Skip to main content
skill CX Codex

ensure-all-tests-pass-after-code-changes — Claude Code skill

ensure-all-tests-pass-after-code-changes — a skill that keeps the agent honest about tests: run them after an edit, and don't hand a failing branch to review. Test updates ship with the code.

MIT ★ 539 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ZaxbyHub/opencode-swarm --skill ensure-all-tests-pass-after-code-changes -a claude-code
Open on GitHub

What ensure-all-tests-pass-after-code-changes does

The skill puts a rule in front of the agent: run the tests after touching code, and don't send a branch to review while something is failing. Test edits travel in the same change as the implementation.

Inside is a short procedure and a list of shortcuts that are off limits. One of them is spelled out: code that leaves existing tests broken doesn't go up for review. A reviewer walks the diff and confirms every required step is there.

When review turns up failures, the coder repairs the tests or reverts the change first, then comes back. The delegation template carries the path .opencode/skills/generated/ensure-all-tests-pass-after-code-changes/SKILL.md.

What it helps with

  • run the suite after an edit and confirm nothing broke
  • attach a test update to the same change
  • keep a red branch out of review
  • decide whether to repair a failing test or revert
  • check the diff for the test work the agent claims it did

Example prompts for the agent

  • Fix the retry logic in client.py and keep running the suite until it's green.
  • Add a test for the empty-input case in the same change as the code.
  • The suite went red after your edit — fix it or revert before I review.

How to install ensure-all-tests-pass-after-code-changes

1Skills CLI (Vercel)

npx skills add ZaxbyHub/opencode-swarm --skill ensure-all-tests-pass-after-code-changes -a claude-code

2Manually: put the files in place

~/.claude/skills/ensure-all-tests-pass-after-code-changes/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ensure-all-tests-pass-after-code-changes/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about ensure-all-tests-pass-after-code-changes

How do I install ensure-all-tests-pass-after-code-changes in Claude Code?

Run npx skills add ZaxbyHub/opencode-swarm --skill ensure-all-tests-pass-after-code-changes -a claude-code. The skill file lands at ~/.claude/skills/ensure-all-tests-pass-after-code-changes/SKILL.md.

What does ensure-all-tests-pass-after-code-changes do?

It makes the agent run the tests after a code change and include the test updates with the implementation. A change that breaks existing tests never reaches review.

What happens if a change breaks existing tests?

It stays out of review. The coder fixes the tests or reverts the change first.

Source text

SKILL.md · MIT
---
name: ensure-all-tests-pass-after-code-changes
description: ensure all tests pass after code changes
metadata:
  generated_from_knowledge: '["1020596e-e263-4ff9-acfe-d99302496b42"]'
  source_knowledge_ids: '["1020596e-e263-4ff9-acfe-d99302496b42"]'
  generated_at: "2026-07-14T05:31:49.592Z"
  confidence: "0.60"
  status: active
  version: "1"
  skill_origin: generated
---

<!-- generated by opencode-swarm skill-generator. Do not edit by hand; edits will be preserved on regeneration only with controlled update mode. -->

# ensure all tests pass after code changes

## Trigger

- (no explicit trigger metadata; cluster derived from category/tags)

## Required Procedure

- ensure all tests pass after code changes
- include test updates with implementation

## Forbidden Shortcuts

- submitting code that breaks existing tests for review

## Delegation Template

When delegating a task affected by this skill, include:

```
SKILLS: file:.opencode/skills/generated/ensure-all-tests-pass-after-code-changes/SKILL.md
```

## Reviewer Checks

- Verify each required action above appears in the diff.

## Source Knowledge IDs

- 1020596e-e263-4ff9-acfe-d99302496b42 — When a reviewer identifies test failures, the coder must fix the tests or revert the change before re-entering review.

© ZaxbyHub · MIT · ZaxbyHub/opencode-swarm

Similar skills

All skills for Testing and QA →

From the same set121

The whole set →
spread-real-module-exports-as-base-of-every-mock-module-return-o spread-real-module-exports-as-base-of-every-mock-module-return-o is a Claude Code skill that sets a pattern for objects returned by mock.module. It activates around that pattern and Node’s built-in mocking. CX Codex +1 ★ 539repo stars gate-attribution gate-attribution sets the rule that keeps reviewer and test_engineer checks attributable: one taskId per dispatch, with lanes run in parallel to save overhead. CX Codex +1 ★ 539repo stars swarm-implement Adapts the canonical opencode-swarm implementation workflow for multi-file features, refactoring, and structured validation. CX Codex +1 ★ 539repo stars opt-in-tool-registration The opt-in-tool-registration skill sets a pattern for registering opt-in tools through a separate map and conditional merging in agents/index.ts. Use it when adding a feature controlled by a flag. CX Codex +1 ★ 539repo stars codebase-review-swarm codebase-review-swarm executes quote-grounded codebase audits across security, QA, and performance. Suitable for full-repository assessments where no source files may be touched. CX Codex +1 ★ 539repo stars add-path-type-assertions-or-realpath-resolve-calls-in-path-joini add-path-type-assertions-or-realpath-resolve-calls-in-path-joini is a Claude Code skill that adds path-type checks or realpath/resolve calls to path-joining utilities. It activates around path.join, realpath, and fs path work. CX Codex +1 ★ 539repo stars run-failing-tests-immediately-after-test-gate-failure run-failing-tests-immediately-after-test-gate-failure is a Claude Code skill that makes the agent rerun failing tests when test_gate fails and repair the root cause before claiming the task is done. CX Codex +1 ★ 539repo stars run-tests-on-the-unmodified-codebase-before-starting-to-establis run-tests-on-the-unmodified-codebase-before-starting-to-establis is a Claude Code skill that requires running tests on untouched code before edits, recording failures to distinguish them from new regressions. CX Codex +1 ★ 539repo stars

Project sponsors

Companies that keep this analytics open