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.
npx agentmods add instructions/athrael-soju/framework-generator/claude-mdgit clone --depth 1 https://github.com/athrael-soju/framework-generatorWrote 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.
[](https://agentmods.dev/instructions/athrael-soju/framework-generator/claude-md)<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>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 | $0.00919 | $0.00919 |
| Opus 5 | $0.00460 | $0.00460 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
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.
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:
- State the stage - Which stage you're executing and why
- Confirm inputs - Verify you have required inputs
- Execute activities - Follow the activities table
- Produce outputs - Generate the specified format
- Check quality - Run through quality criteria
- 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
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.
- 5d ago First seen · 146 lines · 919 tokens per session scan A 0fea07ee9e18
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.
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.
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.
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.
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.
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).
RAD-Claude-Skills CLAUDE.md
Instructions for RadOrigin-LLC/RAD-Claude-Skills, covering rad claude skills, tech stack, conventions and harness boundary.