What is RAD_framework CLAUDE.md?

A repository template for documenting a project's purpose, technology choices, folder structure, commands, architecture decisions, and coding rules for Claude Code.

Use it when setting up or maintaining project instructions, especially for repositories that require every behavior change to include validation.

It gives coding agents reliable project context and sets explicit expectations for tests, error handling, function size, and implementation quality.

RAD_framework CLAUDE.md — Instructions file for coding agents by seanrreid: A repository template for documenting a project's purpose, techn

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 instructions/seanrreid/rad_framework/claude-md

Clone the repo

git clone --depth 1 https://github.com/seanrreid/RAD_framework

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/instructions/seanrreid/rad_framework/claude-md.svg)](https://agentmods.dev/instructions/seanrreid/rad_framework/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/seanrreid/rad_framework/claude-md"><img src="https://agentmods.dev/badge/instructions/seanrreid/rad_framework/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 5,032 This file is loaded in full into every session.

When invoked 5,032 The same file — it is already loaded in full.

Security scan B 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.05032	$0.05032
Opus 5	$0.02516	$0.02516
Sonnet 5	$0.01006	$0.01006
Haiku 4.5	$0.00503	$0.00503

Measured 4d ago against content hash dd1803af2065, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

RAD_framework CLAUDE.md scanned grade B with 1 finding 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.

Asks the agent to reveal its instructionsmediumSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

`manual` mode: platform scripts print instructions instead of calling CLI tools.

CLAUDE.md · 466 lines

How it starts

The opening of the file, as written. The whole thing — 466 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Context

Always-loaded into every Claude Code session. Fill in every section. Accurate CLAUDE.md = fewer corrections. See docs/architect-guide.md for maintenance guidance.

Project

Name: Description: Status:

Stack

Layer	Technology
Backend
Frontend
Database
Testing
Package manager

Project Structure

[describe your directory layout here]

Commands

# Install


# Run (development)


# Run tests


# Run E2E tests

Architecture Decisions

Coding Conventions

Every behavior change ships a test in the same commit — new scripts get a co-located test-<name>.sh fixture; harness changes extend harness/test/*.test.js; a task with no testable surface says so explicitly in its Validate field
Functions stay under ~40 lines with intent-revealing names; magic values become named constants at the top of the file; comments state constraints, not narration
Never swallow errors: every catch/|| true either rethrows, exits non-zero, or logs the reason with context; fail-closed is the default at every gate or check boundary
Edge cases are named in the task's Validate field before implementation (empty input, missing field, zero/negative, non-array) and each gets an explicit test case

Testing Standards

What Claude Must Never Do

Never commit secrets, tokens, or credentials
Never assume a library exists — only use packages in the package file
Never execute /rad-deliver without an approved event in .agents/state/<feature>/events.jsonl (the gate authority, appended by /rad-approve). The plan doc's Status: approved header is a display-only mirror, not the gate. This rule is now ALSO deterministically enforced by a PreToolUse hook (scripts/deliver-gate-hook.mjs, registered in .claude/settings.json) that blocks an unapproved /rad-deliver Skill call fail-closed (exit 2) — not prose alone.

Read the full file on GitHub · 466 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.

4d ago First seen · 466 lines · 5,032 tokens per session scan B dd1803af2065

Subscribe to this mod's changes

RAD_framework CLAUDE.md is an instructions file published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 9d ago), licensed MIT. It adds 5,032 tokens to every session, about $0.0252 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

RAD_framework CLAUDE.md