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 commands/athrael-soju/framework-generator/organizegit 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/commands/athrael-soju/framework-generator/organize)<a href="https://agentmods.dev/commands/athrael-soju/framework-generator/organize"><img src="https://agentmods.dev/badge/commands/athrael-soju/framework-generator/organize.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 | $0.00012 | $0.00896 |
| Opus 5 | $0.00006 | $0.00448 |
| Sonnet 5 | $0.00002 | $0.00179 |
| Haiku 4.5 | $0.00001 | $0.00090 |
Grade A, and why
organize 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Organize
Map the stages and flow of the framework.
Inputs
| Input | Source |
|---|---|
| framework_charter | Frame stage output |
| stages | User input |
| pattern | User input |
| feedback_loops | User input |
| reference_frameworks | Optional |
Input Format
From Frame stage (output/{date}/{name}/1-frame/charter.md):
# Framework Charter: {NAME}
## Problem
{Workflow being addressed}
## Purpose
{Why this framework exists}
## Scope
**In:** {What's covered}
**Out:** {What's excluded}
## Type
{Foundation / Pipeline / Cyclical / Hub}
## Dependencies
| Requires | From | Why |
Optional reference frameworks:
reference_frameworks:
- path: docs/models/[framework].md
Process
1. Identify Stages - Break the workflow into distinct stages:
- What are the major phases of work?
- Each stage should have a clear purpose and output
- Aim for 3-7 stages (fewer for foundation frameworks)
2. Name Stages - Choose clear, action-oriented names:
- Verbs or nouns that describe what happens
- Consider acronym potential if desired
- Check for naming conflicts with existing skills
3. Map Flow - Determine how stages connect:
- Linear: A → B → C
- Branching: A → B or C based on condition
- Hub: Central stage others connect to
- Draw the flow as a mermaid diagram
4. Define Dependencies - What does this framework need from others:
- Which inputs come from other frameworks?
- At which stage are they needed?
5. Identify Feedback Loops - When to go backwards:
- What conditions cause a return to earlier stages?
- What triggers re-evaluation?
6. Define Terminal States - How does the framework end:
- Success state(s)
- Failure/exit states
- What actions accompany each?
Interaction
Use the AskUserQuestion tool for:
- Confirming stage names and purposes
- Choosing between flow patterns (linear, branching, hub)
- Identifying feedback loop conditions
Always use AskUserQuestion (not plain text) when gathering input, clarifying requirements, or requesting approval.
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 · 153 lines · 12 tokens per session scan A 81991f852498
organize is a command published in the GitHub repository athrael-soju/framework-generator (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 896 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 2026-08-31.
Other commands, from other repositories
os-architect
Front-door intake for Agentic OS evolution — classifies intent, audits existing capabilities, proposes a path (A/B/C), and dispatches implementation work via Copilot CLI.
readme
Generate a README.md for a repository.
video-script
Generate a video or screencast script from a codebase.
quick-readme
Quick README - skips audience phases for standard developer docs.
commit-push-pr
建立一個 Git 提交、推送到遠端,並開啟一個 Pull Request.
commit
Command "commit" from DennisLiuCk/claude-plugin-marketplace, covering 背景資訊 and 指示.