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.
npx agentmods add instructions/godstale/ide-adapter/claude-mdgit clone --depth 1 https://github.com/godstale/IDE-AdapterWrote 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.
[](https://agentmods.dev/instructions/godstale/ide-adapter/claude-md)<a href="https://agentmods.dev/instructions/godstale/ide-adapter/claude-md"><img src="https://agentmods.dev/badge/instructions/godstale/ide-adapter/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01398 | $0.01398 |
| Opus 5 | $0.00699 | $0.00699 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
IDE-Adapter 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.
How it starts
The opening of the file, as written. The whole thing — 125 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.
Commands
npm run compile # TypeScript build → out/
npm run watch # Incremental watch build
npm run lint # ESLint (src/**/*.ts)
Build output goes to out/. Press F5 in VS Code to launch the Extension Development Host for manual testing.
Architecture
This is a VS Code extension that runs a local WebSocket server (default port 7200). External CLI apps connect as clients.
activate()
├── IdeaLogger — EventEmitter, 500-entry ring buffer, emits 'entry'
├── HandlerRegistry — topic string → IHandler map
├── IdeaServer — WebSocketServer; injects logger + clientId into each session
│ └── ClientSession — per-connection state machine: handshake → request/response loop
├── IdeaPanel — WebviewViewProvider (Activity bar sidebar)
│ ├── Settings tab — server toggle, port change, protocol doc buttons, dev info
│ └── Logs tab — real-time log stream, inline JSON expand/collapse
└── ProtocolViewer — on-demand WebviewPanel for docs/IDEA_*.md files
Module system: "module": "Node16" — all intra-project imports must use .js extension (e.g. import { Foo } from './Foo.js').
Adding a New Handler
- Create
src/handlers/<Name>Handler.tsimplementingIHandlerfromsrc/protocol/types.ts. - Register it in
activate()insrc/extension.ts:registry.register('/app/vscode/...', new NameHandler()). - Document the input params in
docs/IDEA_InputProtocol.mdand result shape indocs/IDEA_OutputProtocol.md.
Protocol Rules
- First message from client must be
{ type: 'handshake', workspacePath: string }. Any other message closes the socket. - Subsequent messages are requests:
{ topic, requestId, params }. Responses echotopicandrequestId. - Error responses have
error: { code, message }; success responses haveresult: { ... }. - Error codes:
PARSE_ERROR,INVALID_REQUEST,UNKNOWN_TOPIC,WORKSPACE_NOT_FOUND,HANDLER_ERROR.
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.
- 4d ago First seen · 125 lines · 1,398 tokens per session scan A 076caeb9efc2
IDE-Adapter CLAUDE.md is an instructions file published in the GitHub repository godstale/IDE-Adapter (3 stars, last pushed 6mo ago), licensed MIT. It adds 1,398 tokens to every session, about $0.0070 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.
Other instructions, from other repositories
TokenTracker CLAUDE.md
Claude Code instructions for xiufengsun/TokenTracker, covering claude.md, project shape, frequently used commands, what's where and load-bearing conventions.
TokenTracker AGENTS.md
AGENTS.md instructions for xiufengsun/TokenTracker, covering agent instructions and insforge backend.
agentrules-architect AGENTS.md
Instructions for trevor-nichols/agentrules-architect, covering development principles, execplans, milestones, prefer cli creation over manual file creation and 2. temporal framework.
sync-agents-settings CLAUDE.md
Instructions for Leoyang183/sync-agents-settings, covering claude.md, commands, architecture, testing and publishing.
sync-agents-settings AGENTS.md
Instructions for Leoyang183/sync-agents-settings, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
kato AGENTS.md
AGENTS.md instructions for spectacular-voyage/kato, a project described as: Own your AI conversations.