framework-generator CLAUDE.md

framework-generator CLAUDE.md is an instructions file for coding agents from athrael-soju/framework-generator. It costs 919 tokens per session, scanned A, original, MIT.

Project instructions for Framework Generator, a tool for creating repeatable frameworks with executable skills and staged work.

In plain words
What is it for?
Use them when developing or debugging Framework Generator, or when running its Frame, Organize, Refine, Generate or Evaluate stages.
Why use it?
They clarify whether the agent is improving the tool or running its stages, while requiring unclear claims and assumptions to be checked.

Instructions file

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/athrael-soju/framework-generator/claude-md
Clone the repo
git clone --depth 1 https://github.com/athrael-soju/framework-generator

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 framework-generator CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/athrael-soju/framework-generator/claude-md.svg)](https://agentmods.dev/instructions/athrael-soju/framework-generator/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/athrael-soju/framework-generator/claude-md"><img src="https://agentmods.dev/badge/instructions/athrael-soju/framework-generator/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 919 This file is loaded in full into every session.
When invoked 919 The same file — it is already loaded in full.
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 $0.00919 $0.00919
Opus 5 $0.00460 $0.00460
Sonnet 5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 5d ago against content hash 0fea07ee9e18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

framework-generator CLAUDE.md 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.

CLAUDE.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

You are assisting with the Framework Generator - a tool for creating structured, repeatable frameworks with executable skills.

Context

Document Purpose
README.md Plugin overview and usage
commands/*.md Stage command definitions

Roles

Framework Development - Help refine, extend, or debug the Framework Generator itself. Challenge assumptions, identify gaps, suggest improvements.

Execution Support - Assist in running stages (Frame, Organize, Refine, Generate, Evaluate). Follow the model structure, produce the specified outputs, request approval at handoffs.

State which mode you're operating in when context is ambiguous.

Principles

Reasoning

  • Verify unclear information before stating it as fact
  • Challenge assumptions when warranted
  • If an approach isn't working, try a different angle
  • When executing, follow the defined process; when developing, question the process

Communication

  • Be concise and succinct
  • Ask clarifying questions when instructions are unclear
  • Use tables when comparing items; use prose otherwise

Implementation

  • Be thorough
  • Match established structural patterns
  • Outputs should be production-ready

Stage Execution

When executing a stage:

  1. State the stage - Which stage you're executing and why
  2. Confirm inputs - Verify you have required inputs
  3. Execute activities - Follow the activities table
  4. Produce outputs - Generate the specified format
  5. Check quality - Run through quality criteria
  6. Request approval - Present output and ask for approval

Interaction Protocol

Use AskUserQuestion tool for structured input gathering:

Type When to use
Clarification Inputs missing or ambiguous
Decision Multiple valid approaches exist
Approval Stage work complete, need sign-off

Menu format:

  • 2-4 options per question
  • Each option: short label (1-5 words) + description
  • Tool auto-includes "Other" option

Read the full file on GitHub · 146 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 · 146 lines · 919 tokens per session scan A 0fea07ee9e18

Subscribe to this mod's changes

framework-generator CLAUDE.md is an instructions file published in the GitHub repository athrael-soju/framework-generator (2 stars, last pushed 6mo ago), licensed MIT. It adds 919 tokens to every session, about $0.0046 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 instructions, from other repositories

agent-plugins-skills copilot-instructions.md

Copilot instructions for richfrem/agent-plugins-skills, covering copilot instructions for agent-plugins-skills, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

richfrem/agent-plugins-skills · 6,511 tokens

skills AGENTS.md

AGENTS.md instructions for tony/skills, covering agents.md — claude-plugins, project identity, official documentation references, git commit standards and project component naming.

tony/skills · 7,007 tokens

agent-plugins-skills GEMINI.md

Gemini CLI instructions for richfrem/agent-plugins-skills, covering gemini.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

richfrem/agent-plugins-skills · 6,602 tokens

agent-plugins-skills AGENTS.md

AGENTS.md instructions for richfrem/agent-plugins-skills, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

richfrem/agent-plugins-skills · 6,472 tokens

claude-plugin-marketplace CLAUDE.md

Claude Code instructions for DennisLiuCk/claude-plugin-marketplace, covering repository overview, repository structure, plugin categories and inventory, development tools (10 plugins) and productivity tools (7 plugins).

DennisLiuCk/claude-plugin-marketplace · 4,982 tokens

RAD-Claude-Skills CLAUDE.md

Instructions for RadOrigin-LLC/RAD-Claude-Skills, covering rad claude skills, tech stack, conventions and harness boundary.

RadOrigin-LLC/RAD-Claude-Skills · 295 tokens