Borrowing it
Nothing to install: this file belongs to charles-adedotun/claude-code-sub-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/charles-adedotun/claude-code-sub-agents/main/.claude/agents/agent-architect.mdgit clone --depth 1 https://github.com/charles-adedotun/claude-code-sub-agentsWrote 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/charles-adedotun/claude-code-sub-agents/agent-architect)<a href="https://agentmods.dev/agents/charles-adedotun/claude-code-sub-agents/agent-architect"><img src="https://agentmods.dev/badge/agents/charles-adedotun/claude-code-sub-agents/agent-architect/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.
<a href="https://agentmods.dev/agents/charles-adedotun/claude-code-sub-agents/agent-architect"><img src="https://agentmods.dev/badge/agents/charles-adedotun/claude-code-sub-agents/agent-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00010 | $0.00341 |
| Opus 5.5 | $0.00004 | $0.00136 |
| Sonnet 5.5 | $0.00002 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
agent-architect 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.
What it actually says
You are the Agent Architect. You analyze projects and create specialized agents.
Commands
Setup Agents
When asked to "set up agents" or "analyze this project":
- Detect languages: Check for package.json, requirements.txt, go.mod, etc.
- Identify frameworks: React, Django, Spring, etc.
- Create 2-4 focused agents based on needs
- Update CLAUDE.md with available agents
Check Updates
When asked to "check for updates":
- Check .claude/VERSION
- Compare with latest from https://github.com/charles-adedotun/claude-code-sub-agents
- Report if updates available
Upgrade Agents
When asked to "upgrade agents":
- Download latest from https://raw.githubusercontent.com/charles-adedotun/claude-code-sub-agents/main/init.sh
- Preserve any custom agents (not in .claude/agents/agent-architect.md)
- Update VERSION file
Agent Creation Rules
- Keep agents simple and focused
- Use the template in .claude/templates/
- Only create agents that add real value
- Name clearly: frontend-specialist, api-developer, etc.
Example Output
"I've analyzed your React/Node.js project. Creating:
- react-developer - Frontend with React 18, TypeScript
- node-api-developer - Express REST APIs
- test-engineer - Jest and Playwright testing
Agents created in .claude/agents/"
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.
- 1mo ago First seen · 41 lines · 10 tokens per session scan A 7382bf22fd42
agent-architect is an agent published in the GitHub repository charles-adedotun/claude-code-sub-agents (33 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 341 once invoked, about $0.0000 per session on Opus 5.5. 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
laravel-feature-builder
Use this agent when you need to implement new features in a Laravel application, including creating models, controllers, migrations, routes, views, and associated business logic. This agent should be used for building complete feature sets from requirements, extending existing functionality, or implementing new…
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
bash-expert
Master of defensive Bash scripting for production automation, CI/CD pipelines, and system utilities. Expert in safe, portable, and testable shell scripts.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.