wiremd CLAUDE.md

wiremd CLAUDE.md is an instructions file for coding agents from akonan/wiremd. It costs 1,024 tokens per session, scanned A, original, MIT.

A repository instruction file for wiremd, a tool that turns Markdown with wireframing notation into visual page drafts and outputs such as HTML, React, Tailwind, or JSON.

In plain words
What is it for?
Use it when developing wiremd, building it, running tests, checking types or lint, or working on its documentation site and command-line tool.
Why use it?
It explains the project structure, commands, and expected testing process so an agent can work on the parser and renderers consistently.

Instructions file

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 instructions/akonan/wiremd/claude-md
Clone the repo
git clone --depth 1 https://github.com/akonan/wiremd

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 wiremd CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/akonan/wiremd/claude-md.svg)](https://agentmods.dev/instructions/akonan/wiremd/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/akonan/wiremd/claude-md"><img src="https://agentmods.dev/badge/instructions/akonan/wiremd/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,024 This file is loaded in full into every session.
When invoked 1,024 The same file — it is already loaded in full.
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 $0.01024 $0.01024
Opus 5 $0.00512 $0.00512
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00102 $0.00102

Measured 4d ago against content hash bad1b62962fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiremd 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 4d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

wiremd converts Markdown with extended wireframing syntax into visual wireframes. It ships as an npm library, a CLI tool, and a VS Code extension. Input is .md files with wiremd syntax; output is HTML (7 styles), React/JSX, Tailwind, or JSON.

Commands

npm run build        # TypeScript + Vite → dist/
npm test             # Run all tests (vitest)
npm test -- tests/parser.test.ts              # Single test file
npm test -- tests/parser.test.ts -t "Button"  # Single test by name
npm run test:coverage
npm run typecheck    # Strict TypeScript check
npm run lint         # ESLint on src/
npm run docs:dev     # VitePress docs dev server

CLI usage (after build):

wiremd input.md --style clean --serve 3001 --watch
wiremd input.md -o output.html -f html -s sketch

Architecture

The pipeline: Markdown string → parse() → WiremdAST → render*() → HTML/React/JSON/Tailwind

src/
├── types.ts                        # ~40 discriminated-union AST node types
├── index.ts                        # Public exports
├── parser/
│   ├── index.ts                    # parse() + validate(); calls resolveIncludes()
│   ├── transformer.ts              # MDAST → wiremd AST (the bulk of parsing logic)
│   ├── remark-containers.ts        # ::: block syntax plugin (supports nesting)
│   └── remark-inline-containers.ts # [[ ... ]] nav/inline syntax plugin
└── renderer/
    ├── index.ts                    # renderToHTML(), renderToReact(), renderToJSON(), renderToTailwind()
    ├── html-renderer.ts            # Component → HTML string (handles all node types)
    ├── react-renderer.ts           # Component → React/JSX string
    ├── tailwind-renderer.ts        # Component → Tailwind-classed HTML
    └── styles.ts                   # 7 CSS style systems (sketch, clean, wireframe, material, brutal, tailwind, none)

Parser flow: unified/remark parses standard Markdown into MDAST, then remark-containers and remark-inline-containers handle wiremd-specific syntax (::: card, [[ nav ]], buttons [Label]*, inputs [_____]). The transformer walks the MDAST and emits wiremd AST nodes.

Read the full file on GitHub · 75 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. 4d ago First seen · 75 lines · 1,024 tokens per session scan A bad1b62962fc

Subscribe to this mod's changes

wiremd CLAUDE.md is an instructions file published in the GitHub repository akonan/wiremd (97 stars, last pushed 3mo ago), licensed MIT. It adds 1,024 tokens to every session, about $0.0051 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.