Borrowing it
Nothing to install: this file belongs to 1cFE/fusion-tea. 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/1cFE/fusion-tea/main/.agents/skills/epic-decomposition/SKILL.mdgit clone --depth 1 https://github.com/1cFE/fusion-teaWrote 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/skills/1cfe/fusion-tea/epic-decomposition)<a href="https://agentmods.dev/skills/1cfe/fusion-tea/epic-decomposition"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/epic-decomposition/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/skills/1cfe/fusion-tea/epic-decomposition"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/epic-decomposition.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 | $0.00095 | $0.01478 |
| Opus 5.5 | $0.00038 | $0.00591 |
| Sonnet 5.5 | $0.00019 | $0.00296 |
| Haiku 4.5 | $0.00010 | $0.00148 |
Grade A, and why
epic-decomposition 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 24d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before executing this skill, read .agentic-mbse/claude.md in Claude Code or .agentic-mbse/codex.md in Codex. Resolve supporting paths from this skill’s installed directory; keep generated outputs in the project or a temporary directory. Read referenced skills from .agents/skills/<name>/SKILL.md when their guidance is needed.
Epic Decomposition
Scale taxonomy, work item sizing, and decomposition process for modeling work.
Core Principle
Decompose by domain concern, not by workflow phase or validation level. Each work item should model one domain subsystem end-to-end, be independently validatable, and produce clear deliverables. The overhead of the workflow (spec/design/plan/implement) must be proportionate to the work.
When to Reference
/backlog— when adding work items or decomposing epics/spec-model— when scoping a work item (is this the right size?)/onboard— when planning initial project work
Scale Taxonomy
| Scale | Behavior | Entry Point | Tracking |
|---|---|---|---|
| Trivial | Direct change + validate. No spec/design/plan. | /quick-model |
No work item directory. Not tracked in PM. |
| Standard | Full pipeline: spec → design → plan → implement. Agent adjusts depth naturally. | /spec-model |
work/active/WI-XXX_{name}/ directory |
| Epic | Must decompose into standard sub-items before execution. | /backlog decompose |
Epic file in work/backlog/epic-{name}.md |
Routing: The system infers scale from scope description and confirms with the user. Power users can state scale directly.
Examples:
- Trivial: Fix a naming convention violation; update a constant from a source revision
- Standard: Model a costing subsystem; integrate power balance with a plant subsystem
- Epic: End-to-end costing pipeline across all subsystems; full system model with multiple configurations
Goldilocks Indicators
Too Large (needs decomposition into epic)
- Spans multiple domain subsystems that could be modeled independently
- Depends on 4+ authority sources
- Would produce 25+ new definitions (part defs, calc defs, constraint defs)
- Success criteria mix structural, validation, and codegen concerns
- Cannot describe scope without referencing multiple architectural decisions (AD-XXX)
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.
- 24d ago Changed · +2 lines 13d91142807f
- 1mo ago First seen · 130 lines · 95 tokens per session scan A 7e1a2a2adff9
epic-decomposition is a skill published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 95 tokens to every session and 1,478 once invoked, about $0.0004 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 2026-09-29.
epic-decomposition compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| epic-decomposition1cFE/fusion-tea | Skill | 5 | 24d ago | MIT | A | 95 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |