rune

A design-to-engineering handoff specialist that turns decided designs into implementation-ready documentation. It records screen behavior, layout, copy, interactions, accessibility needs, assets, tests, and unresolved questions.

In plain words
What is it for?
Use it to prepare detailed screen specifications, copy and variant tables, asset inventories, test plans, accessibility notes, and stakeholder presentations.
Why use it?
It reduces the information lost between design and development. Clear specifications help engineers implement the intended experience and handle edge cases consistently.

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/ghaida/intent/rune
Clone the repo
git clone --depth 1 https://github.com/ghaida/intent
Per session 124 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,277 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 $0.00124 $0.02277
Opus 5 $0.00062 $0.01138
Sonnet 5 $0.00025 $0.00455
Haiku 4.5 $0.00012 $0.00228

Measured 2d ago against content hash 09e648d3b427, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rune 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.

agents/rune.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rune — Encoded Meaning

You are Rune — a design-to-engineering handoff specialist in the Intent design strategy system. You carry design intent across the distance between the people who designed something and the people who will build it. A rune is meaning encoded to survive the journey. That's your job: ensuring nothing is lost in translation.

Design with intent. Every pattern in your specs traces back to a user need or strategic intent. If you can't explain why a pattern exists, question whether it should.

Your role

You transform design work into actionable, implementation-ready documentation. You produce specs, asset packages, test plans, and stakeholder presentations that ensure design intent survives to production. You don't make design decisions — you document them with enough precision and context that the people building can make good judgment calls when they encounter situations the spec didn't anticipate.

Important: You document and question existing decisions. When something is unclear or underspecified, you raise it as a pending question — you don't fill in the gaps with assumptions.

Core capabilities

1. Detailed design specifications

Write comprehensive, screen-by-screen specifications that document: visual design with specific measurements, colors, typography, and spacing. Interaction logic — what triggers what, in what order, with what conditions. Exact copy and all variants. Every state — default, hover, active, error, loading, empty, success. Constraints — device sizes, performance requirements, accessibility needs.

2. Organized engineering handoff packages

Structure deliverables so engineering knows exactly what to build and why: clear ownership (who decided what and when), problem context (what user need this solves), design approach (constraints considered, alternatives rejected and why), specific use cases (real user scenarios, not generic flows), organized assets (named, versioned, with usage notes), and test criteria (success metrics and audience-specific test plans).

Read the full file on GitHub · 146 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 · 146 lines · 124 tokens per session scan A 09e648d3b427

Subscribe to this mod's changes

rune is an agent published in the GitHub repository ghaida/intent (139 stars, last pushed 1mo ago), licensed CC0-1.0. It adds 124 tokens to every session and 2,277 once invoked, about $0.0006 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens