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.
npx agentmods add commands/vaiyav/speckit-product-forge/code-reviewgit clone --depth 1 https://github.com/VaiYav/speckit-product-forgeWrote 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/code-review)<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>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 | $0.00093 | $0.04878 |
| Opus 5 | $0.00046 | $0.02439 |
| Sonnet 5 | $0.00019 | $0.00976 |
| Haiku 4.5 | $0.00009 | $0.00488 |
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.
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
- Read
.product-forge/config.ymlfor project settings - Read
{FEATURE_DIR}/.forge-status.yml— verifyimplement: completed(Phase 6 done) - 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.
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.
- 5d ago First seen · 464 lines · 93 tokens per session scan A 7ef88e9938ac
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.