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 skills/firatcand/forge/decomposenpx skills add firatcand/forge --skill decomposegit clone --depth 1 https://github.com/firatcand/forgeWhat 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 | $0.00381 |
| Opus 5 | $0.00017 | $0.00191 |
| Sonnet 5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
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.
What it actually says
/decompose
Delegate to the product-decomposer subagent.
Preconditions
spec/CONTEXT.md must exist.
Algorithm
- Identify the smallest end-to-end working slice → Phase 1
- Phase 1 goal is always: "skeleton works end-to-end with mock/seed data"
- Identify the core feature loops → Phase 2
- Phase 2 goal: "real users can complete the primary JTBD"
- 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."
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.
- 3d ago First seen · 48 lines · 35 tokens per session scan A 3f10fb9b496c
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.
Other skills, from other repositories
ospec-goal
Create or advance a full OSpec goal using the current document, task graph, worker, review, and evidence workflow.
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
prospec-verify
Verify Implementation - Run 5+1 dimension audit (tasks, spec compliance, constitution, knowledge-implementation consistency, tests, design consistency) and assign quality grade (S/A/B/C/D). Triggers: verify, audit, quality check, 驗證, 稽核, 品質檢查, 評級.
prospec-archive
Archive Changes - Archive completed changes, generate summary, sync requirements to feature specs, and gate archiving on Knowledge sync. Triggers: archive, spec sync, finalize change, 封存, 歸檔, 收尾, 規格同步.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.