agentsclimarketplace

Check environment

Skill claude-world/director-mode-lite/skills/check-environment

Verify Claude, Codex, and Grok availability plus Director guidance, relay, agents, and skills. Audit optional hooks only when selected. Use after installation or when a native surface misbehaves.From its SKILL.md

Install
npx -y skills add claude-world/director-mode-lite --skill check-environment

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • runs commandsInstructs the agent to run 8 commands, including `git --version` and 7 more.

SKILL.md

3.2 KB, 858 tokens by cl100k_base, as published. Nobody here has run it

Environment Check

Verify your development environment is ready for Director Mode.


Checks Performed

1. Director Mode Dependencies

ToolPurposeCheckRequired
gitVersion controlgit --versionYes
python3Installer, adapters, and relaypython3 --versionYes
jqLegacy automation hooks onlyjq --versionNo

2. CLI versions

claude --version
codex --version
grok --version

Minimum: 2.0.0+

3. Project-Specific Tools

Auto-detect project type and check relevant tools:

Project TypeDetected ByTools to Check
Node.jspackage.jsonnode --version, npm --version or pnpm --version
Pythonrequirements.txt, pyproject.tomlpython3 --version, pip --version
RustCargo.tomlrustc --version, cargo --version
Gogo.modgo version
Javapom.xml, build.gradlejava --version, mvn --version or gradle --version

4. Director Mode Installation

  • .claude/ directory exists
  • .claude/skills/ populated (35 skills expected)
  • .agents/skills/ populated when the Codex adapter is selected
  • .director-mode/bin/director-relay is executable
  • .director-mode/bin/director-open is executable
  • .claude/agents/ populated (14 agents expected)
  • .codex/agents/ and .grok/agents/ populated for selected adapters
  • no active hooks for the default install
  • optional hooks match the explicitly selected mode and contain no surprise deny/block response
  • CLAUDE.md exists

5. Git Status

  • Inside git repository
  • Clean working tree (or note uncommitted changes)

Output Format

## Environment Check Results

### Director Mode Dependencies
- [x] git: 2.39.0
- [x] python3: 3.11.0
- [x] jq: 1.7

### Claude Code
- [x] Version: 2.1.201

### Project Tools (Node.js detected)
- [x] node: 20.10.0
- [x] pnpm: 8.12.0

### Director Mode Installation
- [x] .claude/ directory exists
- [x] 35 skills installed
- [x] Cross-CLI guidance and relay installed
- [x] 14 agents installed
- [x] default hook mode: none
- [x] native open launcher installed
- [x] CLAUDE.md exists

### Git Status
- [x] Git repository initialized
- [ ] Warning: 3 uncommitted changes

### Summary
**Status**: Ready

Follow-up Actions

IssueAction
Missing python3Install Python 3: brew install python3 (macOS) or apt install python3 (Linux)
Missing jqIgnore unless legacy --hooks automation was explicitly selected
Missing gitInstall git for your OS
Missing nodeInstall Node.js LTS: https://nodejs.org
Old Claude CodeRun claude update
No .claude/Run install script: ./install.sh .
Unexpected hooks activeInspect Claude user settings and grok inspect --json; Grok may load Claude-compatible hooks
No CLAUDE.mdRun /project-init or /claude-md-template

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most quality gates skills give in 858 tokens

Counted across 1,524 of the 2,830 authors here whose files we hold, read 2026-09-06

  • Read full output and check exit codein 45 of 1524, across 40 files
  • Verify output confirms the claimin 44 of 1524, across 39 files
  • Identify the command that proves the claimin 43 of 1524, across 39 files
  • Execute the full verification commandin 36 of 1524, across 30 files
  • Produce a verification reportin 34 of 1524, across 18 files
  • Review git diff changesin 30 of 1524, across 16 files
  • Fix build failures immediatelyin 29 of 1524, across 9 files
  • Group findings by severityin 28 of 1524
  • State claim only with evidencein 27 of 1524, across 22 files
  • Verify regression tests with red-green cyclein 26 of 1524, across 22 files
  • Run the full test suitein 26 of 1524, across 25 files
  • Run test suite with coveragein 25 of 1524, across 10 files

Said here and by no other author read

  • Verify python3 version
  • Check claude version
  • Check codex version
  • Check grok version
  • Verify executable permissions
  • Report environment check results

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.