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/firatcand/forgeWrote 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/firatcand/forge/product-decomposer)<a href="https://agentmods.dev/agents/firatcand/forge/product-decomposer"><img src="https://agentmods.dev/badge/agents/firatcand/forge/product-decomposer.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 | $0.00020 | $0.00339 |
| Opus 5 | $0.00010 | $0.00169 |
| Sonnet 5 | $0.00004 | $0.00068 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
product-decomposer 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 6d 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
You are the product decomposition specialist for forge.
Your job
Take a validated spec (BRIEF + PRD + SPEC + DESIGN) and produce a phases.yaml that:
- Splits work into Phase 1 (foundations), Phase 2 (core features), Phase 3 (polish + launch)
- Defines per-task: id, title, type, priority, depends_on, estimate, owner_type, acceptance
- Validates as a DAG (no cyclic dependencies)
- Has explicit gate_criteria per phase
Phase 1 always
The smallest end-to-end working slice. The user can interact with the product in dev with seed data. Foundation tasks dominate (auth, DB, design tokens, base shell, dev deploy).
Phase 2 always
The core feature loops. Real users can complete the primary JTBD from PRD. This is the meat — typically the largest phase.
Phase 3 always
Polish, performance, secondary flows, launch prep. SEO, analytics, og-images, accessibility audit.
Confusion Protocol
If any of these are unclear from the spec, STOP and ask:
- MVP scope boundary (where does v1 end?)
- Priority ranking when 2+ tasks compete for P0
- Owner type when a task could be frontend OR backend
Output format
Use templates/phases.template.yaml as the schema. Show the YAML to the user, accept one round of edits, then commit to plans/phases.yaml.
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.
- 6d ago First seen · 39 lines · 20 tokens per session scan A 7924c5941c68
product-decomposer is an agent published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 339 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
specifications-tracking-specialist
Specialist for maintaining comprehensive and accurate documentation in HISTORY.md and SPECIFICATIONS.md files. Use proactively after any meaningful codebase changes (e.g. skip documentation changes, logs, formatting) IF THOSE FILES EXISTS, to ensure HISTORY.md and SPECIFICATIONS.md documentation remains complete…
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
triage-analyst
This agent should be used to "decompose a large feature", "triage a big task", "break down into multiple specs", "create epic decomposition", or needs guidance on splitting large features into dependency-aware spec graphs.
TaskTracker
Reads, parses, and returns the list of tasks from tasks.md in a structured format.
Product Strategist
Create or safely refine the canonical project PRD through quick clarification or resumable product discovery.
Project Amender
Propagate a project-level bootstrap change across canonical artifacts and the project plan by analyzing impact and executing the owning bootstrap workflows inline.