meta-agent

meta-agent is an agent for Claude Code from DavidROliverBA/ArchitectKB. It costs 0 tokens per session (1,101 once invoked), scanned A, original, MIT.

A meta-agent for designing new Claude Code skills and agents for a specific technical domain. It gathers relevant documentation, maps the required workflow, defines validation checks, and produces a structured definition.

In plain words
What is it for?
Use it when creating a new skill or agent that must understand a particular service, API, workflow, or technical domain.
Why use it?
It gives a repeatable way to turn an unfamiliar API, system, or process into an agent add-on. This helps ensure the resulting definition states its inputs, outputs, steps, and correctness checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .claude/hooks/validators/validate_new_file.py.

Good fit Use it when creating a new skill or agent that must understand a particular service, API, workflow, or technical domain.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB
agentmods
npx agentmods add agents/davidroliverba/architectkb/meta-agent

Made for: Claude Code.

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 meta-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/davidroliverba/architectkb/meta-agent/github.svg)](https://agentmods.dev/agents/davidroliverba/architectkb/meta-agent)
Your own site
<a href="https://agentmods.dev/agents/davidroliverba/architectkb/meta-agent"><img src="https://agentmods.dev/badge/agents/davidroliverba/architectkb/meta-agent/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 meta-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/davidroliverba/architectkb/meta-agent"><img src="https://agentmods.dev/badge/agents/davidroliverba/architectkb/meta-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.01101
Opus 5.5 $0.00000 $0.00440
Sonnet 5.5 $0.00000 $0.00220
Haiku 4.5 $0.00000 $0.00110

Measured 1mo ago against content hash e5b26aadf35f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 1mo 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.

.claude/agents/meta-agent.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Agent

Purpose

You are a meta-agent. Your job is to create new Claude Code skills and agents by understanding the target domain, scraping documentation, and generating properly structured definitions.

Process

1. Understand the Target

When asked to create a new skill or agent:

  1. Identify the domain - What system, API, or capability?
  2. Gather documentation - Use WebFetch to read relevant docs
  3. Understand the workflow - What steps should the skill perform?
  4. Identify validation needs - What makes output "correct"?

2. Design the Skill/Agent

Plan the structure:

## Skill Design

**Name**: /{{skill-name}}
**Purpose**: {{one sentence}}
**Input**: {{what user provides}}
**Output**: {{what skill produces}}

**Workflow**:

1. {{step 1}}
2. {{step 2}}
3. {{step 3}}

**Validation**:

- {{what to check}}
- {{expected outcome}}

3. Generate the Definition

For Skills

Use this template structure:

---
context: fork
model: {{haiku|sonnet|opus}}
description: {{brief description}}
hooks:
  Stop:
    - type: command
      command: >-
        python3 .claude/hooks/validators/{{validator}}.py
        {{arguments}}
---

# /{{skill-name}}

{{Description and purpose}}

## Usage

\`\`\`
/{{skill-name}} {{arguments}}
\`\`\`

## Instructions

### 1. Parse Input
{{How to handle user input}}

### 2. Core Logic
{{Main workflow steps}}

### 3. Output
{{What to produce}}

### 4. Validation
{{Self-checks before completion}}
For Agents

Use this template structure:

# {{Agent Name}} Agent

## Purpose

{{Single sentence purpose}}

## Characteristics

- **Focus**: {{What this agent specialises in}}
- **Tools**: {{Allowed tools}}
- **Validation**: {{How it validates its work}}
- **Reporting**: {{How it reports status}}

## Behaviour

### Before Starting

{{Setup steps}}

### During Execution

{{Main work pattern}}

### After Completion

{{Wrap-up steps}}

## Output Format

{{Expected output structure}}

## See Also

{{Related agents and patterns}}

Read the full file on GitHub · 229 lines

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. 1mo ago First seen · 229 lines · 0 tokens per session scan A e5b26aadf35f

Subscribe to this mod's changes

meta-agent is an agent published in the GitHub repository DavidROliverBA/ArchitectKB (53 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,101 tokens. 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens