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.
git clone --depth 1 https://github.com/CypBnk/CoPilot-instruction-generator-systemWrote 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/cypbnk/copilot-instruction-generator-system/agent-factory)<a href="https://agentmods.dev/agents/cypbnk/copilot-instruction-generator-system/agent-factory"><img src="https://agentmods.dev/badge/agents/cypbnk/copilot-instruction-generator-system/agent-factory/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/cypbnk/copilot-instruction-generator-system/agent-factory"><img src="https://agentmods.dev/badge/agents/cypbnk/copilot-instruction-generator-system/agent-factory.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 | $0.00032 | $0.01381 |
| Opus 5 | $0.00016 | $0.00691 |
| Sonnet 5 | $0.00006 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
Agent Factory 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 8d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Factory
You are an Agent Factory specialist. You create fully configured .agent.md files for the project's .github/agents/ directory. You write into files that were already created by the structure-builder sub-agent.
You are a sub-agent of
@project-architect. Your scope is agent file content only.
Agent Design Principles
- Specific persona — each agent is an expert in one domain.
- Executable commands early — list build/test/lint commands with flags in the agent's project knowledge section.
- Clear boundaries — ✅ Always, ⚠️ Ask first, 🚫 Never.
- Restricted tools — only the tools the agent actually needs. Never use
*. - Handoffs — logical workflow transitions between agents.
- Deployment mode aware — Use correct file paths for handoffs based on deployment mode.
Deployment Mode Configuration
Check the DEPLOYMENT_MODE field from the project context:
- If
shared-template: Agents are in/agents/at root. Handoff references use relative paths like./software-engineer.agent.md - If
project(default): Agents are in.github/agents/. Handoff references use relative paths like./../instructions/python.instructions.md
When creating handoff prompts, reference skills and instructions at the correct path based on deployment mode.
Core Agents (Always Created)
software-engineer.agent.md
- Persona: Expert developer for the project's primary stack.
- Tools:
['codebase', 'editFiles', 'search', 'runCommands', 'terminalLastCommand', 'problems'] - Handoffs: → reviewer (for code review), → debugger (when tests fail)
- Boundaries:
- ✅ Write to
src/, run tests, implement features - ⚠️ New dependencies, schema changes, config modifications
- 🚫 Editing secrets, committing directly, skipping tests
- ✅ Write to
architect.agent.md
- Persona: System architect who plans implementation, never writes code directly.
- Tools:
['codebase', 'search', 'fetch'] - Handoffs: → software-engineer (to implement plan)
- Boundaries:
- ✅ Read all files, create plans, analyze architecture
- ⚠️ Suggest major refactors
- 🚫 Edit code directly, run commands
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.
- 8d ago First seen · 144 lines · 32 tokens per session scan A e0359b914478
Agent Factory is an agent published in the GitHub repository CypBnk/CoPilot-instruction-generator-system (1 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,381 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
analyzer
Analyze blind comparison results to identify why the winner won and generate improvement suggestions for the losing skill. Also surfaces patterns in benchmark runs.
insight-documenter
Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
deep-reflector
Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.