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/gradusnikov/eclipse-chatgpt-plugin/claude-mdgit clone --depth 1 https://github.com/gradusnikov/eclipse-chatgpt-pluginWrote 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/gradusnikov/eclipse-chatgpt-plugin/claude-md)<a href="https://agentmods.dev/instructions/gradusnikov/eclipse-chatgpt-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/gradusnikov/eclipse-chatgpt-plugin/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 | $0.01403 | $0.01403 |
| Opus 5 | $0.00701 | $0.00701 |
| Sonnet 5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
eclipse-chatgpt-plugin 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AssistAI - Eclipse IDE Plugin
Project Overview
AssistAI is an Eclipse IDE plugin that integrates LLM assistants (OpenAI, Anthropic, Gemini, Grok, DeepSeek, Groq) into the development environment. It also functions as an MCP Server, exposing Eclipse IDE tools via HTTP for external clients like Claude Code and Claude Desktop.
Project Structure
plugins/com.github.gradusnikov.eclipse.plugin.assistai.main/— main plugin (Java 21, Eclipse PDE)src/com/github/gradusnikov/eclipse/assistai/— source rootchat/— chat session managementcommands/— Eclipse command handlerscompletion/— code completion integrationhandlers/— event and request handlersjobs/— Eclipse background jobsmcp/— MCP (Model Context Protocol) implementationannotations/—@McpServer,@Tool,@ToolParamannotationshttp/— HTTP server infrastructure (auth, registry, preferences)local/— in-memory MCP transportservers/— MCP server endpoint classes (@McpServerannotated)services/— service classes with business logic for MCP tools
models/— data modelsnetwork/clients/— API connector clients (OpenAI, OpenAI Responses, Anthropic, Gemini, Grok, DeepSeek, Groq)preferences/— preference pages and initializersprompt/— prompt templates and managementresources/— resource cachingservices/— top-level services (separate from MCP services)tools/— utility classesview/— UI views and editors
tests/com.github.gradusnikov.eclipse.plugin.assistai.main.tests/— test project
MCP Tools Available
This project exposes Eclipse IDE capabilities as MCP tools. When working on code in Eclipse projects, prefer using these MCP tools over direct file edits.
The full reference — every tool, its parameters and the shape of what it returns — is
plugins/com.github.gradusnikov.eclipse.plugin.assistai.main/docs/mcp-api.md. It is
generated from the annotations by tools/generate-mcp-api.sh; do not edit it by hand,
and note that McpApiDocPDETest fails if it drifts from the code.
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 · 96 lines · 1,403 tokens per session scan A c2d076ec3f02
eclipse-chatgpt-plugin CLAUDE.md is an instructions file published in the GitHub repository gradusnikov/eclipse-chatgpt-plugin (167 stars, last pushed 6d ago), licensed MIT. It adds 1,403 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 2026-08-30.
Other instructions, from other repositories
python-sdk AGENTS.md
AGENTS.md instructions for modelcontextprotocol/python-sdk, covering development guidelines, note for ai agents, branching model, package management and code quality.
bifrost AGENTS.md
AGENTS.md instructions for maximhq/bifrost, covering agents.md — bifrost ai gateway, what is bifrost?, repository layout, go workspace and build, test & dev commands.
agent CLAUDE.md
Claude Code instructions for 1mcp-app/agent, covering claude.md, repository information, development commands, setup and build & run.
mcp-dotnet-samples AGENTS.md
AGENTS.md instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
Embody AGENTS.md
AGENTS.md instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
rust-sdk fetch-mcp-doc.instructions.md
Instructions for modelcontextprotocol/rust-sdk, covering overall, key changes, architecture, baseprotocol and lifecycle.