running-tests · zaxbyhub — skill for Claude Code: run tests in opencode-swarm
running-tests — a skill to safely run tests in opencode-swarm from Claude Code, Codex, or OpenCode. Runs focused tests, checks file isolation, validates changes as in CI, and diagnoses errors without stalling the session.
MIT ★ 539 updated 2026-10-29
npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a claude-codeWhat running-tests does
Use it when the agent runs focused tests on a single file, checks test impact from changes, validates the full set as in CI, or diagnoses truncated output. Inside: a shell adapter for bun --smol test, file loops, and repo scripts. On Windows, if Bun reports EPERM after a forced dependency refresh, rerun the same command with elevated access before treating it as a test failure.
Requires Bun and shell access. One file or explicit test can be targeted narrowly; for multiple files use loops or documented tier commands. The skill reads AGENTS.md and .opencode/skills/running-tests/SKILL.md to find the exact commands.
What it helps with
- run focused tests on a single file without stalling
- check which tests broke after your changes
- isolate tests for one component
- validate the full test suite as in a CI pipeline
- diagnose truncated or incomplete test output
Example prompts for the agent
- Run tests for
src/utils.test.ts - Check impact of changes on all tests with a file loop
- Run the full test suite as in CI and capture long output
How to install running-tests
1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a claude-code2Manually: put the files in place
~/.claude/skills/running-tests/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/running-tests/
1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a codex2Manually: put the files in place
.agents/skills/running-tests/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a cursor2Manually: put the files in place
.cursor/skills/running-tests/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install ZaxbyHub/opencode-swarm .agents/skills/running-tests2Manually: put the files in place
.github/skills/running-tests/SKILL.md1Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a gemini-cli2Platform CLI
gemini skills install https://github.com/ZaxbyHub/opencode-swarm --path .agents/skills/running-testsManually: put the files in place
.devin/skills/running-tests/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about running-tests
How do I install running-tests in Claude Code?
Run npx skills add ZaxbyHub/opencode-swarm --skill running-tests -a claude-code, then load ~/.claude/skills/running-tests/SKILL.md.
What does running-tests do?
It's an adapter to safely run opencode-swarm tests inside Claude Code, Codex, or OpenCode. Runs focused tests, checks file isolation, validates as in CI, and diagnoses errors without stalling the session.
What do I need for the skill to work?
Bun and shell access. On Windows, if Bun reports EPERM after a dependency refresh, rerun the command with elevated access.
Source text
SKILL.md · MIT
--- name: running-tests description: Codex adapter for safely executing opencode-swarm tests. Use whenever Codex needs to run focused tests, per-file isolation loops, CI-equivalent validation, test-impact checks, or diagnose failing/truncated test output without stalling the session. metadata: audience: swarm-plugin --- # Running Tests Use this adapter when executing tests in `opencode-swarm`. For writing tests, load `$writing-tests` instead. Read, in order: 1. `AGENTS.md` 2. `.opencode/skills/running-tests/SKILL.md` Codex-specific execution notes: - Use the available shell execution tool for `bun --smol test` and PowerShell/bash loops. - Prefer `rg` and repo scripts to rediscover exact commands from source. - Capture long output to a temp file when needed and report the important tail or failure lines. - Do not use broad OpenCode `test_runner` scopes for repo validation. - On Windows, if Bun reports `EPERM` after a forced dependency refresh, rerun the same focused command with approved/elevated access before treating it as a test failure. Default rule: one source file or one explicit test file can be targeted narrowly; multiple files or directories should use shell loops or the documented tier commands.
© ZaxbyHub · MIT · ZaxbyHub/opencode-swarm
Similar skills
All skills for Testing and QA →running-tests by other authors comes first.