speckit.product-forge.bridge

speckit.product-forge.bridge is a command for Claude Code from VaiYav/speckit-product-forge. It costs 79 tokens per session (4,762 once invoked), scanned A, original, MIT.

A bridge between Product Forge planning documents and SpecKit, a workflow for turning product requirements into coding tasks. It combines approved requirements, user journeys, measures of success, screen descriptions, and research into a SpecKit-ready spec.md file.

In plain words
What is it for?
Use it to create a detailed spec.md and start either the usual plan-to-tasks-to-implementation workflow or the V-Model workflow, which tests requirements throughout development.
Why use it?
It prevents developers from rewriting a short specification without the product context already gathered and approved. It also checks that the required approval steps are complete before continuing.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is > - Product Spec: [product-spec/README.md](./product-spec/README.md).

Part of the speckit-product-forge plugin — 31 commands shipped together

Good fit Use it to create a detailed spec.md and start either the usual plan-to-tasks-to-implementation workflow or the V-Model workflow, which tests requirements throughout development.

Compare 6 commands from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/VaiYav/speckit-product-forge
agentmods
npx agentmods add commands/vaiyav/speckit-product-forge/bridge

Made for: Claude Code.

Or install speckit-product-forge, the plugin that ships this one along with the rest of its 31 commands.

Wrote 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.

agentmods badge for speckit.product-forge.bridge

README.md
[![agentmods](https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/bridge.svg)](https://agentmods.dev/commands/vaiyav/speckit-product-forge/bridge)
Your own site
<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>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,762 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash 209f947e6fcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

commands/bridge.md · 541 lines

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:

  1. Read {FEATURE_DIR}/.forge-status.ymlrevalidation must be approved
  2. Verify {FEATURE_DIR}/product-spec/product-spec.md exists
  3. Verify {FEATURE_DIR}/review.md contains "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):

  1. product-spec/product-spec.md — user stories, requirements, personas, risks
  2. product-spec/journeys/journeys.yml — structured journeys (JRN/STEP/EDGE), the E2E source of truth
  3. product-spec/metrics.md — success criteria, KPIs
  4. product-spec/wireframes* — screen descriptions
  5. research/README.md — research executive summary
  6. research/competitors.md — competitive intelligence (extract key patterns)
  7. research/ux-patterns.md — UX recommendations
  8. 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).

Read the full file on GitHub · 541 lines

Changes

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.

  1. 8d ago First seen · 541 lines · 79 tokens per session scan A 209f947e6fcf

Subscribe to this mod's changes

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.