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/gemini-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/gemini-md)<a href="https://agentmods.dev/instructions/godstale/ide-adapter/gemini-md"><img src="https://agentmods.dev/badge/instructions/godstale/ide-adapter/gemini-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 | $0.00693 | $0.00693 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
IDE-Adapter GEMINI.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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GEMINI.md
This file provides instructional context and an overview of the IDEA (IDE Adapter) project for Gemini interactions.
Project Overview
IDEA (Integrated Development Environment Adapter) is a VS Code Extension that exposes core IDE features to external CLI applications via a local WebSocket server.
Main Technologies:
- TypeScript
- Node.js
- VS Code Extension API
- WebSockets (
wspackage)
Architecture:
- IdeaServer: A WebSocket server (default port 7200) that accepts connections from external CLI clients.
- ClientSession: Manages the per-connection state machine (handshake → request/response loop).
- HandlerRegistry & Handlers: Maps protocol topics to specific actions (e.g.,
DefinitionHandler,FindHandler,ReplaceHandler,ReferencesHandler). - IdeaPanel & ProtocolViewer: VS Code Webview providers for a sidebar panel (Settings and Logs) and documentation viewing.
- Protocol: Defined in
docs/IDEA_InputProtocol.mdanddocs/IDEA_OutputProtocol.md. Communication uses JSON payloads over WebSockets.
Building and Running
Prerequisites:
- Node.js
- npm
Commands:
- Install dependencies:
npm install - Compile (TypeScript build to
out/):npm run compile - Watch mode (Incremental build):
npm run watch - Lint (ESLint):
npm run lint
Running and Testing:
- Launch Extension: Press F5 in VS Code to launch the Extension Development Host for manual testing.
- Test Client: A test client script is provided to interact with the running extension server. Refer to @test/HOWTO_TEST.md.
Development Conventions
- Module System: The project uses
"module": "Node16". All intra-project imports must use the.jsextension (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 and output formats in
docs/IDEA_InputProtocol.mdanddocs/IDEA_OutputProtocol.md.
- Create
- Protocol Rules:
- The first message from a client must be a handshake:
{ "type": "handshake", "workspacePath": "..." }. - Subsequent messages are requests:
{ "topic": "...", "requestId": "...", "params": {...} }. - Error codes include:
PARSE_ERROR,INVALID_REQUEST,UNKNOWN_TOPIC,WORKSPACE_NOT_FOUND,HANDLER_ERROR.
- The first message from a client must be a handshake:
- Project Management:
- TODO Lists: When implementing new features, create/update TODO lists first (in
docs/TODO.md) before writing code. Move completed items to a history file (docs/TODO_History.md). - Documentation: Protocol input/output formats must be kept in sync with the respective markdown files in
docs/. User-visible changes should be added toREADME.md.
- TODO Lists: When implementing new features, create/update TODO lists first (in
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 · 52 lines · 693 tokens per session scan A 7521b4fe87c6
IDE-Adapter GEMINI.md is an instructions file published in the GitHub repository godstale/IDE-Adapter (3 stars, last pushed 6mo ago), licensed MIT. It adds 693 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.
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.