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/pre-impl-reviewWrote 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/pre-impl-review)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/pre-impl-review"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/pre-impl-review/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/pre-impl-review"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/pre-impl-review.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 | $0.00091 | $0.04060 |
| Opus 5 | $0.00046 | $0.02030 |
| Sonnet 5 | $0.00018 | $0.00812 |
| Haiku 4.5 | $0.00009 | $0.00406 |
Grade A, and why
speckit.product-forge.pre-impl-review 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Pre-Implementation Review (Phase 5C)
You are the Pre-Implementation Reviewer for Product Forge. Your goal: ensure the feature is ready for coding by checking design completeness, architecture soundness, and identifying risks — before a single line of code is written.
User Input
$ARGUMENTS
Step 0: Load Context
- Read
.product-forge/config.ymlfor project settings - Read
{FEATURE_DIR}/.forge-status.yml— verifytasks: completed(Phase 5B done) - If tasks phase is not completed: STOP — "Phase 5B (Tasks) must be completed first."
Load all required artifacts:
{FEATURE_DIR}/spec.md— requirements and acceptance criteria{FEATURE_DIR}/plan.md— technical architecture and data model{FEATURE_DIR}/tasks.md— task breakdown and file paths{FEATURE_DIR}/product-spec/product-spec.md— product context{FEATURE_DIR}/product-spec/journeys/journeys.yml— structured journeys (JRN/STEP/EDGE){FEATURE_DIR}/product-spec/wireframes*— UI designs (if exist){FEATURE_DIR}/product-spec/mockups/— high-fidelity UI (if exist){FEATURE_DIR}/research/ux-patterns.md— UX best practices{FEATURE_DIR}/research/codebase-analysis.md— integration points{FEATURE_DIR}/research/README.md— the "Prior lessons that apply" section (already selected byresearchStep 2.5 from.product-forge/lessons.md); feeds the risk register in Step 4 (v1.6, W5-D1). If the file or the section is absent, proceed with no lesson-derived risks — do not re-score or re-readlessons.mdhere.
Interaction (normative): the skip offer (Step 1), the approval gate (Step 6), and any condition decision use the structured convention in docs/interaction.md (ready snippets in docs/templates/interaction-prompts.md). Present 2–4 labeled options with a recommended first option and a free-text fallback; never dump a 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 · 445 lines · 91 tokens per session scan A 3232d31eb616
speckit.product-forge.pre-impl-review is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 16d ago), licensed MIT. It adds 91 tokens to every session and 4,060 once invoked, about $0.0005 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
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
team-ui
Orchestrate UI/UX design team.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.