---
title: Claude Agent Template Library
category: product
entity_type: skill
price: $15
canonical: https://forgehouse.ai/skills/claude-agent-template-library/
lang: en
hreflang_alt: https://forgehouse.ai/tr/skiller/claude-agent-template-library/
last_updated: 2026-06-20
---

# Claude Agent Template Library

> A categorized canon of 100+ Claude Code subagent templates with a strict frontmatter standard, enforcing Mission Brief, Agent Chain and bypass-permissions discipline.

A categorized canon of 100+ Claude Code subagent templates with a strict frontmatter standard (name, description, tool whitelist, model alias, system prompt). It enforces the three disciplines that make agent dispatch reliable: the Mission Brief pattern, Agent Chain handoffs, and the never-forgotten bypass-permissions mode. Build new agents from proven templates instead of from scratch, and retroactively audit your existing fleet for missing guardrails.

## Use cases
- Authoring a new subagent with correct frontmatter and tool whitelist
- Adding a new capability to an existing agent without breaking its scope
- Designing a multi-agent pipeline with mandatory chain handoffs
- Creating a platform-specific specialist agent for a new customer type
- Auditing your current agent fleet for missing guardrails
- Debugging dispatch failures from a forgotten permissions mode

## Benefits
- Save 80%+ effort by cloning canon templates instead of writing agents from zero
- Eliminate dispatch interruptions by enforcing bypass-permissions mode every time
- Keep each agent focused with single-responsibility 'does / doesn't' tables
- Prevent scope creep with the 5-field Mission Brief on every dispatch

## What’s included
- A complete agent frontmatter skeleton with tool pattern-whitelisting and model alias rules
- A 100+ template taxonomy across research, planning, coding, writing, orchestration, RAG and more
- The 5-field Mission Brief template (purpose, in-scope, out-of-scope, done criteria, verification)
- A dispatch wrapper that validates the brief and queues mandatory chain-after agents
- A retroactive audit script that flags missing guardrails across your agent fleet
- An anti-pattern catalog covering open Bash whitelists, missing chains, and PII leakage

## Who it’s for
Teams building and maintaining a fleet of Claude Code subagents who want reliable, standardized dispatch instead of one-off agents that need constant supervision.

## How it runs
New agents start from a 100+ template taxonomy, not a blank file. Cloning, strict frontmatter, a Does and Does-not table and a mandatory downstream chain keep every agent single-purpose and auditable.
1. Classifies the requested agent against a 100+ template taxonomy (research, planning, coding, writing, multi-agent, RAG, browser automation) and clones the closest canonical template instead of writing from scratch
2. Fills the fixed frontmatter skeleton: name, trigger-keyword description for intent matching, model alias instead of a hardcoded version, a pattern-based tool whitelist (never open-ended shell access), and chain links to predecessor and successor agents
3. Writes the Does / Does-not table so the agent carries a single responsibility, plus an anti-pattern section of at least five forbidden behaviors
4. Embeds a Mission Brief parser into the system prompt: the agent must reject any dispatch missing purpose, in-scope, out-of-scope, done criteria or verification, which kills scope creep at the door
5. Runs the audit script across all existing agents, checking frontmatter completeness, chain discipline and tool whitelist strictness, and outputs a PASS / NEEDS-PATCH table per agent
6. Registers the mandatory next-hop chain (code work hands off to QA, content hands off to SEO review) so no agent output ships without its downstream check

## FAQ
### Are these tied to Claude Code, or generic agent prompts?
They are built around the Claude Code subagent format, with the frontmatter fields dispatch actually reads: name, description, tool whitelist, model alias and system prompt. That is what lets them drop in rather than need translation.

### Is a library of a hundred-plus templates just a pile to dig through?
They are categorized as a canon, and the value is the shared standard underneath: the Mission Brief pattern, chain handoffs and the dispatch settings that are easy to forget. You copy a known-good shape instead of re-deriving it each time.

### Will a template give my agent its actual domain expertise?
No, it gives you a correct, scoped skeleton with the disciplines wired in. The specific instructions and knowledge for your task are still yours to write into the system prompt.

## Price
$15, one-time, no subscription. VAT included.

Related guide: [AI and LLM engineering](https://forgehouse.ai/guides/ai-llm-engineering/)