What is coherent-design-method CLAUDE.md?

Project instructions for Coherent Design Method, a system that encodes visual design rules so AI-generated user interfaces follow a consistent style. A user interface is the screens and controls people use in an application.

Use them when working on this project to consult its design decisions, known AI-output problems, model notes, validation rules, and release workflow.

They give an AI agent the project’s required reading and development rules before it changes code.

How skovtun/coherent-design-method configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to skovtun/coherent-design-method. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/skovtun/coherent-design-method/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/skovtun/coherent-design-method

Made for: Claude Code.

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/instructions/skovtun/coherent-design-method/claude-md/github.svg)](https://agentmods.dev/instructions/skovtun/coherent-design-method/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/skovtun/coherent-design-method/claude-md"><img src="https://agentmods.dev/badge/instructions/skovtun/coherent-design-method/claude-md/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/instructions/skovtun/coherent-design-method/claude-md"><img src="https://agentmods.dev/badge/instructions/skovtun/coherent-design-method/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,235 This file is loaded in full into every session.

When invoked 4,235 The same file — it is already loaded in full.

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	$0.04235	$0.04235
Opus 5.5	$0.01694	$0.01694
Sonnet 5.5	$0.00847	$0.00847
Haiku 4.5	$0.00424	$0.00424

Measured 14d ago against content hash c75111b9141c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coherent-design-method CLAUDE.md 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 14d 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.

CLAUDE.md · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coherent Design Method

The model designs. Coherent governs. Since v0.27.0 Coherent does not author UI. The coding agent (Claude Code, Codex) builds the app; Coherent scopes every edit against a code-derived graph, enforces its write set, verifies it in a real browser (build, renders, pixel diff, browser errors, identity leaks), returns an honest verdict and rolls back what fails. Why: ADR-0011 (plain Claude Code beat the coherent chat pipeline on every screen). The generator pipeline below is classic / deprecated (init --classic).

Current version: 0.32.0 Packages: @getcoherent/core + @getcoherent/cli (published together, same version) Tests: 2679 passing

⚡ Start-of-session reading (REQUIRED before any work)

Coherent maintains a platform-level LLM wiki with decisions, patterns, and ideas that persist across sessions. Read these before touching code:

docs/wiki/PATTERNS_JOURNAL.md — append-only log of every AI-output bug we've seen, its root cause, and what we shipped in response. If you're debugging something that feels familiar, it probably IS.
docs/wiki/RULES_MAP.md — every rule in design-constraints.ts with origin bug, validator, golden pattern. Check this before adding or modifying a rule.
docs/wiki/MODEL_PROFILE.md — empirical notes on Claude Sonnet 4's systematic behaviors. Saves time on "why does AI keep doing X?" questions.
docs/wiki/IDEAS_BACKLOG.md — open proposals, deferred work, rejected ideas with reasons. Check before proposing a new feature — it might already be scoped.
docs/wiki/ADR/ — architectural decision records for significant shifts (e.g., "why golden patterns over word-based rules").

These files capture why things are the way they are. CLAUDE.md and CHANGELOG.md answer "what is" and "what changed"; the wiki answers "why". Update them when you:

Add a new rule (row in RULES_MAP.md + JOURNAL entry if bug-driven).
Observe a new AI-output failure pattern (JOURNAL entry).
Make a breaking or philosophically-significant change (new ADR).
Propose or defer an idea (IDEAS_BACKLOG.md).

Read the full file on GitHub · 403 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.

14d ago Changed c75111b9141c
16d ago Changed a2561a6e8373
17d ago Changed · +3 lines · +87 tokens per session 47f7489ac74e
18d ago Changed · +36 lines · +558 tokens per session 3345a8d1716e
2mo ago First seen · 364 lines · 3,590 tokens per session scan A 736cb7d406ef

Subscribe to this mod's changes

coherent-design-method CLAUDE.md is an instructions file published in the GitHub repository skovtun/coherent-design-method (21 stars, last pushed 15d ago), licensed MIT. It adds 4,235 tokens to every session, about $0.0169 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 2026-08-30.

Code Generation Design and UX ai cli code-generator design-system design-systems

coherent-design-method CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
coherent-design-method CLAUDE.mdskovtun/coherent-design-method	Instructions file	21	15d ago	MIT	A	4,235	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

coherent-design-method: Instructions file for Claude Code