agent-development

agent-development is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 36 tokens per session (2,350 once invoked), scanned B, original, MIT.

A guide for creating and checking Claude Code subagents, which are specialized workers that operate with their own context and defined tool access.

In plain words
What is it for?
Use it to create, audit, or refine an agent, including its folder structure, frontmatter, allowed tools, task scope, and validation checklist.
Why use it?
It helps prevent unclear responsibilities, invalid settings, and overly broad permissions. It also distinguishes configured workers from reusable instruction sets called skills.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Good fit Use it to create, audit, or refine an agent, including its folder structure, frontmatter, allowed tools, task scope, and validation checklist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager
Install

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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-development-git-fg-meta-plugin-manager
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-development-git-fg-meta-plugin-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.02350
Opus 5 $0.00018 $0.01175
Sonnet 5 $0.00007 $0.00470
Haiku 4.5 $0.00004 $0.00235

Measured 9d ago against content hash df4f1e7f010a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

agent-development scanned grade B with 1 finding 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 9d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| Limit destructive tools | Allow rm, rm -rf without hooks |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/agent/agent-development-git-fg-meta-plugin-manager/SKILL.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<mission_control> Create and audit agents that follow toolkit standards: proper configuration, tool constraints, and task scope <success_criteria>Agent has valid frontmatter, appropriate allowed-tools, and clear task scope</success_criteria> </mission_control>

Quick Start

If you need to create an agent: Create .claude/agents/name/ with agent.md.

If you need to audit an agent: Invoke this skill directly to validate configuration.

If you need to refine an agent: Compare against patterns and apply fixes.

If you need... Read this section...
Directory structure ## PATTERN: Directory
Frontmatter format ## PATTERN: Frontmatter
allowed-tools ## PATTERN: Allowed Tools
Perfect agent examples ## PATTERN: Perfect Agent
Common failures ## ANTI-PATTERN: Common Failures
Validation checklist ## Validation Checklist

Philosophy

Agents are specialized workers with isolated context. Unlike skills (portable knowledge), agents are configured workers with specific tool access and task scope.

Key insight: Agents are "configured workers" - they have specific capabilities defined by their configuration, unlike skills which encode knowledge.

Why this matters:

  • Agents have isolated context (Task tool spawns subagent)
  • Agents can have tool restrictions (allowed-tools)
  • Agents are task-specific workers, not general knowledge
  • Agent behavior is defined by frontmatter, not SKILL.md

PATTERN: Directory

Agents use a simple directory structure:

.claude/agents/agent-name/
└── agent.md

Directory Structure

Item Purpose
agent.md Agent configuration with frontmatter
No references/ Agents are self-configuring

Example Structure

.claude/agents/
├── planning-agent/
│   └── agent.md
├── code-review-agent/
│   └── agent.md
└── testing-agent/
    └── agent.md

PATTERN: Frontmatter

Read the full file on GitHub · 408 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago First seen · 408 lines · 36 tokens per session scan B df4f1e7f010a

Subscribe to this mod's changes

agent-development is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 2,350 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.