# everything-claude-code-harness

The skill builds out an agent harness: subagents, slash commands, memory hooks and a security scan. Useful when every Claude session starts from a blank slate.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1800 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/everything-claude-code-harness/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/everything-claude-code-harness

## What it does

Inside the skill you get a set of specialised subagents, skill modules, custom slash commands, lifecycle hooks and language rules. Commands run with the plugin prefix, so a planning call looks like `/everything-claude-code:plan` and a scan like `/everything-claude-code:security-scan`.

Hooks listen on `SessionStart`, `Stop`, `PostEdit`, `PreBash` and `PostBash`. Strictness comes from `ECC_HOOK_PROFILE` — `minimal`, `standard` or `strict` — and individual hooks are switched off by listing them in `ECC_DISABLED_HOOKS`. Package manager detection walks a chain that starts with `CLAUDE_PACKAGE_MANAGER`, then `.claude/package-manager.json`, then lock files.

The `rules/` folder is not shipped into your project by the plugin. You copy the stack you need into `.claude/rules/` or call `./install.sh` with a stack name such as `./install.sh typescript`, adding `--target cursor` when the rules should land in Cursor. Skip that step and the agent picks up commands and hooks while the rules never arrive.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill everything-claude-code-harness -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/everything-claude-code-harness/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/everything-claude-code-harness/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill everything-claude-code-harness -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/everything-claude-code-harness/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill everything-claude-code-harness -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/everything-claude-code-harness/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills everything-claude-code-harness
```

2. **Manually: put the files in place**
- File: `.github/skills/everything-claude-code-harness/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill everything-claude-code-harness -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/everything-claude-code-harness
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/everything-claude-code-harness/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill everything-claude-code-harness -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/everything-claude-code-harness/SKILL.md

## When to use it
- put the right rules for a TypeScript, Python, Go or Swift repo in place
- run a security scan before pushing a branch
- turn a pattern from a past session into a reusable instinct
- switch hook strictness to match the task at hand
- plan multi-agent work that spans backend and frontend

## Example prompts
- Run `/everything-claude-code:plan "Add an OAuth2 login flow"` and lay out the steps
- Scan the current branch with `/everything-claude-code:security-scan`
- Look into caching options first: `/everything-claude-code:research "content hashing for API responses"`

## Similar
- [setup-matt-pocock-skills](https://affpapa.org/en/nevibecode/skills/setup-matt-pocock-skills.md) — skill · 1052851 installs
- [ask-matt](https://affpapa.org/en/nevibecode/skills/ask-matt.md) — skill · 766587 installs
- [to-tickets](https://affpapa.org/en/nevibecode/skills/to-tickets.md) — skill · 711230 installs
- [writing-plans](https://affpapa.org/en/nevibecode/skills/writing-plans.md) — skill · 282859 installs
- [caveman-review](https://affpapa.org/en/nevibecode/skills/caveman-review.md) — skill · 411800 installs
- [caveman-compress](https://affpapa.org/en/nevibecode/skills/caveman-compress.md) — skill · 411500 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 139 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md