What is coherent-design-method AGENTS.md?

Project instructions for Coherent Design Method, a codebase organized as several related packages in one repository. They describe its structure, development process, tests, and required checks.

Use them when modifying the CLI, core package, documentation, or related configuration. They guide builds, tests, linting, type checks, regression tests, and package boundaries.

They give a coding agent project-specific rules, so it knows where code belongs and which checks must pass before changes are committed. The test process follows TDD: write a failing test, make it pass, then improve the code.

How skovtun/coherent-design-method configures Codex and OpenCode

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/AGENTS.md

Clone the repo

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

Made for: Codex, OpenCode.

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

Your own site

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

Per session 603 This file is loaded in full into every session.

When invoked 603 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	$0.00603	$0.00603
Opus 5.5	$0.00241	$0.00241
Sonnet 5.5	$0.00121	$0.00121
Haiku 4.5	$0.00060	$0.00060

Measured 2mo ago against content hash 67ab8eb64281, 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 AGENTS.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 2mo 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.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Coherent Design Method

How AI agents should work with this codebase.

Project Structure

packages/
  cli/          # @getcoherent/cli — CLI tool (coherent init/chat/preview/export)
  core/         # @getcoherent/core — Generators, types, managers
docs/           # Case studies, documentation
.bmad-core/     # BMAD agent templates and checklists
.cursor/rules/  # Cursor AI rules (BMAD agents, UI generation)

Development Workflow

Before coding

Write a failing test (RED)
Implement the fix (GREEN)
Refactor if needed (REFACTOR)
Run pnpm test — must be all green before commit

Commands

pnpm build          # Build all packages
pnpm test           # Run all tests (vitest)
pnpm lint           # ESLint
pnpm typecheck      # TypeScript strict check

Testing

Tests live next to source: foo.ts → foo.test.ts
Framework: vitest
Every bug fix MUST have a regression test
Run tests before every commit

CI Pipeline

Build → Lint → Typecheck → Test (all must pass)

Architecture Decisions

Packages

core: Pure logic — generators, schemas, managers. No side effects, no I/O prompts.
cli: User-facing — commands, AI providers, file I/O, spinners.

Key patterns

Zod schemas validate all AI-generated data with .transform() for auto-correction
autoFixCode() post-processes generated TSX to fix common AI mistakes
Shared components are extracted from pages and registered in design-system.config.ts
Backups are created after every coherent chat in .coherent/backups/

Error handling rules

Every CLI command must have a top-level try/catch
Never swallow errors silently (no empty catch {})
Use ora spinners — always .fail() or .warn() on error (never leave running)
API rate limits: maxRetries: 1 to fail fast

Common AI generation bugs to guard against

< / > / & HTML entities in JavaScript code
Non-existent lucide-react icon names (validate against package exports)
Routes without leading / (auto-fix in Zod schema)
Dynamic routes [id] in navigation links (filter out)
Missing "use client" when hooks are used

Read the full file on GitHub · 70 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.

2mo ago First seen · 70 lines · 603 tokens per session scan A 67ab8eb64281

Subscribe to this mod's changes

coherent-design-method AGENTS.md is an instructions file published in the GitHub repository skovtun/coherent-design-method (21 stars, last pushed 15d ago), licensed MIT. It adds 603 tokens to every session, about $0.0024 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 ai cli code-generator design-system design-systems

coherent-design-method AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
coherent-design-method AGENTS.mdskovtun/coherent-design-method	Instructions file	21	15d ago	MIT	A	603	Codex, OpenCode
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 Codex