Test-first development, reliable unit and end-to-end tests, evidence-based root-cause debugging, and real-browser verification, for any language or framework.
A setup for AI coding agents, made by Kitloom. One source, generated for every major agent: Claude Code, OpenAI Codex, Cursor, Google Antigravity, Gemini CLI, GitHub Copilot, Windsurf (Devin), opencode and Aider.
- Download this repository as a ZIP, or use the Check and download button on its Kitloom page, which checks it first.
- Read the files. Nothing here runs on its own: the kit has no hooks and no install scripts.
- Copy the folders and files you want into the root of your project.
AGENTS.mdis the shared instructions file; edit it to fit your project.
tdd— Building a feature or fixing a bug test-first with a red-green-refactor loop.diagnosing-bugs— Something is broken, throwing, failing or slow and the cause is not obvious yet.debugging-and-error-recovery— A test fails, a build breaks, or behaviour differs from what was expected.parallel-debugging— A bug has several plausible causes and you want competing hypotheses tested against evidence.five-whys— A problem keeps coming back and you need the cause you can fix, not the symptom.e2e-testing-patterns— Writing or repairing Playwright or Cypress tests, especially flaky ones.browser-testing-with-devtools— Checking behaviour in a real browser: DOM, console errors, network requests, performance.kiro-verify-completion— Before saying a fix works, tests pass or a task is done, to back the claim with fresh evidence.
Invoke by name (for example /tdd-cycle).
tdd-cycle— Implement a described behaviour test-first, one red-green-refactor step at a time.debug— Investigate a failure to its root cause, then fix it with a regression test.flaky-test— Diagnose and stabilise an intermittently failing test.
bug-investigator— Delegate when a failure needs reproducing and tracing to a root cause without editing code.test-reviewer— Delegate to review new or changed tests for coverage gaps, brittleness and weak assertions.
test-files— Conventions for writing and editing test files.e2e-tests— Stability rules for end-to-end and browser tests.debugging-discipline— Always-on rule: find the root cause with evidence before changing code.
| Agent | Instructions | Skills and commands | Rules | Sub-agents |
|---|---|---|---|---|
| Claude Code | CLAUDE.md (imports AGENTS.md) |
.claude/skills/ |
.claude/rules/ |
.claude/agents/ |
| OpenAI Codex | AGENTS.md |
.agents/skills/ |
listed in AGENTS.md |
.codex/agents/ |
| Cursor | AGENTS.md |
.agents/skills/, .claude/skills/ |
.cursor/rules/ |
.claude/agents/ |
| Google Antigravity | AGENTS.md |
.agents/skills/ |
.agents/rules/ |
.agents/agents/ |
| Gemini CLI | AGENTS.md via .gemini/settings.json |
.agents/skills/, .gemini/commands/ |
listed in AGENTS.md |
.gemini/agents/ |
| GitHub Copilot | AGENTS.md |
.agents/skills/, .github/prompts/ |
.github/instructions/ |
.claude/agents/ |
| Windsurf (Devin) | AGENTS.md |
.agents/skills/, .windsurf/workflows/ |
.windsurf/rules/ |
— |
| opencode | AGENTS.md |
.agents/skills/, .opencode/commands/ |
listed in AGENTS.md |
.opencode/agents/ |
| Aider | AGENTS.md via .aider.conf.yml |
— | — | — |
Skills are stored twice (.agents/skills/ and .claude/skills/) because Claude Code reads only its own folder. Agents that read both may list a skill twice; delete the copy you do not need.
The skills come from these open-source repositories, each under its own licence. Their licence and a notice are kept beside every copied skill.
| Skill | Source | Licence |
|---|---|---|
tdd |
mattpocock/skills at 49dd158 |
MIT |
diagnosing-bugs |
mattpocock/skills at 49dd158 |
MIT |
debugging-and-error-recovery |
addyosmani/agent-skills at aeac41d |
MIT |
parallel-debugging |
wshobson/agents at 46891e7 |
MIT |
five-whys |
wesammustafa/Claude-Code-Everything-You-Need-to-Know at b97a62b |
MIT |
e2e-testing-patterns |
wshobson/agents at 46891e7 |
MIT |
browser-testing-with-devtools |
addyosmani/agent-skills at aeac41d |
MIT |
kiro-verify-completion |
gotalab/cc-sdd at e2a0c67 |
MIT |
Everything else in this repository (instructions, rules, commands, sub-agents) is by Kitloom under the MIT licence.
Read every file before you use it. Agent instructions can make an agent run commands on your machine. This kit was checked with Kitloom's pre-download check, which looks for warning signs but cannot prove anything is safe.