An RFC manager for creating, reviewing, listing, updating, and changing the status of architecture proposals. An RFC, or request for comments, is a written proposal used to discuss and record technical decisions.

Use it to manage RFC files across supported project directories, from first draft through review and status changes.

It gives design proposals a consistent place and process instead of leaving decisions scattered across messages and files.

rfc — Skill for Claude Code by joaquimscosta/arkhe-claude-plugins

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.

Any agent

npx skills add joaquimscosta/arkhe-claude-plugins --skill rfc

Clone the repo

git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/rfc/github.svg)](https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/rfc)

Your own site

<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/rfc"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joaquimscosta/arkhe-claude-plugins/rfc"><img src="https://agentmods.dev/badge/skills/joaquimscosta/arkhe-claude-plugins/rfc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,144 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00053	$0.02144
Opus 5.5	$0.00021	$0.00858
Sonnet 5.5	$0.00011	$0.00429
Haiku 4.5	$0.00005	$0.00214

Measured today against content hash 52235980cab3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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.

plugins/doc/skills/rfc/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RFC Manager

Manage architecture RFCs with 5 operations: create, review, list, update, status.

Argument Parsing

Parse $ARGUMENTS to determine the action:

First word	Remaining args	Operation
`create`	`<topic>`	Draft a new RFC
`review`	`<path-to-rfc>`	Review an existing RFC
`list`	(none)	List all RFCs
`update`	`<path-to-rfc>`	Update specific RFC sections
`status`	`<number> <status>`	Transition RFC status with validation and side effects
(empty)		Ask the user which action to perform

If the first word does not match any action, treat the entire $ARGUMENTS as a topic and default to create.

RFC Directory Discovery

Used by all operations. Search for RFC files across all convention paths (exclude *.spec.md companion files):

docs/rfcs/*.md
docs/20-architecture/rfcs/*.md (jd-docs — detected via .jd-config.json or docs/20-architecture/ directory)
.arkhe/rfcs/*.md (arkhe convention)
arkhe/rfcs/*.md

For create and update, resolve a write directory:

If jd-docs detected → docs/20-architecture/rfcs/
Else if docs/rfcs/ exists → docs/rfcs/
Else → create docs/rfcs/ as default

Operation: create

Draft a populated RFC — NOT a blank template. Gather context, write a spec, then write a real first draft with honest self-assessment.

Determine topic from args after create (or ask if empty)
Gather context — search conversation, research artifacts (docs/30-research/, docs/50-research/, docs/research/), memory files, relevant source code, and ADRs (docs/20-architecture/22-adr/, docs/20-architecture/adr/, docs/adr/). See WORKFLOW.md for detail.
Confirm scope with user before drafting — present what you found and proposed scope. Use AskUserQuestion for meaningful alternatives.
Resolve number and slug — discover write directory, glob all convention paths for highest existing number, assign next (zero-padded 4 digits). Confirm title with user, generate kebab-case slug. Both spec and RFC will use NNNN-<slug>.
Write spec file — read spec template at ${CLAUDE_SKILL_DIR}/templates/rfc-spec-template.md. Fill Problem Statement, Key Constraints, Success Criteria, and Scope Boundaries with concrete content. Write to <dir>/NNNN-<slug>.spec.md. Present to user for confirmation via AskUserQuestion. See WORKFLOW.md for spec guidance.
Read RFC template at ${CLAUDE_SKILL_DIR}/templates/rfc-template.md for section structure
Draft populated RFC filling every section with substantive content. See WORKFLOW.md for per-section guidance. Set Author to git user name, Status to Draft, Date to today.
Append Author's Notes — below Open Questions, record: shortcuts taken, unverified assumptions, areas of uncertainty, low-confidence sections. Aim for 3-8 items. Be specific — these feed the adversarial review. See WORKFLOW.md for confession guidelines.
Write RFC to <dir>/NNNN-<slug>.md
Suggest next steps: /rfc review <path> for adversarial design review (uses rfc-critic agent)

Read the full file on GitHub · 145 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

today First seen · 145 lines · 53 tokens per session scan A 52235980cab3

Subscribe to this mod's changes

rfc is a skill published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 2,144 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-16.

Planning Writing and docs ai-agents ai-developer-tools anthropic claude-code-agents claude-code-plugins

test-writer

Generate comprehensive tests including unit, integration, and property-based tests.

kivo360/OmoiOS · 12 tokens

git-workflow

Git branching, commits, and PR workflow following GitFlow conventions.

kivo360/OmoiOS · 12 tokens

pm

Universal, project-agnostic PRODUCT MANAGER playbook — the scope-disciplined PM that plans a project, gates its launch, and says no. Five modes, one workflow each: prd (turn a spec or a user request into a build-ready PRD — objectives, in-scope, out-of-scope guards, an acceptance-criteria table mapping every success…

endorphin-ai/hasbrains-agent-kit · 310 tokens

rfc