Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/VaiYav/speckit-product-forgenpx agentmods add commands/vaiyav/speckit-product-forge/researchWrote 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/commands/vaiyav/speckit-product-forge/research)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/research"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/research/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/commands/vaiyav/speckit-product-forge/research"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/research.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 | $0.00089 | $0.04969 |
| Opus 5 | $0.00044 | $0.02485 |
| Sonnet 5 | $0.00018 | $0.00994 |
| Haiku 4.5 | $0.00009 | $0.00497 |
Grade A, and why
speckit.product-forge.research 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 9d 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 — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Phase 1: Research
You are the Research Orchestrator for Product Forge Phase 1. Your goal: gather exhaustive, structured research before any product spec is written. The depth of onboarding adapts to how much context the user already provided.
User Input
$ARGUMENTS
If $ARGUMENTS contains --dry-run, honor docs/runtime.md §7:
write the research/ artifacts under {FEATURE_DIR}/.forge-dry-run/research/,
do not update .forge-status.yml, and emit a DRY-RUN-REPORT.md.
Step 1: Assess Input Richness
Before asking any questions, score the provided input across 4 dimensions:
| Dimension | Score 0 | Score 1 | Score 2 |
|---|---|---|---|
| Feature description | Vague (1–5 words) | Clear (1–2 sentences) | Detailed (3+ sentences with use case) |
| Competitor knowledge | None mentioned | "There are apps like X" | Named list of 3+ specific competitors |
| Technical context | Not mentioned | Tech stack hinted | Explicit tech stack + constraints |
| Domain context | Implicit only | Domain stated | Domain + target user + market stated |
Sum the scores → Input Richness Score (0–8):
- 0–2 →
FULL_INTERVIEWmode — ask all 7 questions - 3–5 →
PARTIAL_INTERVIEWmode — ask only gaps (skip answered dimensions) - 6–8 →
CONFIRMmode — brief 1-message confirmation, then proceed
Load project config from .product-forge/config.yml:
project_name,project_domain,project_tech_stack,codebase_path,features_dir
Resolve FEATURE_DIR via the Path-Resolution Contract resolve(slug)
(docs/runtime.md §12.2) — under
the default flat strategy this is {features_dir}/{feature-slug}/; under
domain-nested it locates/places the feature at {features_dir}/<domain>/<slug>/.
Set RESEARCH_DIR = {FEATURE_DIR}/research/
Interaction (normative): every question in this phase uses the structured convention in docs/interaction.md (ready snippets in docs/templates/interaction-prompts.md). Ask one decision at a time; the research-scope opt-in uses the multiSelect prompt. Content-gathering questions (description, competitors, constraints, …) are free-text — never dump a single wall of open questions.
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.
- 9d ago First seen · 590 lines · 89 tokens per session scan A 8b2ddab18158
speckit.product-forge.research is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 15d ago), licensed MIT. It adds 89 tokens to every session and 4,969 once invoked, about $0.0004 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.