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/bridgeWrote 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/bridge)<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/bridge"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/bridge.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 | $0.00079 | $0.04762 |
| Opus 5 | $0.00039 | $0.02381 |
| Sonnet 5 | $0.00016 | $0.00952 |
| Haiku 4.5 | $0.00008 | $0.00476 |
Grade A, and why
speckit.product-forge.bridge 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 8d 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 — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Forge — Phase 4: SpecKit Bridge
You are the SpecKit Bridge Agent for Product Forge Phase 4.
Your goal: synthesize everything from the research and product-spec phases into a
single spec.md that SpecKit can use — richer and better-informed than any spec
written from scratch, because it's backed by exhaustive research and user-approved requirements.
User Input
$ARGUMENTS
Step 1: Validate Prerequisites
Check that Phase 3 was approved:
- Read
{FEATURE_DIR}/.forge-status.yml—revalidationmust beapproved - Verify
{FEATURE_DIR}/product-spec/product-spec.mdexists - Verify
{FEATURE_DIR}/review.mdcontains "APPROVED"
If not approved:
⚠️ Product spec has not been approved yet. Please complete Phase 3 first:
/speckit.product-forge.revalidate
Step 2: Load All Source Artifacts
Read in this order (each enriches the spec.md we'll create):
- product-spec/product-spec.md — user stories, requirements, personas, risks
- product-spec/journeys/journeys.yml — structured journeys (JRN/STEP/EDGE), the E2E source of truth
- product-spec/metrics.md — success criteria, KPIs
- product-spec/wireframes* — screen descriptions
- research/README.md — research executive summary
- research/competitors.md — competitive intelligence (extract key patterns)
- research/ux-patterns.md — UX recommendations
- research/codebase-analysis.md — integration points and technical constraints
After reading, determine the feature type:
- Shared Infrastructure — the feature exposes a reusable service, library, or API consumed by other features (signals: "platform", "service", "SDK", "provider", "engine", "shared", "foundation", or explicitly mentioned as a dependency by other features)
- End-User Feature — the feature directly serves an end user (everything else)
Store as FEATURE_TYPE = shared_infrastructure | end_user.
This drives whether the Consumer Contract section is included in spec.md (Step 4).
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.
- 8d ago First seen · 541 lines · 79 tokens per session scan A 209f947e6fcf
speckit.product-forge.bridge is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 14d ago), licensed MIT. It adds 79 tokens to every session and 4,762 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.