frame

frame is a command for coding agents from athrael-soju/framework-generator. It costs 12 tokens per session (798 once invoked), scanned A, original, MIT.

A planning stage for defining the purpose, users, context, and boundaries of a new framework.

In plain words
What is it for?
It asks about the current process, its problems, desired outcome, constraints, intended users, and any existing frameworks to use as references.
Why use it?
It turns a painful or inconsistent manual workflow into a clearly scoped proposal before detailed files are generated.

Command

Part of the framework-generator plugin — 6 commands shipped together

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

Or install framework-generator, the plugin that ships this one along with the rest of its 6 commands.

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 frame

README.md
[![agentmods](https://agentmods.dev/badge/commands/athrael-soju/framework-generator/frame.svg)](https://agentmods.dev/commands/athrael-soju/framework-generator/frame)
Your own site
<a href="https://agentmods.dev/commands/athrael-soju/framework-generator/frame"><img src="https://agentmods.dev/badge/commands/athrael-soju/framework-generator/frame.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 798 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00012 $0.00798
Opus 5 $0.00006 $0.00399
Sonnet 5 $0.00002 $0.00160
Haiku 4.5 $0.00001 $0.00080

Measured 4d ago against content hash 581bf4d88f71, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frame 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/frame.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frame

Define the purpose and boundaries of a new framework.

Inputs

Input Source
problem_description User input
context User input
scope User input
reference_frameworks Optional: existing frameworks

Input Format

User-provided problem description:

problem_description: |
  What workflow or process needs systematizing?
  What's painful or inconsistent about it?
  What would success look like?

User-provided context:

context:
  domain: [Area of work]
  constraints: [Limitations, requirements]
  intended_users: [Who will run this framework]

Optional reference frameworks:

reference_frameworks:
  - name: [Framework Name]
    path: docs/models/[framework].md

Process

1. Clarify Problem - Ask what workflow or process the user wants to systematize:

  • What are the steps they currently do manually?
  • What's painful or inconsistent about it?
  • What would success look like?

2. Articulate Purpose - Draft why this framework should exist:

  • What value does systematizing provide?
  • Why a framework vs. a checklist or ad-hoc process?

3. Set Boundaries - Define scope:

  • What's explicitly in scope?
  • What's explicitly out of scope?
  • What adjacent problems are we not solving?

4. Identify Triggers - When should this framework be run:

  • One-time vs. ongoing?
  • What events or conditions trigger execution?

5. Determine Type - What kind of framework:

  • Foundation: single assessment, run once, feeds other frameworks
  • Pipeline: sequential stages, ongoing, feedback loops
  • Cyclical: repeating execution on a cadence
  • Hub: central stage that others connect to

6. Map Dependencies - What other frameworks does this require:

  • Does it need outputs from another framework?
  • What external inputs are required?

Interaction

Use the AskUserQuestion tool for:

  • Clarifying the problem and workflow to systematize
  • Choosing between framework types
  • Confirming scope boundaries

Read the full file on GitHub · 143 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 · 143 lines · 12 tokens per session scan A 581bf4d88f71

Subscribe to this mod's changes

frame 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 798 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.