agentmods.dev

astrotation CLAUDE.md

Project instructions for astrotation, an Astro development tool where people annotate webpage elements and send feedback to coding agents. It describes how the browser toolbar, development server, annotation store, and MCP connection work.

In plain words
What is it for?
Useful when developing, testing, or debugging astrotation and its live annotation and feedback tools.
Why use it?
It gives the agent the project’s architecture and operating rules, making it easier to work on the code correctly.

Instructions file

0 1mo ago A scan 707 tokens original MIT
View the source file dpush91/astrotation
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/dpush91/astrotation/claude-md
Clone the repo
git clone --depth 1 https://github.com/dpush91/astrotation
Per session 707 This file is loaded in full into every session.
When invoked 707 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 $0.00707 $0.00707
Opus 5 $0.00353 $0.00353
Sonnet 5 $0.00141 $0.00141
Haiku 4.5 $0.00071 $0.00071

Measured 2d ago against content hash e9e1bbb397e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

astrotation 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 2d 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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — astrotation

What this is

Astro integration: visual feedback tool for AI coding agents (Agentation replica, Astro-native). Owner annotates elements in the Astro Dev Toolbar overlay → annotations land in an in-process store → agents consume them live over MCP (Streamable HTTP, port 7133).

Architecture (single process, dev-only)

browser: toolbar.js (Dev Toolbar app, ShadowRoot UI)
   ↕ Astro toolbar server events (astrotation:* messages, built-in WS)
dev server: index.js (integration) + store.js (JSON file + EventEmitter)
   ↕ mcp.js — Streamable HTTP MCP on 127.0.0.1:7133/mcp (stateless,
     fresh McpServer per request; store is the shared singleton)
Claude Code: astrotation_list / get / watch / acknowledge / feedback /
             dismiss / reply / clear
  • src/index.js — integration; hooks: config:setup (addDevToolbarApp), server:setup (store + toolbar bridge + MCP), server:done (close).
  • src/store.js — AnnotationStore: CRUD, thread replies, clear(), atomic save (tmp+rename), watch() long-poll (batches events for 1.5s).
  • src/mcp.js — MCP tools + HTTP endpoint; /health for checks. buildServer(store) exported for the smoke test.
  • src/toolbar.js — overlay: hover highlight with source label, ↑/↓ DOM traversal, click → note popup, pins (status-colored), panel (threads, replies, delete, clear-done, copy-markdown fallback).
  • test/smoke.mjs — npm test; store + all MCP tools (InMemoryTransport) + /health. Runs on prepublishOnly.

Key facts

  • Plain JS, no build step; exports points straight at src/.
  • Deps: @modelcontextprotocol/sdk + zod. Peer: astro >= 4.7 (toolbar API).
  • Element→source mapping = Astro's own data-astro-source-file/-loc dev attributes. The dev toolbar strips them from the live DOM on load, so on annotate we re-fetch the page HTML (attrs intact there) and resolve the selector via DOMParser. Paths trimmed to src/….
  • Capture also includes trimmed outerHTML, section (nearest heading), role/aria-label — richer context for the agent than a selector alone.
  • Store file: <project>/.astrotation/annotations.json (host projects should gitignore it).
  • Statuses: pending → acknowledged → feedback (agent done, awaiting owner review) → resolved | dismissed. Agent terminal action = astrotation_feedback (pin turns red ◆); resolve/dismiss are owner-side (overlay set-status button). Owner replies wake astrotation_watch.
  • License: MIT, ours. Agentation (PolyForm Shield) used as concept reference ONLY — no code copied. See decisions.md.

Read the full file on GitHub · 57 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. 2d ago First seen · 57 lines · 707 tokens per session scan A e9e1bbb397e2

Subscribe to this mod's changes

astrotation CLAUDE.md is an instructions file published in the GitHub repository dpush91/astrotation (0 stars, last pushed 1mo ago), licensed MIT. It adds 707 tokens to every session, about $0.0035 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 2026-08-31.

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 · 6,785 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

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

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 · 4,345 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

next.js 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