From director-mode-lite
Validates .claude/agents/*.md files for YAML frontmatter format including required name/description/color/model, optional tools/skills/hooks/memory, valid values, and content structure. Use on specific file or all.
npx claudepluginhub claude-world/director-mode-liteThis skill uses the workspace's default tool permissions.
Validate agent files in `.claude/agents/` for correct format.
Validates AI agent configuration files including SKILL.md, CLAUDE.md, AGENTS.md, hooks, MCP, Cursor, and Copilot instructions against 385 rules using agnix CLI. Supports lint, auto-fix, watch modes; installs tool if needed.
Audits Claude subagent configurations in .claude/agents/ for frontmatter completeness, tool assignment security, privilege risks, and naming consistency.
Audits and writes AGENTS.md files using execution-first standards, checking commands, gotchas, and signal-to-noise ratio. Use to review, refactor, score, or improve agent instructions.
Share bugs, ideas, or general feedback.
Validate agent files in .claude/agents/ for correct format.
.claude/agents/*.md---
name: agent-name # Required: lowercase, hyphenated, 3-50 chars
description: > # Required: 10-5000 chars, include triggering conditions + <example> blocks
Use this agent when [conditions]. Examples:
<example>
Context: [situation]
user: "[request]"
assistant: "[response using this agent]"
</example>
color: cyan # Required: yellow, red, green, blue, magenta, cyan
model: sonnet # Required: inherit, haiku, sonnet, opus, best, sonnet[1m], opus[1m], opusplan
tools: # Optional: YAML list (omit = all tools available)
- Read
- Write
- Grep
# forkContext: "true" # Optional: run in forked context (string "true"/"false")
# maxTurns: 20 # Optional: max conversation turns (positive integer)
skills: # Optional: auto-load skills (array)
- linked-skill
memory: # Optional: memory scopes to load (array)
- user
- project
- local
mcpServers: # Optional: MCP server refs or objects (array)
- server-name
hooks: # Optional: agent-scoped lifecycle hooks
PreToolUse:
- matcher: Write
hooks:
- type: command
command: ./validate.sh
PostToolUse:
- matcher: Bash
hooks:
- type: command
command: ./log.sh
permissionMode: default # Optional: permission handling
disallowedTools: # Optional: explicit tool blocking
- NotebookEdit
---
Read, Write, Edit, Bash, Grep, Glob, Task,
WebFetch, WebSearch, TodoWrite, NotebookEdit
yellow, red, green, blue, magenta, cyan
inherit, haiku, sonnet, opus, best, sonnet[1m], opus[1m], opusplan
name exists (lowercase, hyphenated, 3-50 chars)description exists (10-5000 chars, recommend 200-1000 with <example> blocks)color is set (valid color name)model is set (inherit/haiku/sonnet/opus/best/sonnet[1m]/opus[1m]/opusplan)tools are valid tool names, YAML list format (omit = all tools available)skills references existing skills (array, if set)forkContext is string "true" or "false" (if set)maxTurns is positive integer (if set)memory is valid array of: user, project, local (if set)mcpServers is valid array of string refs or objects (if set)hooks has valid structure (if set)permissionMode is valid value (if set)disallowedTools are valid tool names (if set)# Agent Name heading## Activation sectiontools uses YAML list format (not [Read, Write] bracket array)## Agent Validation Report
### Files Checked
| File | Status | Issues |
|------|--------|--------|
| code-reviewer.md | OK | None |
| my-agent.md | WARN | Missing color, model |
### Summary
- Total: [N]
- Valid: [N]
- Needs fixes: [N]
color field (default: cyan)model field (default: inherit)