rfc

rfc is a skill for Claude Code, Codex from 0xrafasec/ai-workflow. It costs 84 tokens per session (814 once invoked), scanned A, original, MIT.

A Request for Comments document: a written proposal for a significant technical or process change that a team reviews before implementation. It is more detailed than an Architecture Decision Record but lighter than a full specification.

In plain words
What is it for?
It is for proposing new systems, major refactors, breaking changes, and process changes while recording motivation, scope, design, alternatives, and migration concerns.
Why use it?
It gives teammates a shared proposal to discuss before work begins, especially when the change could be large or disruptive.

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/0xrafasec/ai-workflow/rfc
Any agent
npx skills add 0xrafasec/ai-workflow --skill rfc
Clone the repo
git clone --depth 1 https://github.com/0xrafasec/ai-workflow

Made for: Claude Code, Codex.

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 rfc

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/rfc.svg)](https://agentmods.dev/skills/0xrafasec/ai-workflow/rfc)
Your own site
<a href="https://agentmods.dev/skills/0xrafasec/ai-workflow/rfc"><img src="https://agentmods.dev/badge/skills/0xrafasec/ai-workflow/rfc.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 814 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 5.1 $0.00084 $0.00814
Opus 5 $0.00042 $0.00407
Sonnet 5 $0.00017 $0.00163
Haiku 4.5 $0.00008 $0.00081

Measured 5d ago against content hash 82f73ef562b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 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.

skills/rfc/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a Request for Comments. Argument: $ARGUMENTS

Context

RFCs are for significant changes that need team input before implementation — new systems, major refactors, breaking changes, process changes. Heavier than an ADR, lighter than a full spec. The goal is to get feedback, not to be exhaustive.

Context Gathering

  1. Check docs/rfc/ for existing RFCs — determine the next number. If none exist, start at 0001.
  2. Read recent RFCs (last 2-3) to match the project's style.
  3. Read docs/ARCHITECTURE.md and docs/PRD.md if they exist — the RFC should reference existing design, not repeat it.

Interview

Use AskUserQuestion to understand the proposal deeply. Push back on vague motivation — "why now?" and "what happens if we don't do this?"

  1. Proposal — What are you proposing? What's the elevator pitch?
  2. Motivation — Why is this needed? What's broken, missing, or changing? What happens if we do nothing?
  3. Scope — What does this change? What does it NOT change? Where are the boundaries?
  4. Design — How would this work at a high level? What are the key technical decisions?
  5. Alternatives — What other approaches were considered? Why not those?
  6. Migration — If this changes existing behavior, how do we get from here to there? Is it backwards-compatible?
  7. Risks — What could go wrong? What are the unknowns? What needs prototyping?
  8. Open questions — What do you want feedback on specifically? What are you least sure about?

Write

Write to docs/rfc/NNNN-<slug>.md:

# RFC-NNNN: [Title]

**Status:** Draft | In Review | Accepted | Rejected | Withdrawn
**Author:** [who]
**Date:** [date]
**Review deadline:** [date, if applicable]

## Summary

[2-3 sentence elevator pitch. What is this and why should someone care?]

## Motivation

[Why is this needed? What problem does it solve? What happens if we don't do this?]

## Proposal

[Detailed description of the proposed change. Include diagrams (Mermaid) where they help. This should be concrete enough for someone to evaluate but not a full implementation spec.]

### Key Design Decisions

[Call out the important choices and why you made them.]

## Alternatives Considered

### [Alternative 1]
[Description, why it was rejected]

### [Alternative 2]
[Description, why it was rejected]

## Migration Plan

[If this changes existing behavior: how do we transition? Is it backwards-compatible? What's the rollback plan?]

[If greenfield: skip this section]

## Risks and Open Questions

| Item | Type | Status |
|------|------|--------|
| [concern] | Risk / Question | Open / Resolved: [answer] |

## Feedback Requested

[What specifically do you want reviewers to focus on? What are you least sure about?]

## References

- [Links to related docs, prior art, external resources]

Read the full file on GitHub · 91 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 · 91 lines · 84 tokens per session scan A 82f73ef562b6

Subscribe to this mod's changes

rfc is a skill published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 814 once invoked, about $0.0004 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 2026-08-31.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens