Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/emdashcodes/claude-code-plugins/claude-code-subagentsnpx skills add emdashcodes/claude-code-plugins --skill claude-code-subagentsgit clone --depth 1 https://github.com/emdashcodes/claude-code-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00055 | $0.02249 |
| Opus 5 | $0.00028 | $0.01125 |
| Sonnet 5 | $0.00011 | $0.00450 |
| Haiku 4.5 | $0.00006 | $0.00225 |
Grade A, and why
claude-code-subagents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Subagents
Guide Claude through creating and configuring specialized subagents for Claude Code.
Purpose
Subagents are pre-configured AI personalities that handle specific types of tasks with their own context windows, custom system prompts, and tool configurations. This skill helps create well-structured subagents that improve task delegation, context management, and specialized workflows.
When to Use This Skill
Use this skill when:
- Creating new custom subagents (project, personal, or plugin)
- Configuring subagent properties (tools, model, system prompts)
- Setting up specialized workflows with subagent delegation
- Troubleshooting subagent invocation or behavior
Subagent Types
Project Subagents
- Stored at:
.claude/agents/ - Shared with the team (versioned in git)
- Highest priority when name conflicts occur
- Team-specific workflows and conventions
Personal Subagents
- Stored at:
~/.claude/agents/ - Available across all projects
- Lower priority than project subagents
- Personal preferences and workflows
Plugin Subagents
- Stored at:
agents/in plugin root - Distributed via plugin marketplaces
- Shown as
(plugin:plugin-name)in/agents - Support all configuration features
- Can be invoked explicitly or automatically
Creating Subagents
Quick Creation with Helper Script
Use the bundled creation script for fast, templated subagent setup:
# Create project subagent with code-reviewer template
scripts/create_subagent.sh code-reviewer --project --template code-reviewer
# Create personal subagent with custom template
scripts/create_subagent.sh my-agent --user --template debugger
# Create plugin subagent (auto-detects plugin from current directory)
scripts/create_subagent.sh my-agent --plugin
# Create plugin subagent for specific plugin
scripts/create_subagent.sh my-agent --plugin my-plugin-name
# Available templates: code-reviewer, debugger, custom
The script is located at: scripts/create_subagent.sh
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 318 lines · 55 tokens per session scan A 7cce767637a0
claude-code-subagents is a skill published in the GitHub repository emdashcodes/claude-code-plugins (13 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,249 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
agentmail
Use when an agent needs AgentMail CLI email inboxes.
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Agent Development
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development…
skill-creator
Scaffold a new yoyo skill when a human or community issue asks for one ("add a skill for X", "create a skill that does Y"). Generates correct frontmatter, validates, writes to disk.
subagent-delegation
Canonical protocol for delegating GSD work to native Antigravity subagents — when to delegate, how to invoke, workspace isolation modes, and the inline fallback for older IDE versions.