add-framework

A command for saving a reusable thinking framework from a conversation.

In plain words
What is it for?
Use it when a conversation has produced a clear, reusable process or decision structure. It checks for duplicates and saves the framework with the project’s existing terminology.
Why use it?
It prevents useful decision rules or mental models from being lost after a one-off discussion, while checking that the framework will be useful again.

Command

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/extremeclarity/claude-plugins/add-framework
Clone the repo
git clone --depth 1 https://github.com/extremeclarity/claude-plugins
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 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 $0.00008 $0.00442
Opus 5 $0.00004 $0.00221
Sonnet 5 $0.00002 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash 9fc81e65c831, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-framework 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 2d 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.

plugins/worldview/commands/add-framework.md · 56 lines

What it actually says

Add Framework

Create a reusable thinking framework from the current conversation.

The Bar

Only add frameworks that will clearly help in future sessions.

Before creating a framework, ask:

  1. Reuse Test: Will this framework be applied to similar problems in the future? If it's a one-off analysis, don't create a framework.

  2. Future Value Test: Can you articulate a concrete future scenario where having this framework changes Claude's approach for the better?

  3. Structure Test: Does it have clear structure (criteria, steps, matrix, model)? Vague advice doesn't make a framework.


Process

  1. Review — Look at the recent conversation for patterns, decision criteria, or mental models that emerged.

  2. Check for duplicates — Read .worldview/frameworks/index.txt. If a similar framework exists, ask the user: update existing or create new?

  3. Align terminology — Read .worldview/terminology.txt. Use consistent terms from the existing terminology.

  4. Write the framework — Create .worldview/frameworks/[framework-name].md with:

    • Clear title
    • When to use this framework
    • The framework structure (criteria, steps, decision matrix, etc.)
    • Examples if helpful

    Use kebab-case for framework name (e.g., decision-matrix.md, error-handling-patterns.md).

  5. Update index — Append to .worldview/frameworks/index.txt:

    [framework-name].md: One-line summary
    
  6. Extract terms — If the framework introduces terms with non-obvious meanings, append to .worldview/terminology.txt:

    [YYYY-MM-DD] *Term*: Definition
    

    Apply the same bar: only add terms that will help Claude in future sessions.

Guidelines

  • Keep frameworks focused on a single problem type
  • Use the user's language and framing where possible
  • Reference existing terminology to maintain consistency
  • Keep framework files concise — capture the structure, not exhaustive explanation
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. 2d ago First seen · 56 lines · 8 tokens per session scan A 9fc81e65c831

Subscribe to this mod's changes

add-framework is a command published in the GitHub repository extremeclarity/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 442 once invoked, about $0.0000 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.