import-framework

A command that reads a file or folder and proposes useful project context to import. It checks whether the information is relevant, valuable for future sessions, and not already covered by the project worldview.

In plain words
What is it for?
Use it to import selected Markdown or text-based frameworks, terminology, principles, and related insights into a project worldview.
Why use it?
It reduces the risk of filling future agent sessions with unnecessary context. It asks for a path when none is provided instead of scanning the project by guesswork.

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/import-framework
Clone the repo
git clone --depth 1 https://github.com/extremeclarity/claude-plugins
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 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 $0.00010 $0.01046
Opus 5 $0.00005 $0.00523
Sonnet 5 $0.00002 $0.00209
Haiku 4.5 $0.00001 $0.00105

Measured 2d ago against content hash f22a89ac0f40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

import-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/import-framework.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Import Framework

Import frameworks from external files or folders, with supporting terminology and insights.

Input: File path or folder path (as argument)

The Bar

Only import what will clearly help in future sessions.

Every import costs context space in every future session. Before proposing anything, ask:

  1. Future Value Test: Will this meaningfully help Claude in future sessions on this project? If you can't articulate a concrete scenario, skip it.

  2. Relevance Test: Does it connect to what this project is already about? Unrelated frameworks add noise.

  3. Uniqueness Test: Is this already captured in the worldview, or is it general knowledge Claude already has?


Step 0: Get Source Path

If no path was provided as an argument, ask the user for the file or folder path to import from. Do not guess or scan for files.

Process

1. Read Source + Project Context

Source:

  1. If path is a file: read the file
  2. If path is a folder: use Glob to find **/*.md and **/*.txt, read all
  3. If >2000 lines: warn user and recommend splitting

Project context (for relevance checking):

  • .worldview/terminology.txt
  • .worldview/principles.txt
  • .worldview/frameworks/index.txt (index only, not full frameworks)

2. Detect Candidate Frameworks

Scan source for structured knowledge that could become frameworks:

  • Decision trees / evaluation criteria
  • Multi-step processes / workflows
  • Mental models with clear structure
  • Comparison matrices / trade-off analyses
  • Causal models / diagnostic frameworks

For each candidate, apply the bar:

  • Duplicate check: Does it already exist in frameworks index?
  • Relevance check: Does it connect to project terminology, principles, or existing frameworks?
  • Future value check: Will having this framework change Claude's approach in future sessions?

Skip anything that doesn't clearly pass all three.

3. Extract Supporting Items

For each candidate framework, extract:

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 10 tokens per session scan A f22a89ac0f40

Subscribe to this mod's changes

import-framework is a command published in the GitHub repository extremeclarity/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 10 tokens to every session and 1,046 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.