rfc

rfc is a command for Claude Code from avelikiy/great_cto. It costs 24 tokens per session (2,629 once invoked), scanned A, original, MIT.

A structured process for making and recording technical decisions across teams. It creates, tracks, and closes Requests for Comments (RFCs), then creates Architecture Decision Records (ADRs) for accepted decisions.

In plain words
What is it for?
Use it to propose a cross-team technical change, follow its review status, and turn an accepted proposal into a lasting architecture record.
Why use it?
It gives larger teams a shared way to discuss decisions and keeps the reasoning available after the discussion ends.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; positional $N argument.

Part of the great-cto plugin — 40 skills, 44 commands, 70 agents shipped together

Good fit Use it to propose a cross-team technical change, follow its review status, and turn an accepted proposal into a lasting architecture record.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/avelikiy/great_cto/rfc
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.

Clone the repo
git clone --depth 1 https://github.com/avelikiy/great_cto

Made for: Claude Code.

Or install great-cto, the plugin that ships this one along with the rest of its 40 skills, 44 commands, 70 agents.

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/commands/avelikiy/great_cto/rfc.svg)](https://agentmods.dev/commands/avelikiy/great_cto/rfc)
Your own site
<a href="https://agentmods.dev/commands/avelikiy/great_cto/rfc"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/rfc.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,629 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.02629
Opus 5 $0.00012 $0.01314
Sonnet 5 $0.00005 $0.00526
Haiku 4.5 $0.00002 $0.00263

Measured 4d ago against content hash 0f5e93060cf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 4d 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.

commands/rfc.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the RFC command. Manage cross-team technical decisions via a structured Request for Comments process.

Setup

source .great_cto/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"

TEAM_SIZE_RAW=$(grep "^team-size:" .great_cto/PROJECT.md 2>/dev/null | awk '{print $2}')
# Validate: must be a plain positive integer. Anything else → treat as 1 (single dev).
if [[ "$TEAM_SIZE_RAW" =~ ^[0-9]+$ ]]; then
  TEAM_SIZE="$TEAM_SIZE_RAW"
else
  [ -n "$TEAM_SIZE_RAW" ] && echo "WARN: team-size='$TEAM_SIZE_RAW' is not a positive integer — treating as 1."
  TEAM_SIZE=1
fi
if [ "$TEAM_SIZE" -lt 10 ]; then
  echo "RFC process is for teams of 10+. Your team: $TEAM_SIZE."
  echo "For smaller teams, discuss decisions in chat and record them as ADRs directly."
  echo "To use RFC anyway: set 'team-size: 10' in .great_cto/PROJECT.md"
  exit 0
fi

RFC_DIR="docs/rfcs"
INDEX_FILE="$RFC_DIR/RFC-INDEX.md"
ACTION="${1:-list}"
mkdir -p "$RFC_DIR"

Action: new "title" — create a new RFC

TITLE="$2"
# Get next RFC number
LAST_NUM=$(ls "$RFC_DIR"/RFC-*.md 2>/dev/null | grep -oE 'RFC-[0-9]+' | grep -oE '[0-9]+' | sort -n | tail -1 || echo "0")
NUM=$(printf "%03d" $((LAST_NUM + 1)))
SLUG=$(echo "$TITLE" | tr '[:upper:]' '[:lower:]' | tr ' ' '-' | tr -cd 'a-z0-9-' | cut -c1-40)
RFC_FILE="$RFC_DIR/RFC-${NUM}-${SLUG}.md"
AUTHOR=$(git config user.name 2>/dev/null || echo "unknown")
DATE=$(date +%Y-%m-%d)
DEADLINE=$(python3 -c "from datetime import date, timedelta; d=date.today(); days=0; count=0
while count<5:
  d+=timedelta(1)
  if d.weekday()<5: count+=1
print(d.isoformat())" 2>/dev/null || date -v+7d +%Y-%m-%d 2>/dev/null || date +%Y-%m-%d)

Write $RFC_FILE:

# RFC-<NUM>: <title>

Status: DRAFT
Author: <author>
Created: <date>
Review deadline: <5 business days from today>
Teams affected: []
Related ADR: —
Supersedes: —   # optional: comma list of ADRs this RFC replaces, e.g. ADR-003, ADR-007

---

## Problem

> What problem are we solving? Who is affected? What happens if we don't solve it?

[Fill in]

## Proposal

> The specific change or decision being proposed.

[Fill in]

## Alternatives considered

> At least 2 alternatives you evaluated and why they were rejected.

1. **Do nothing**: [reason rejected]
2. **[Alternative B]**: [reason rejected]

## Impact

**Breaking changes:** [yes/no — describe if yes]
**Migration path:** [if breaking — how teams migrate]
**Teams affected:** [list teams who need to act or adjust]
**Cost:** [infra cost delta, if any]
**Timeline:** [estimate]

## Open questions

- [ ] Q1: [question that needs resolution before this can be accepted]
- [ ] Q2:

## Comments

> Add comments with: /rfc comment <id> "text"

---

## Decision

> Filled in by: /rfc close <id> accept|reject

Status: DRAFT
Decision: —
Decided by: —
Date: —
Reason: —
ADR created: —

Read the full file on GitHub · 293 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. 4d ago First seen · 293 lines · 24 tokens per session scan A 0f5e93060cf7

Subscribe to this mod's changes

rfc is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,629 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 2026-09-03.