speckit.product-forge.implement

speckit.product-forge.implement is a command for coding agents from VaiYav/speckit-product-forge. It costs 87 tokens per session (4,596 once invoked), scanned A, original, MIT.

A coordinator that carries out coding tasks from tasks.md and checks progress during implementation. It keeps the implementation connected to the product specification and can optionally run independent task groups in parallel.

In plain words
What is it for?
Use it to execute a prepared task list, monitor completion, run progressive checks, and report when implementation is finished.
Why use it?
It reduces manual tracking during a large feature build and catches problems at checkpoints instead of only at the end. A dry run records intended changes without editing the real project or committing code.

Command

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

Install

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.

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

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.implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/implement.svg)](https://agentmods.dev/commands/vaiyav/speckit-product-forge/implement)
Your own site
<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/implement"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00087 $0.04596
Opus 5 $0.00044 $0.02298
Sonnet 5 $0.00017 $0.00919
Haiku 4.5 $0.00009 $0.00460

Measured 4d ago against content hash 670594619135, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.product-forge.implement scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL "https://api.npmjs.org/downloads/point/last-month/<pkg>" | \
commands/implement.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Forge — Phase 6: Implementation (with Progressive Verification)

You are the Implementation Coordinator for Product Forge Phase 6. Your job: drive implementation to completion from tasks.md, keep implementation agents anchored to the product spec, run progressive verification checkpoints, and report when all tasks are done.

This is a standalone command — it does one thing and exits. The next step is /speckit.product-forge.code-review (Phase 6B) or /speckit.product-forge.verify-full (Phase 7).

User Input

$ARGUMENTS

If $ARGUMENTS contains --parallel, attempt intra-phase task-group parallelism in Step 3 (Hermes delegate_task), strictly bounded by the path-disjointness proof and the carve-out in docs/policy.md §1.1. Without the flag, implementation runs sequentially as before.

If $ARGUMENTS contains --dry-run, honor the dry-run contract in docs/runtime.md §7: redirect every write (implementation edits, task_log[], status, digest) under {FEATURE_DIR}/.forge-dry-run/implement/ instead of the real paths, make no external side-effect (no commit), write a DRY-RUN-REPORT.md of what would change, and do not update .forge-status.yml. If the build truly cannot separate compute from write, abort per §7.3 rather than writing for real.


Step 1: Validate Prerequisites

  1. Read .forge-status.ymltasks must be completed
  2. Verify tasks.md exists with at least one unchecked task [ ]
  3. Verify plan.md and spec.md exist

If all tasks are already [x]:

✅ All tasks in tasks.md are already completed. Run /speckit.product-forge.verify-full for full traceability verification.


Step 2: Implementation Brief

Show the user a summary before starting:

🔨 Implementation Brief: {Feature Name}

tasks.md:         {FEATURE_DIR}/tasks.md
plan.md:          {FEATURE_DIR}/plan.md
spec.md:          {FEATURE_DIR}/spec.md
Product spec:     {FEATURE_DIR}/product-spec/

Tasks to complete: {N} remaining / {N} total
Task groups: {N}
  • {group 1}: {N} tasks
  • {group 2}: {N} tasks
  ...

Key context for implementation agents:
  • Mockups + component map: {FEATURE_DIR}/product-spec/mockups/ (+ component-map.yml)
  • Design system manifest:  {FEATURE_DIR}/design-system/manifest.yml (use real CMP-* components)
  • Structured journeys:     {FEATURE_DIR}/product-spec/journeys/journeys.yml
  • Acceptance criteria in spec.md — reference these for each task group
  • Live matrix:             {FEATURE_DIR}/traceability.yml (fill code paths as you go)

Read the full file on GitHub · 382 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. 4d ago First seen · 382 lines · 87 tokens per session scan A 670594619135

Subscribe to this mod's changes

speckit.product-forge.implement is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 10d ago), licensed MIT. It adds 87 tokens to every session and 4,596 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.