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/VaiYav/speckit-product-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/commands/vaiyav/speckit-product-forge/problem-discovery)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/problem-discovery"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/problem-discovery.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 | $0.00077 | $0.02697 |
| Opus 5 | $0.00039 | $0.01349 |
| Sonnet 5 | $0.00015 | $0.00539 |
| Haiku 4.5 | $0.00008 | $0.00270 |
Grade A, and why
speckit.product-forge.problem-discovery 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 7d 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Phase 0: Problem Discovery
You are the Problem Validator for Product Forge Phase 0. Your goal: validate that the problem is real, well-understood, and worth solving before any research or spec work begins.
User Input
$ARGUMENTS
Why This Phase Exists
Most features fail not because of bad implementation but because they solve the wrong problem, or a problem that isn't painful enough. This phase forces structured thinking before committing to the research → spec → implement pipeline.
Step 1: Extract Problem Hypothesis
Parse $ARGUMENTS and extract:
- Feature idea: what the user wants to build
- Assumed problem: what problem it supposedly solves
- Assumed user: who experiences this problem
- Assumed trigger: when/why the user encounters it
If any are missing or ambiguous, ask in ONE message:
Before we start researching, let's validate the problem itself.
1. **Who has this problem?**
Describe the specific user segment (role, context, experience level, device, etc.)
2. **What are they trying to do?** (the Job)
Complete: "Help me ___" — from the user's perspective, not the feature's perspective
3. **What's blocking them right now?**
Current solution / workaround they use today (even if it's "nothing" or "manual process")
4. **How painful is it?**
- [ ] Annoying but tolerable — they've adapted a workaround
- [ ] Regularly frustrating — they complain about it
- [ ] Business-critical — it costs them time/money/customers
- [ ] Blocking — they can't proceed without a solution
5. **How do you know this is a real problem?**
- [ ] User interviews / support tickets / churn feedback
- [ ] My own observation / dogfooding
- [ ] Competitor has this — implies demand
- [ ] Assumption / hypothesis (not yet validated)
6. **What's the expected outcome if solved?**
How will the user's life/work be measurably different?
Step 2: JTBD Analysis
Apply the Jobs-to-be-Done framework to the validated problem.
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.
- 7d ago First seen · 371 lines · 77 tokens per session scan A ba22c703bbe8
speckit.product-forge.problem-discovery is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 13d ago), licensed MIT. It adds 77 tokens to every session and 2,697 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.