A structured method for writing software requirements, milestone designs, small behaviour specifications, and implementation plans. It separates what the product needs from how the system works and how the work will be carried out.

It is for writing or revising PRDs, planning milestones, defining testable increments, and closing completed work.

It prevents requirements, design details, acceptance criteria, and file-level tasks from being placed in the wrong document or discussed at the wrong level.

design-docs — Skill for Claude Code by xdg/xdg-claude

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.

Any agent

npx skills add xdg/xdg-claude --skill design-docs

Clone the repo

git clone --depth 1 https://github.com/xdg/xdg-claude

Made for: Claude Code.

Or install design-docs, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/xdg/xdg-claude/design-docs/github.svg)](https://agentmods.dev/skills/xdg/xdg-claude/design-docs)

Your own site

<a href="https://agentmods.dev/skills/xdg/xdg-claude/design-docs"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/design-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/xdg/xdg-claude/design-docs"><img src="https://agentmods.dev/badge/skills/xdg/xdg-claude/design-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,793 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00105	$0.01793
Opus 5.5	$0.00042	$0.00717
Sonnet 5.5	$0.00021	$0.00359
Haiku 4.5	$0.00011	$0.00179

Measured 1mo ago against content hash 9727b0f09fdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

design-docs 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 1mo 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.

design-docs/skills/design-docs/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Docs

The ladder

The ladder has four rungs; each answers one question. Each rung is a level of content that is always present, even when two rungs share a file.

	PRD	Milestone design	Inchstone spec	Implementation plan
Label	Needs	Shape	Behavior	Steps
Question	What must the product do, for whom, and why?	What does this milestone deliver, and how is the system composed to deliver it?	What must this increment observably do, precisely enough to test?	In what order, in which files?
Unit	The product	One milestone: a complete slice, either a capability its consumer can use or an experiment that resolves a question	One inchstone: one tangible, independently acceptable increment	One inchstone
States	Users, goals, non-goals, vocabulary, numbered requirements with reasons, constraints, open questions, future possibilities	Scope thesis, in/out with destinations, components and ownership, data flow, enforcement points, mechanisms with losing alternatives, inchstone list, exit criteria	Boundary, go/no-go discovery, continuity, forced changes to existing code, data and API in general terms, numbered acceptance criteria	Tasks, files, types, signatures, test names, sequence
Omits	Any mechanism, mode, layout, field, or owner of upkeep	Behavior detail (errors, edges, defaults), acceptance criteria, field names, endpoint contracts	Structure (inherited from the design), construction	Re-deciding anything above
Reader	Spec author ("required or invented?"); user ("does it do X?")	Spec author ("what is in, what shape?"); anyone ("why not X?")	Implementer, acceptor, reviewer a year on	Implementer, today

Strategy, then tactics. The PRD says what winning the war means. The design picks this hill, now, and not another, and fixes the shape of the force that takes it; it constrains every choice below. The spec says what "held" means: the flag on the summit, the road below cut, no fire from the ridge; conditions an observer can check without knowing how the assault went. The plan is the marching orders. Design and spec both answer "how" at different altitudes: design creates shapes and forecloses options; spec fills in what must be true for the work to count as done.

Read the full file on GitHub · 118 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed 9727b0f09fdc
2mo ago First seen · 118 lines · 105 tokens per session scan A 2e4366a70229

Subscribe to this mod's changes

design-docs is a skill published in the GitHub repository xdg/xdg-claude (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 105 tokens to every session and 1,793 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-07.

Planning Project management

design-docs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
design-docsxdg/xdg-claude	Skill	20	6d ago	Apache-2.0	A	105	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code