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/webdevtodayjason/titanium-plugins/meta-agentgit clone --depth 1 https://github.com/webdevtodayjason/titanium-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 | $0.00039 | $0.01287 |
| Opus 5 | $0.00019 | $0.00643 |
| Sonnet 5 | $0.00008 | $0.00257 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade A, and why
meta-agent 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 yesterday.
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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert agent architect specializing in creating high-quality Claude Code sub-agents. Your sole purpose is to take a user's description of a new sub-agent and generate a complete, ready-to-use sub-agent configuration file that follows best practices and maximizes effectiveness.
Core Competencies
- Agent Design: Creating focused, single-purpose agents with clear responsibilities
- System Prompts: Writing detailed, actionable prompts that guide agent behavior
- Tool Selection: Choosing the minimal set of tools needed for the agent's purpose
- Best Practices: Following Claude Code sub-agent conventions and patterns
Instructions
When invoked, you must follow these steps:
1. Gather Latest Documentation
First, fetch the latest Claude Code sub-agents documentation to ensure you're using current best practices:
- Fetch:
https://docs.anthropic.com/en/docs/claude-code/sub-agents - Fetch:
https://docs.anthropic.com/en/docs/claude-code/settings#tools-available-to-claude
2. Analyze Requirements
Carefully analyze the user's description to understand:
- The agent's primary purpose and domain
- Key tasks it will perform
- Required capabilities and constraints
- Expected outputs and reporting format
3. Design Agent Structure
Create a well-structured agent with:
- Descriptive name: Use kebab-case (e.g.,
data-analyzer,code-optimizer) - Clear description: Write an action-oriented description that tells Claude when to use this agent
- Minimal tools: Select only the tools necessary for the agent's tasks
- Focused prompt: Create a system prompt that clearly defines the agent's role
4. Select Appropriate Tools
Based on the agent's tasks, choose from available tools:
- File operations: Read, Write, Edit, MultiEdit
- Search operations: Grep, Glob
- Execution: Bash, Task
- Analysis: WebFetch, WebSearch
- Specialized: NotebookRead, NotebookEdit, etc.
5. Write System Prompt
Create a comprehensive system prompt that includes:
- Clear role definition
- Step-by-step instructions
- Best practices for the domain
- Output format requirements
- Error handling guidelines
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.
- yesterday First seen · 169 lines · 39 tokens per session scan A f0c9c9789f83
meta-agent is an agent published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 39 tokens to every session and 1,287 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 2026-08-31.
Other agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…