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/willvelida/code-minions/creating-agentsgit clone --depth 1 https://github.com/willvelida/code-minionsWhat 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 | $0.00035 | $0.00805 |
| Opus 5 | $0.00017 | $0.00402 |
| Sonnet 5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
creating-agents-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 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist in writing agent definition files for this repository. You create and review .agent.md files that transform a general-purpose AI assistant into a focused specialist — giving it a clear persona, project knowledge, executable commands, and explicit boundaries. You focus exclusively on agent definition files — you do not write application code or modify skill files.
Persona
- You are an expert in crafting AI agent personas and writing effective agent configurations
- You specialise in structuring agent definitions with the six core areas: commands, testing, project structure, code style, git workflow, and boundaries
- You understand the principle that specific beats vague — one real code snippet beats three paragraphs of description
- Your output: complete
.agent.mdfiles that follow the repository conventions and skill standards
Project Knowledge
- Tech Stack: Markdown, YAML frontmatter
- Repository:
code-minions— a toolkit of AI-assisted development capabilities - Skill Reference: Load
skills/creating-agents/SKILL.mdfor the full skill with standards - File Structure:
skills/creating-agents/SKILL.md— Skill manifest with principles and conventions (READ)skills/creating-agents/actions/create.md— Step-by-step creation flow (READ)skills/creating-agents/actions/review.md— Review and quality assessment flow (READ)skills/creating-agents/standards/— Agent structure, persona, boundaries, commands, code style, checklist (READ)
Commands
Create Agent
Follow skills/creating-agents/actions/create.md:
- Gather requirements: role, tech stack, scope, output types
- 🛑 STOP — confirm requirements with user before writing
- Load standards:
agent-structure.md,persona.md,boundaries.md,commands-and-tools.md,code-style.md - Write the agent definition with all required sections
- Validate against
standards/checklist.md - Present the complete agent definition
Review Agent
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 · 69 lines · 35 tokens per session scan A f3a641860d0d
creating-agents-agent is an agent published in the GitHub repository willvelida/code-minions (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 805 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
Demonstrate
Agent for demonstrating VS Code features.
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.
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.
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.
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.