agentmods.dev

ai: Instructions file for Claude Code

CLAUDE.md

ai CLAUDE.md is an instructions file for Claude Code from fluttersdk/ai. It costs 1,341 tokens per session, scanned A, original, MIT.

A project instruction file for FlutterSDK AI, a registry that distributes coding skills, tool connections, and commands for several developer assistants. It describes the project structure, supported components, and maintenance commands.

In plain words
What is it for?
Use it when working on the FlutterSDK AI registry, its skills, its tool server, or its installation scripts. It helps with builds, tests, linting, registry validation, and dry-run installations.
Why use it?
It gives contributors the rules needed to build, test, lint, validate, and install changes consistently. It also documents how the registry is organized across different coding tools.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions subagents.

This is fluttersdk/ai's own configuration. It tells Claude Code how to work on ai 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 ai configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 3repo yesterday A scan 1,341 tokens original MIT
View source ↗ fluttersdk/ai
Reuse

Borrowing it

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

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 ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fluttersdk/ai/claude-md/github.svg)](https://agentmods.dev/instructions/fluttersdk/ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fluttersdk/ai/claude-md"><img src="https://agentmods.dev/badge/instructions/fluttersdk/ai/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.

agentmods 80×15 button for ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fluttersdk/ai/claude-md"><img src="https://agentmods.dev/badge/instructions/fluttersdk/ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,341 This file is loaded in full into every session.
When invoked 1,341 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01341 $0.01341
Opus 5.5 $0.00536 $0.00536
Sonnet 5.5 $0.00268 $0.00268
Haiku 4.5 $0.00134 $0.00134

Measured 1mo ago against content hash 39224dc88fc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai 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 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.

CLAUDE.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

FlutterSDK AI skill registry that distributes AI coding skills, MCP servers, and commands for Wind UI, Magic Framework, and more across OpenCode, Claude Code, Cursor, Gemini CLI, and VS Code Copilot.

Hosted via GitHub Pages at fluttersdk.github.io/ai/

Commands

Command Description
npm run build Compile MCP server (from mcps/fluttersdk-mcp/)
npm run lint ESLint check (MCP server)
npm test Run MCP server tests
cd mcps/fluttersdk-mcp && npm test Run bridge-specific tests
node -e "JSON.parse(require('fs').readFileSync('skills/index.json','utf8'))" Validate registry JSON
bash scripts/install.sh --dry-run Preview multi-tool installation

Architecture

  • skills/: GitHub Pages root. Each skill = <name>/SKILL.md + <name>/references/*.md
    • wind-ui/: Wind UI className system, from fluttersdk_wind
    • magic-framework/: Magic Framework IoC + Facades + ORM, from magic
    • fluttersdk-dusk/: E2E Flutter app driver via MCP, from fluttersdk_dusk
    • fluttersdk-telescope/: Runtime inspector, 9 ring buffers, from fluttersdk_telescope
    • fluttersdk-artisan/: CLI framework + stdio MCP server, from fluttersdk_artisan

Every skills/<name>/ directory is a MIRROR. Never edit a skill here. sync.yml rsyncs the upstream subtree with --delete, so a registry-only file is one sync away from deletion; that is how six hand-written wind-ui reference files disappeared before anyone noticed. Edit the skill in its upstream repo (fluttersdk/wind, magic, dusk, telescope, artisan) and let the sync deliver it.

The sync fires when an upstream publishes a release, not on every upstream push. To pull an unreleased skill fix, run the upstream repo's "Dispatch skill update to registry" workflow manually. Per-skill versions live in each SKILL.md frontmatter and in skills/index.json; do not copy them into prose here, they drift within a release cycle.

  • skills/index.json: OpenCode discovery manifest. Source of truth for file listing
  • .claude-plugin/: Plugin manifest (plugin.json) + marketplace catalog (marketplace.json)
  • mcps/: MCP servers (TypeScript, stdio transport, Zod schemas)
  • commands/: Claude Code plugin commands (flutter-test.md); auto-discovered as /fluttersdk:<name>
  • agents/: plugin subagents (flutter-reviewer.md, flutter-reviewer-deep.md); auto-discovered as fluttersdk:<name>. Plugin agents support name, description, model, effort, maxTurns, tools, disallowedTools, skills, memory, background, isolation only; hooks, mcpServers, and permissionMode are ignored for plugin-shipped agents, so do not add them
  • references/: plugin-owned reference files the skill and agents read through ${CLAUDE_PLUGIN_ROOT} (flutter-review-core.md, dart-style-core.md). Not part of any mirrored skill

Read the full file on GitHub · 78 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. 1mo ago First seen · 78 lines · 1,341 tokens per session scan A 39224dc88fc8

Subscribe to this mod's changes

ai CLAUDE.md is an instructions file published in the GitHub repository fluttersdk/ai (3 stars, last pushed yesterday), licensed MIT. It adds 1,341 tokens to every session, about $0.0054 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 2026-08-31.

fluttermagic-frameworkskillswind-ui
Related

Other instructions, from other repositories

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 · 9,649 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 · 7,257 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens