsers=ChromeHeadless

  2. Check for failures

    • If no test failures, run mvn verify. If green, print ✅ All tests pass! and stop.
    • Otherwise proceed to step 3.

  3. List each failing test with the reason Parse target/surefire-reports/*.txt. Group failures by root cause. For each:

    • Test class & method name
    • Exception type and stack trace
    • Assertion details (expected vs actual)

  4. Fix each root cause (one at a time)

    • Read ARCHITECTURE.md and the test + production code.
    • Apply a direct fix — never Thread.sleep(), @Disabled, or swallowed exceptions.
    • Re-run: mvn test -Dtest=ClassName#methodName

  5. Repeat steps 3–4 until tests pass, then run mvn verify once.

After fix is green: write one report under reports/ per issues-test-failure-diagnosis.mdc.

Start the loop now.

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. 1mo ago First seen · 41 lines · 17 tokens per session scan A a1732e4aa8e7

Subscribe to this mod's changes

Fix All Tests is a command published in the GitHub repository vepo/issues (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 399 once invoked, about $0.0001 per session on Opus 5.5. 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.

DebuggingTestingangularquarkus
Related

Other commands, from other repositories

playwright-test-heal

Run all my tests and fix the failing ones.

microsoft/playwright · 2 tokens

verify-bug

Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.

HoangNguyen0403/agent-skills-standard · 0 tokens

api-aqa-flow-execution-and-report-analysis

Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).

griddynamics/rosetta · 28 tokens

bugfix

Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.

nWave-ai/nWave · 18 tokens

timeout-fix

A procedure for diagnosing and fixing tests that exceed their time limit by finding causes such as slow processing, hanging network calls, deadlocks, heavy setup, or leaked resources.

classmethod/tsumiki · 52 tokens

AGENTS

Run the current binary in a temporary test repository with a real PTY. Use tmux-cli when available, capture terminal output, and inspect -vv logs when behavior depends on timing or shell state. Avoid treating a piped command as proof of interactive behavior.

max-sixty/worktrunk · 0 tokens