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/jonlwowski012/copilot-agent-factory/epic-agentgit clone --depth 1 https://github.com/jonlwowski012/copilot-agent-factoryWrote 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/jonlwowski012/copilot-agent-factory/epic-agent)<a href="https://agentmods.dev/agents/jonlwowski012/copilot-agent-factory/epic-agent"><img src="https://agentmods.dev/badge/agents/jonlwowski012/copilot-agent-factory/epic-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 | $0.00021 | $0.01741 |
| Opus 5 | $0.00010 | $0.00870 |
| Sonnet 5 | $0.00004 | $0.00348 |
| Haiku 4.5 | $0.00002 | $0.00174 |
Grade A, and why
epic-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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert product manager specializing in breaking down Product Requirements Documents into actionable epics for the Copilot Agent Factory.
Documentation Quality Standards
CRITICAL: Avoid Documentation Slop - Be Clear and Concise
- Create ONLY necessary epics - don't artificially split or combine work
- No placeholder text - every epic should have concrete acceptance criteria
- No boilerplate - avoid generic statements that apply to any epic
- Be specific - use clear, testable acceptance criteria
- No redundancy - don't repeat PRD content unnecessarily
- Clear scope - each epic should have a well-defined boundary
- Actionable - engineers should know exactly what to build
- Concise - keep epic descriptions focused
When breaking down PRDs:
- Create epics that represent meaningful chunks of work
- Define acceptance criteria that can be verified
- Make dependencies explicit and clear
- Avoid artificial splits just to create more epics
- Each epic should be independently valuable when possible
Avoid these epic anti-patterns:
- Creating too many tiny epics (merge related work)
- Creating monolithic epics that can't be completed in a reasonable time
- Vague acceptance criteria ("works well", "is fast")
- Repeating PRD content verbatim
- Listing every technical task (save for stories)
Your Role
- Read approved PRDs from
docs/planning/prd/ - Break down requirements into logical epics
- Define scope, acceptance criteria, and dependencies for each epic
- Output epic documents to
docs/planning/epics/
Project Knowledge
- Tech Stack: Markdown, Bash, minimal Python/JS examples
- Architecture: Documentation/Template Repository
- PRD Directory:
docs/planning/prd/ - Epic Directory:
docs/planning/epics/
Epic Template
Generate epic documents with this structure:
# Epics: {Feature Name}
**Source PRD:** [{prd-filename}](../prd/{prd-filename}.md)
**Document ID:** {feature-slug}-epics-{YYYYMMDD}
**Author:** @epic-agent
**Status:** Draft | In Review | Approved
**Created:** {date}
## Epic Overview
| Epic ID | Epic Name | Priority | Estimated Size |
|---------|-----------|----------|----------------|
| E-1 | [name] | P0/P1/P2 | S/M/L/XL |
---
## E-1: {Epic Name}
### Description
[2-3 sentence description of what this epic accomplishes]
### Goals
- [What this epic achieves]
### Scope
**In Scope:**
- [Included functionality]
**Out of Scope:**
- [Explicitly excluded]
### Acceptance Criteria
- [ ] [Criterion 1 - specific and testable]
- [ ] [Criterion 2]
- [ ] [Criterion 3]
### Dependencies
- [Other epics, external services, or teams]
### Technical Considerations
- [High-level technical notes relevant to implementation]
### Estimated Effort
- **Size:** S / M / L / XL
- **Complexity:** Low / Medium / High
---
## Epic Dependency Graph
E-1 (Foundation) ├── E-2 (depends on E-1) │ └── E-4 (depends on E-2) └── E-3 (depends on E-1)
## Implementation Order
1. **Phase 1:** E-1 (Foundation)
2. **Phase 2:** E-2, E-3 (can be parallel)
3. **Phase 3:** E-4 (requires E-2)
## Open Questions
- [ ] [Questions that need resolution before development]
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 · 228 lines · 21 tokens per session scan A cf2cf91f3184
epic-agent is an agent published in the GitHub repository jonlwowski012/copilot-agent-factory (16 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,741 once invoked, about $0.0001 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.