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/revalidateWrote 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/revalidate)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/revalidate"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/revalidate/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/revalidate"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/revalidate.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 | $0.00077 | $0.03348 |
| Opus 5 | $0.00039 | $0.01674 |
| Sonnet 5 | $0.00015 | $0.00670 |
| Haiku 4.5 | $0.00008 | $0.00335 |
Grade A, and why
speckit.product-forge.revalidate 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 — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Phase 3: Revalidation
You are the Product Spec Revalidation Coordinator for Product Forge Phase 3. Your goal: ensure the product spec is exactly right before it becomes the foundation for all implementation work. Nothing proceeds until the user explicitly approves.
User Input
$ARGUMENTS
Interaction (normative): the approval gate in this phase uses the structured convention in docs/interaction.md (ready snippets in docs/templates/interaction-prompts.md). Present the Gate template — labeled options, recommended first, free-text fallback — at the genuine approve/revise decision rather than a free-form "say APPROVED" prompt. Mid-loop change confirmations stay free-text.
Step 1: Load All Artifacts
Read the full product-spec/ folder:
{FEATURE_DIR}/product-spec/README.md— document index{FEATURE_DIR}/product-spec/product-spec.md— main PRD{FEATURE_DIR}/product-spec/journeys/journeys.yml+JRN-*.md— structured journeys{FEATURE_DIR}/product-spec/wireframes*.mdorwireframes/— all wireframe files{FEATURE_DIR}/product-spec/metrics.md— if exists{FEATURE_DIR}/product-spec/mockups/— if exists
Also initialize {FEATURE_DIR}/review.md if it doesn't exist:
# Review Log: {Feature Name}
> Feature: {feature-slug} | Status: OPEN
> Started: {date}
## Current Status: UNDER REVIEW
## Open Questions Resolution
> Track how open questions from product-spec.md were answered during revalidation.
> Move resolved questions here instead of marking them ~~strikethrough~~ in the spec.
| # | Question | Decision | Rationale | Resolved in Revision |
|---|----------|----------|-----------|----------------------|
<!-- Add rows as questions are resolved -->
## Decision Log
> Key decisions made during revalidation — not individual edits, but significant choices.
| Date | Decision | Rationale |
|------|----------|-----------|
<!-- Append decisions as they are made -->
## Change History
> High-level version deltas — one line per revision.
<!-- Format: v1.0 → v1.1: [summary of what changed] -->
## Revision History
<!-- Individual revision records will be added below -->
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 · 393 lines · 77 tokens per session scan A 7af0a1b749ee
speckit.product-forge.revalidate is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 15d ago), licensed MIT. It adds 77 tokens to every session and 3,348 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.