decompose

A planning workflow that turns an approved specification into phases.yaml, a file describing tasks, dependencies, owners, estimates, and acceptance checks.

In plain words
What is it for?
Use it to create Phase 1, 2, and 3 work plans, refine them with the user, and prepare the roadmap for tracker synchronization.
Why use it?
It breaks a large specification into ordered, testable pieces and checks that dependencies do not form a cycle.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/firatcand/forge/decompose
Any agent
npx skills add firatcand/forge --skill decompose
Clone the repo
git clone --depth 1 https://github.com/firatcand/forge

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00381
Opus 5 $0.00017 $0.00191
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 3d ago against content hash 3f10fb9b496c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decompose 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 3d 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.

skills/decompose/SKILL.md · 48 lines

What it actually says

/decompose

Delegate to the product-decomposer subagent.

Preconditions

spec/CONTEXT.md must exist.

Algorithm

  1. Identify the smallest end-to-end working slice → Phase 1
    • Phase 1 goal is always: "skeleton works end-to-end with mock/seed data"
  2. Identify the core feature loops → Phase 2
    • Phase 2 goal: "real users can complete the primary JTBD"
  3. Identify polish + launch prep → Phase 3
    • Phase 3 goal: "quality bar for public launch"

Per-task fields

  • id (P{phase}-T{nn})
  • title (verb + noun, max 8 words)
  • description (1 paragraph)
  • type (foundation | data | backend | integration | content | infra | skill | docs)
  • priority (P0 | P1 | P2)
  • depends_on (list of task IDs)
  • estimate (S | M | L | XL)
  • owner_type (which subagent picks this up — use 'human' for manual bootstrap work, never auto-dispatched)
  • acceptance (concrete, testable)

Hard rules

  • No XL tasks ship — split them
  • Every phase has explicit gate_criteria
  • Dependency graph must be a DAG (validator catches cycles)

Refinement

Show YAML to user, ask for one round of edits. Then write to plans/phases.yaml.

Print: "phases.yaml written. /push-to-tracker unlocked. Gate 4 — review the breakdown."

Changes

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.

  1. 3d ago First seen · 48 lines · 35 tokens per session scan A 3f10fb9b496c

Subscribe to this mod's changes

decompose is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 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 2026-08-30.