agentic-mermaid: Instructions file for Claude Code

CLAUDE.md

agentic-mermaid CLAUDE.md is an instructions file for Claude Code from adewale/agentic-mermaid. It costs 758 tokens per session, scanned A, original, from a forked repository, MIT.

Repository guidance for AI coding agents working on Agentic Mermaid, a tool that renders Mermaid diagrams as SVG, PNG, ASCII, or Unicode and supports typed editing. It documents the project structure, commands, testing, and pull requests.

In plain words
What is it for?
Use it when installing dependencies, running tests or type checks, tracking layout quality, rendering diagrams, building the website, or preparing pull requests.
Why use it?
It gives an agent the project-specific rules and checks needed to make safe changes and reproduce test failures.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is adewale/agentic-mermaid's own configuration. It tells Claude Code how to work on agentic-mermaid itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-mermaid configures →

Reuse

Borrowing it

Nothing to install: this file belongs to adewale/agentic-mermaid. 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/adewale/agentic-mermaid/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/adewale/agentic-mermaid

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.

agentmods badge for agentic-mermaid CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adewale/agentic-mermaid/claude-md.svg)](https://agentmods.dev/instructions/adewale/agentic-mermaid/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/adewale/agentic-mermaid/claude-md"><img src="https://agentmods.dev/badge/instructions/adewale/agentic-mermaid/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 758 This file is loaded in full into every session.
When invoked 758 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 fork From a forked repository.
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 $0.00758 $0.00758
Opus 5 $0.00379 $0.00379
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 7d ago against content hash 0a48a59ca7c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agentic-mermaid 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 7d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for AI agents working in this repository.

Project

Agentic Mermaid (agentic-mermaid on npm) — a fork of lukilabs/beautiful-mermaid that renders Mermaid diagrams to SVG/PNG/ASCII/Unicode with a typed, agent-native editing surface. Source lives in src/; the layout pipeline is in src/layout-engine.ts, the deterministic layout-quality rubric in src/layout-rubric.ts.

Commands

  • bun install — install dependencies.
  • bun run test — run the full covered unit suite with the canonical timeout (the CI gate). fast-check seeds are pinned by a preload; AM_FC_SEED=<int> reproduces a roll, AM_FC_SEED=random is finder mode (see docs/testing-strategy.md §4).
  • bun run typecheck — canonical typecheck across core and repository surfaces.
  • bun run track — heuristic layout-quality tracker (improvements/regressions vs baseline).
  • bun run bin/am.ts render <file> --format png --output out.png — render a diagram.
  • bun run website — build the Cloudflare Workers site into website/public/, a gitignored build artifact (rebuilt at deploy by deploy-cloudflare.yml, and on-demand by explicit imports of src/__tests__/website-public-fixture.ts). You do not commit it. website/src/generated/ is also ephemeral. website:check performs an in-memory clean regeneration and contract comparison for both trees; run bun run website only when local serving, deployment, or an explicit fixture consumer needs materialized outputs.

Layout is deterministic: identical input must produce identical geometry.

Pull requests — use the good-pr skill

Before opening or updating a PR, use the good-pr skill (https://github.com/adewale/good-pr; install with npx skills add adewale/good-pr). It evaluates a PR across seven dimensions and ships a readiness script and a description template. Apply it to every PR in this repo.

The seven dimensions:

  1. Reproduction steps — reference the issue; give the exact steps/probe a maintainer can run to reproduce the bug and confirm the fix.
  2. Visual evidence — for visual/UI changes include captioned before/after renders (generated artifacts preferred). If a geometry change is below visual perceptibility, say so honestly and let the quantitative metric stand as the evidence — do not pad the PR with near-identical screenshots.
  3. Code that fits — match existing patterns, naming, and comment density; no unrelated refactoring smuggled in.
  4. Tests that prove the fix — tests must fail when the fix is reverted. Verify red→green and state the result (e.g. "N tests fail without the fix").
  5. Scoped and safe — one concern, minimal diff, full test suite run, risks flagged.
  6. Standalone description — what / why / how / testing / risk, understandable without reading the diff.
  7. Trust — be honest about readiness, limitations, and any test that is a regression guard rather than a bug-discriminating test.

Read the full file on GitHub · 64 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. 7d ago First seen · 64 lines · 758 tokens per session scan A 0a48a59ca7c8

Subscribe to this mod's changes

agentic-mermaid CLAUDE.md is an instructions file published in the GitHub repository adewale/agentic-mermaid (50 stars, last pushed 7d ago), licensed MIT. It adds 758 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens