NetFabric/NetFabric.Numerics / .agents/skills/claude-code-custom-agents
claude-code-custom-agents
VerifiedCreate and maintain Claude Code custom subagents (.claude/agents/*.md files). USE FOR: authoring project (.claude/agents/) or user (~/.claude/agents/) subagent files; frontmatter fields (name, description, tools, disallowedTools, model, permissionMode, maxTurns, skills, mcpServers, hooks, memory, background, effort, isolation, color, initialPrompt); writing descriptions that drive automatic delegation and 'use proactively' phrasing; invoking subagents via natural language, @-mention, session-wide --agent, or the Agent tool; restricting which subagent types a coordinator can spawn with Agent(name1, name2); nested subagents and depth limits; built-in subagents (Explore, Plan, general-purpose, claude); troubleshooting a subagent that won't load or isn't invoked. DO NOT USE FOR: GitHub Copilot CLI custom agents (use copilot-cli-custom-agents); agent teams/teammates (a different, session-spanning feature); MCP server authoring; SKILL.md authoring (use create-skill).
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.1 KB |
| references/authoring-workflow.md | markdown | 3.4 KB |
| references/delegation-and-squads.md | markdown | 3.5 KB |
| references/frontmatter-reference.md | markdown | 5.0 KB |
| references/undocumented-and-gotchas.md | markdown | 3.3 KB |
| references/writing-style.md | markdown | 2.8 KB |
references/writing-style.md
View on GitHub# Writing Style: Descriptions and Prompt Bodies
## The `description` field drives delegation
Claude matches your request, the current context, and every subagent's `description` to decide whether to delegate — there is no separate routing config. A vague description ("Backend helper") rarely triggers; a specific one with concrete trigger conditions does.
| Weak | Strong |
| --- | --- |
| "Code helper" | "Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code." |
| "Database agent" | "Execute read-only database queries. Use when analyzing data or generating reports." |
Include "**use proactively**" or "**use immediately after X**" when the subagent should be delegated to eagerly rather than only on an explicit request — this phrasing measurably changes delegation behavior, it isn't just documentation flavor.
## Prompt body structure
The body is the subagent's entire system prompt (plus environment details Claude Code appends) — it does not inherit the main conversation's system prompt, output style, or history. Write it as a self-contained role definition:
```markdown
You are a senior code reviewer ensuring high standards of code quality and security.
When invoked:
1. Run git diff to see recent changes
2. Focus on modified files
3. Begin review immediately
Review checklist:
- Code is clear and readable
- No exposed secrets or API keys
- Input validation implemented
Provide feedback organized by priority: critical issues (must fix), warnings
(should fix), suggestions (consider improving). Include specific examples.
```
| Section | Purpose |
| --- | --- |
| Role statement | One line establishing expertise/persona |
| Numbered "when invoked" steps | Concrete first actions — a subagent starts with no context, so tell it where to look |
| Domain checklist | The specific things this role must check/produce |
| Output format | How results should be organized (priority tiers, sections, etc.) — this is what actually reaches the parent conversation |
## Restating rules the subagent needs
A subagent doesn't see the main conversation's `CLAUDE.md`-derived understanding directly beyond the raw file content, and `Explore`/`Plan` skip `CLAUDE.md` and git status entirely. If a rule from your project conventions must reach the subagent (e.g. "ignore the `vendor/` directory"), restate it explicitly in the delegation prompt or the subagent's own body — don't assume it's inherited.
## Anti-patterns
- ❌ A description that only names a technology ("Python agent") instead of a task/trigger
- ❌ Omitting numbered steps and expecting the subagent to infer a workflow from a vague role description
- ❌ Assuming project conventions from `CLAUDE.md` reach the subagent automatically
- ❌ Writing an output format the parent conversation has to reformat before using it
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |