write-design-doc

write-design-doc is a skill for Claude Code, Codex from marin-community/marin. It costs 33 tokens per session (2,405 once invoked), scanned A, original, Apache-2.0.

A workflow for creating Marin design-document artifacts: a short proposal, supporting research, and a concrete specification. A design document is a written plan used to get feedback before implementation.

In plain words
What is it for?
Use it when explicitly preparing a design doc, one-page proposal, research summary, or specification for a Marin project.
Why use it?
It separates early architectural decisions from implementation details and records the agreed public contracts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents); mentions AGENTS.md.

About the project

Marin is an open-source research program, software platform, and community for developing foundation models such as large language models. Researchers use it for data preparation, tokenization, pretraining, posttraining, evaluation, and related experiments, including work on audio-text, DNA, and protein models. The catalogue entries are add-ons that support workflows around Marin.

marin-community/marin · 3,403 stars · on GitHub · marin.community

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 skills/marin-community/marin/write-design-doc
Any agent
npx skills add marin-community/marin --skill write-design-doc
Clone the repo
git clone --depth 1 https://github.com/marin-community/marin

Made for: Claude Code, Codex.

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 write-design-doc

README.md
[![agentmods](https://agentmods.dev/badge/skills/marin-community/marin/write-design-doc.svg)](https://agentmods.dev/skills/marin-community/marin/write-design-doc)
Your own site
<a href="https://agentmods.dev/skills/marin-community/marin/write-design-doc"><img src="https://agentmods.dev/badge/skills/marin-community/marin/write-design-doc.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,405 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 5.1 $0.00033 $0.02405
Opus 5 $0.00016 $0.01203
Sonnet 5 $0.00007 $0.00481
Haiku 4.5 $0.00003 $0.00241

Measured 6d ago against content hash ba3fdb724312, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

write-design-doc 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 6d 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/skills/write-design-doc/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Design Doc Workflow

Purpose

A design doc in Marin is a ~1-page proposal for early feedback before implementation. Area owners LGTM or comment quickly, and the author implements in parallel. See issue #5210 for rationale.

This skill is interactive: ask the user questions when you genuinely don't know, but make reasonable inferences and proceed when you can.

The template lives at .agents/projects/design-template.md. New docs go to a slug-named directory .agents/projects/<slug>/ (slug only, no date prefix — git log records the date). Inside it:

  • design.md — the 1-pager (always).
  • research.md — in-repo refs, prior art, Q&A summary (always — even a short one).
  • spec.md — concrete contracts, written after the design stabilises (always).

spec.md is the contract layer, not an implementation plan. It pins the public surface — .proto content, public class/function signatures with types, schema-registry CREATE tables, directory layout, file paths. It excludes algorithm pseudocode, sequenced steps, file-by-file plans, "how" rather than "what" — those belong in the PR description or get deleted in favor of writing the code. Even an "internal" refactor has a public surface (an imported function, a passed flag, a config key); the spec pins it so reviewers know what they're agreeing to. If you can't write a spec, you don't have a design yet.

When to use this skill

This is a change-mode design workflow. Use it only when the user explicitly asks to create a design doc, one-pager, or proposal. Diff size, complexity, duration, and cross-subproject scope do not invoke this skill. This skill owns the repository files and publishing workflow for design artifacts.

Do not use this skill for questions, walkthroughs, informal architecture reviews, or requests to assess whether an idea is reasonable. Investigate those requests and answer inline. Start this workflow only after the user explicitly asks for a design.

Read the full file on GitHub · 156 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. 6d ago First seen · 156 lines · 33 tokens per session scan A ba3fdb724312

Subscribe to this mod's changes

write-design-doc is a skill published in the GitHub repository marin-community/marin (3,403 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 2,405 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens