speckit.product-forge.code-review

speckit.product-forge.code-review is a command for coding agents from VaiYav/speckit-product-forge. It costs 93 tokens per session (4,878 once invoked), scanned A, original, MIT.

A structured review of implemented code using the product research, specification, and plan as context. It checks code organization, security risks, consistency with the existing codebase, and test coverage, with an optional review by another model.

In plain words
What is it for?
Use it after implementation and before verification to review quality, security, design consistency, and coverage. A dry-run option records findings without changing release gates or status.
Why use it?
It connects code-review findings to what the feature is meant to do instead of treating the code as an isolated change. It can also identify requirements that the tests do not cover.

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/code-review
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.code-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/code-review.svg)](https://agentmods.dev/commands/vaiyav/speckit-product-forge/code-review)
Your own site
<a href="https://agentmods.dev/commands/vaiyav/speckit-product-forge/code-review"><img src="https://agentmods.dev/badge/commands/vaiyav/speckit-product-forge/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,878 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00093 $0.04878
Opus 5 $0.00046 $0.02439
Sonnet 5 $0.00019 $0.00976
Haiku 4.5 $0.00009 $0.00488

Measured 5d ago against content hash 7ef88e9938ac, 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.code-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 5d 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/code-review.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Forge — Code Review (Phase 6B)

You are the Code Review Conductor for Product Forge. Your goal: perform a structured, multi-dimensional code review of the implementation, enriched with full product context from research, spec, and plan artifacts.

User Input

$ARGUMENTS

If $ARGUMENTS contains --cross-model (optionally --cross-model <reviewer-id>), run the cross-model review loop in Step 2.5 — export the consolidated review surface as a portable package, have a different model review it, and ingest the result back into the F-NNN namespace. See Step 2.5. Without the flag, code-review runs single-model as before.

If $ARGUMENTS contains --dry-run, honor docs/runtime.md §7: write code-review.md / gate-review.md additions and any cross-review package under {FEATURE_DIR}/.forge-dry-run/code_review/, record no gates[] entry or status change, emit a DRY-RUN-REPORT.md, and make no external side-effect.


Step 0: Load Context

  1. Read .product-forge/config.yml for project settings
  2. Read {FEATURE_DIR}/.forge-status.yml — verify implement: completed (Phase 6 done)
  3. If implement phase is not completed: STOP — "Phase 6 (Implementation) must be completed first."

Load artifacts:

  • {FEATURE_DIR}/tasks.md — extract completed tasks with file paths
  • {FEATURE_DIR}/spec.md — requirements and acceptance criteria
  • {FEATURE_DIR}/plan.md — architecture decisions and patterns
  • {FEATURE_DIR}/research/codebase-analysis.md — existing patterns and conventions
  • {FEATURE_DIR}/research/ux-patterns.md — UX recommendations (for frontend code)
  • {FEATURE_DIR}/pre-impl-review.md — conditions and risks (if exists)
  • {FEATURE_DIR}/implementation-log.md — progressive verify notes (if exists)

Interaction (normative): the review gate (Step 5) and any in-review question 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.

Read the full file on GitHub · 464 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. 5d ago First seen · 464 lines · 93 tokens per session scan A 7ef88e9938ac

Subscribe to this mod's changes

speckit.product-forge.code-review is a command published in the GitHub repository VaiYav/speckit-product-forge (23 stars, last pushed 11d ago), licensed MIT. It adds 93 tokens to every session and 4,878 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.