verify-rfc

A review process that compares an RFC or design document with the code that was actually built. An RFC is a written proposal describing how a software change should work.

In plain words
What is it for?
Use it to check whether a feature matches its specification, find implementation gaps, and document discrepancies with evidence from the code.
Why use it?
It reveals requirements that were missed, behavior that differs from the proposal, and code changes that the document does not describe.

Skill for Claude CodeCodex

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 skills/gleanwork/cursor-plugins/verify-rfc
Any agent
npx skills add gleanwork/cursor-plugins --skill verify-rfc
Clone the repo
git clone --depth 1 https://github.com/gleanwork/cursor-plugins

Made for: Claude Code, Codex.

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00083 $0.01504
Opus 5 $0.00042 $0.00752
Sonnet 5 $0.00017 $0.00301
Haiku 4.5 $0.00008 $0.00150

Measured 2d ago against content hash ba5afb6d4c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-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 2d 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.

Origin

This is a copy

100% identical to verify-rfc — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

glean/skills/verify-rfc/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RFC Verification

You are verifying a design document (RFC, spec, design doc) against the actual implementation. Identify completeness, gaps, and discrepancies.

Input

Determine the RFC, design doc URL, or topic from the user's request. If it is not clear, ask: "Which RFC or design doc would you like to verify? You can give me a URL, a document title, or a topic to search for."


Core Principles

  • Thorough but efficient: Don't over-analyze trivial items
  • Quote evidence: Show specific code when claiming implementation exists
  • Be skeptical: Just finding related code doesn't mean the requirement is met
  • Honesty over completeness: Better to say "couldn't verify" than claim incorrectly

Phase 1: Fetch the Design Document

Goal: Get the full RFC content

Actions:

  1. Get the document:

    • If given a URL: read_document "[URL]"
    • If given a topic: search "[topic] RFC OR design doc" then read_document on the best match
  2. Extract verifiable requirements:

    • Functional requirements
    • Technical specifications
    • Integration points
    • Non-functional requirements (performance, security)
  3. Create a checklist of requirements to verify


Phase 2: Search the Codebase

Goal: Find implementations for each requirement

Actions:

  1. For each major requirement area, search the local codebase using your host's local file-search tools (grep/glob/read) to find relevant files by name patterns, locate specific implementations, and examine implementation details.

  2. Also search Glean for related internal code:

    code_search "[requirement] implementation"
    
  3. Document what you find for each requirement


Phase 3: Vet Each Finding (CRITICAL)

Goal: Rigorously verify claims — BE SKEPTICAL

For each requirement × implementation pair, evaluate:

Match Quality Test

  • Does the code actually implement this requirement?
  • ✅ IMPLEMENTED: Clear, direct implementation with evidence
  • ⚠️ PARTIAL: Some aspects present, others missing
  • ❓ UNCLEAR: Code exists but doesn't clearly fulfill requirement
  • ❌ NOT FOUND: No evidence of implementation

Read the full file on GitHub · 221 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. 2d ago First seen · 221 lines · 83 tokens per session scan A ba5afb6d4c4e

Subscribe to this mod's changes

verify-rfc is a skill published in the GitHub repository gleanwork/cursor-plugins (4 stars, last pushed 12d ago), licensed MIT. It adds 83 tokens to every session and 1,504 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to verify-rfc, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens