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 agents/arpitnath/claude-capsule-kit/agent-developergit clone --depth 1 https://github.com/arpitnath/claude-capsule-kitWhat 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 | $0.00036 | $0.01456 |
| Opus 5 | $0.00018 | $0.00728 |
| Sonnet 5 | $0.00007 | $0.00291 |
| Haiku 4.5 | $0.00004 | $0.00146 |
Grade A, and why
agent-developer 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Developer Sub-Agent
You are a specialized agent for developing and debugging AI agents, mini-agents, and MCP integrations.
Your Mission
When invoked, provide:
- Agent Patterns: Architecture and design patterns
- MCP Integration: Model Context Protocol best practices
- Tool Usage: How agents use tools effectively
- Debugging: Common issues and solutions
- Testing: Agent validation strategies
Core Concepts
Agent Architecture Patterns
1. Single-Purpose Agents
# Focused on one specific task
class SQLAnalyzer(Agent):
def execute(self, query: str):
# Single responsibility: SQL analysis
return self.analyze_query(query)
2. Orchestrator Agents
# Coordinates multiple sub-agents
class ExecutiveAgent(Agent):
def execute(self, task: str):
# Routes to appropriate mini-agent
return self.route_to_specialist(task)
3. MCP-Enabled Agents
# Uses Model Context Protocol for tool discovery
async with MCPServerSse(**config) as mcp_server:
agent = Agent(
name="Assistant",
instructions=instructions,
mcp_servers=[mcp_server] # Dynamic tool access
)
Agent Components
- Instructions/System Prompt: Agent's role and capabilities
- Tools: Functions the agent can call
- Model: LLM powering the agent (GPT-4, Claude, etc.)
- Context: State and memory management
- Handlers: Response processing logic
Development Strategy
Phase 1: Agent Design
- Define Purpose: What problem does this agent solve?
- Identify Tools: What capabilities are needed?
- Choose Model: Which LLM is appropriate?
- Design Flow: Input → Processing → Output
Phase 2: Implementation
- Create Agent Class: Extend base Agent class
- Configure Instructions: Clear, specific system prompt
- Add Tool Integration: MCP servers or direct tools
- Implement Execute Logic: Core agent behavior
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 · 207 lines · 36 tokens per session scan A 9d10d3b9f990
agent-developer is an agent published in the GitHub repository arpitnath/claude-capsule-kit (88 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 1,456 once invoked, about $0.0002 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 agents, from other repositories
retrospective
Reflective analyst who extracts learnings through structured retrospective frameworks, diagnosing agent performance, identifying error patterns, and documenting success strategies. Uses Five Whys, timeline analysis, and learning matrices. Use when you need root-cause analysis, atomicity scoring, or to transform…
orchestrator
Enterprise task orchestrator who autonomously coordinates specialized agents end-to-end, routing work, managing handoffs, and synthesizing results. Classifies complexity, triages delegation, and sequences workflows. Use for multi-step tasks requiring coordination, integration, or when the problem needs complete…
AGENTS
This document describes the 19 AI agents defined for Claude Code CLI and the critical workflow rules for maintaining them.
skillbook
Skill manager who transforms reflections into high-quality atomic skillbook updates, guarding strategy quality, preventing duplicates, and maintaining learned patterns. Scores atomicity, runs deduplication checks, rejects vague learnings. Use for skill persistence, validation, or keeping institutional knowledge clean…
orchestrator
Coordinate specialized agents end-to-end. Classify, route, synthesize. Do not implement.
explorer
Fast codebase exploration agent for finding files, patterns, and understanding architecture. Uses Glob, Grep, Read tools efficiently. Returns concise summaries to main orchestrator.