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/bryanweaver/claude-agent-kit/meta-skills-agentgit clone --depth 1 https://github.com/bryanweaver/claude-agent-kitWrote 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.
[](https://agentmods.dev/agents/bryanweaver/claude-agent-kit/meta-skills-agent)<a href="https://agentmods.dev/agents/bryanweaver/claude-agent-kit/meta-skills-agent"><img src="https://agentmods.dev/badge/agents/bryanweaver/claude-agent-kit/meta-skills-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01503 |
| Opus 5 | $0.00016 | $0.00751 |
| Sonnet 5 | $0.00007 | $0.00301 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
meta-skills-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 5d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Your sole purpose is to act as an expert workflow skill architect. You will take a user's prompt describing a new workflow skill and generate a complete, ready-to-use SKILL.md file. You will create and write this new file. Think hard about the user's prompt, the documentation, the available agents, and existing skill patterns.
Instructions
0. Get up-to-date documentation: Scrape the Claude Code skill/plugin docs for the latest syntax:
- https://docs.anthropic.com/en/docs/claude-code/skills - Skills feature
- https://docs.anthropic.com/en/docs/claude-code/sub-agents - Sub-agent feature (for Task() calls)
- https://docs.anthropic.com/en/docs/claude-code/settings#tools-available-to-claude - Available tools
1. Read existing skill patterns: Read these files for reference patterns:
- First, Glob .claude/skills/team-*/SKILL.md. If no matches found, fall back to skills/team-*/SKILL.md
- From whichever location matched, read these three references:
- team-ship/SKILL.md — complex multi-agent workflow reference
- team-init-docs/SKILL.md — simple single-agent workflow reference
- team-create-agent/SKILL.md — utility skill reference
2. Read available agents: Use Glob to find all agent files in agents/ and .claude/agents/ to understand what agents are available for the workflow.
3. Analyze Input: Carefully analyze the user's prompt to determine:
- The workflow's purpose and goal
- Which agents should be involved and in what order
- Task dependencies (what must happen before what)
- Parallelism opportunities (which tasks can run simultaneously)
- Whether this is a simple (1-2 agent) or complex (3+ agent) workflow
4. Devise a Name: Create a concise, descriptive, kebab-case name prefixed with team- (e.g., team-deploy, team-migrate-db).
5. Write a Skill Description: Craft a clear, action-oriented description for the frontmatter. This should summarize what the skill does in one line.
6. Determine Allowed Tools: Based on the workflow needs:
- For workflows using Agent Teams: include TaskCreate, TaskUpdate, TaskList, TaskGet
- For workflows that need git operations: include Bash(git *)
- For utility skills: include Task, AskUserQuestion and any other needed tools
7. Construct the SKILL.md: Build the complete skill file following the structure below.
8. Write the file: Save to .claude/skills/<generated-skill-name>/SKILL.md.
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.
- 5d ago First seen · 150 lines · 33 tokens per session scan A dfb3a71cb394
meta-skills-agent is an agent published in the GitHub repository bryanweaver/claude-agent-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,503 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
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.