Borrowing it
Nothing to install: this file belongs to nurettincoban/ai-prd-workflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nurettincoban/ai-prd-workflow/main/.claude/commands/review-rfc.mdgit clone --depth 1 https://github.com/nurettincoban/ai-prd-workflowWrote 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/nurettincoban/ai-prd-workflow/review-rfc)<a href="https://agentmods.dev/commands/nurettincoban/ai-prd-workflow/review-rfc"><img src="https://agentmods.dev/badge/commands/nurettincoban/ai-prd-workflow/review-rfc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/nurettincoban/ai-prd-workflow/review-rfc"><img src="https://agentmods.dev/badge/commands/nurettincoban/ai-prd-workflow/review-rfc.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00010 | $0.01007 |
| Opus 5 | $0.00005 | $0.00504 |
| Sonnet 5 | $0.00002 | $0.00201 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
review-rfc scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Target RFC ID: "$ARGUMENTS" — substitute it for [ID] everywhere below. If no ID was given, ask which RFC to work on before doing anything else.
Run this in a fresh session, ideally with a different model than the one that wrote the code. The RFC, RULES.md and FEATURES.md contain everything needed -- that is the point of them. A reviewer holding the author's reasoning is not a reviewer.
You are an expert code reviewer tasked with reviewing an implementation against its RFC specification and project standards.
Review the implementation of the specified RFC and provide a thorough, actionable assessment. Your review should catch bugs, security issues, and deviations from the specification before the code is merged.
Inputs
- The RFC being reviewed (RFC-[ID].md)
- The implementation code
- RULES.md for project standards
- FEATURES.md for requirement traceability
WHEN ARTIFACTS CONFLICT
Order of authority: PRD.md > FEATURES.md > RULES.md > RFCs > generated plans. Where this prompt's generic guidance conflicts with RULES.md, RULES.md wins -- it was written for this project and this prompt was not. Never resolve a contradiction between two artifacts silently: state it, say which one you followed and why, and flag the other for correction.
STEP 0: RUN IT
Before assessing anything, run the project's build, typecheck, and test suite. Paste the actual output. Then verify each acceptance criterion has a test that would FAIL if the behavior regressed -- a passing suite is not evidence that the criteria are covered. Reading code cannot distinguish "this test asserts the right thing" from "this test passes."
If you cannot execute commands in this environment, say so explicitly and mark every verdict below as unverified rather than assessing by reading alone.
SCOPE THE CHECKLIST TO THE PRODUCT TYPE
First classify the product: web app · mobile app · library/SDK · CLI · service/API · data pipeline · game.
Apply only the sections and checks that fit that type. For a library/SDK, skip infrastructure, scalability, regulatory, business-model, accessibility, responsive-design, state-management, and auth concerns -- instead probe: public API surface and consistency, semver/deprecation policy, peer-dependency ranges, bundle size, tree-shaking, types quality, the public/internal boundary, and mutation of caller-owned data. Every other product type has its own equivalents; work them out before applying the generic list below.
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.
- 12d ago First seen · 85 lines · 10 tokens per session scan A 047f0d480817
review-rfc is a command published in the GitHub repository nurettincoban/ai-prd-workflow (285 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,007 once invoked, about $0.0001 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
code-review
Review code for bugs, improvements, and best practices with actionable feedback.
lfe-complexity-check
Inspector sub-skill. Analyses changed code for cyclomatic complexity, excessive nesting, oversized functions, and cognitive load indicators. Pure LLM reasoning — no external tooling. Writes .plans/checks/complexityfindings.md. Called by lfe-inspector when enabled in inspector-config.md.
lfe-hygiene
Conduct a structural audit of the repository to detect "Documentation Drift" or "Spaghetti Files." Use in Phase 5 (Hygiene sub-pipeline, Step 1).
lfe-improve-architecture
Find deepening opportunities in the codebase — turn shallow modules into deep ones. Use in Phase 5 (Hygiene sub-pipeline) or when scheduled by session count.
lfe-perf-check
Inspector sub-skill. Analyses the implementation diff for common performance anti-patterns — resource leaks, N+1 queries, unbounded growth, algorithmic complexity. Pure LLM reasoning, no profilers. Writes .plans/checks/perffindings.md. Called by lfe-inspector when enabled in inspector-config.md.
techdebt-file
Analyze a single source file for technical debt and print a line-numbered issue table of findings sorted by severity.