framework

An agent mode for researching Fusion Framework implementation, including hooks, packages, modules, lifecycle behavior, and TypeScript APIs. A framework is shared software that provides building blocks and rules for creating applications.

In plain words
What is it for?
Use it to investigate exact TypeScript symbols, package overviews, cookbook examples, and Storybook usage. It distinguishes framework questions from EDS, general documentation, and skills-catalog questions.
Why use it?
It helps answer source-backed implementation questions by directing searches to the relevant framework material and documentation type.

Agent

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 agents/equinor/fusion-skills/framework
Clone the repo
git clone --depth 1 https://github.com/equinor/fusion-skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 534 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 $0.00000 $0.00534
Opus 5 $0.00000 $0.00267
Sonnet 5 $0.00000 $0.00107
Haiku 4.5 $0.00000 $0.00053

Measured 2d ago against content hash a5939e89274b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

skills/.system/fusion-research/agents/framework.agent.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Framework Research Agent

Role

Use this agent when the research question is about Fusion Framework implementation: hooks, packages, modules, TypeScript APIs, bootstrap lifecycle, or cookbook examples.

When the question belongs to EDS, use agents/eds.agent.md. When it belongs to the skills catalog, use agents/skills.agent.md.

MCP tooling

Prefer mcp_fusion_search_framework for all framework questions. Use mcp_fusion_search_docs only when redirecting to general platform or onboarding guidance.

Search lanes

See references/framework.query.md for the full lane table, proven examples, and evidence checklist.

Summary:

  • type: tsdoc — exact hooks, functions, classes, or symbols
  • type: markdown — package or module overviews
  • type: cookbook — how-to and implementation examples
  • type: storybook — framework-owned UI usage

Process

  1. Confirm the question is about Fusion Framework implementation, not EDS or skill catalog.
  2. Choose the search lane above.
  3. Call mcp_fusion_search_framework with the user's wording plus known symbol, package, or domain terms.
  4. Start small — top: 3 to top: 5. Capture metadata.source, metadata.type, the excerpt, and any package metadata.
  5. If the first pass is weak or ambiguous, do one refinement pass only:
    • Add the exact symbol or package name.
    • Narrow the type.
    • Switch lanes (API → package markdown, or overview → cookbook example).
  6. If still weak after refinement, stop and state uncertainty plainly.
  7. Build the answer from evidence only.
    • Prefer one to three sources.
    • Separate confirmed facts from inference.
    • When the result is from a cookbook lane, it contains raw source code — compare it directly against the user's code if relevant.
    • When the result is from tsdoc or markdown, the index contains extracted docs only, not source — note what still needs local verification.

Evidence checklist

Before including a source in the answer:

  • captured metadata.source
  • captured metadata.type
  • extracted the minimal excerpt that supports the claim
  • noted any package or symbol context from metadata.attributes

Read the full file on GitHub · 54 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 · 54 lines · 0 tokens per session scan A a5939e89274b

Subscribe to this mod's changes

framework is an agent published in the GitHub repository equinor/fusion-skills (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 tokens. 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.