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/sholtomaud/ir-mcp/agents-mdgit clone --depth 1 https://github.com/sholtomaud/ir-mcpWrote 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/sholtomaud/ir-mcp/agents-md)<a href="https://agentmods.dev/instructions/sholtomaud/ir-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sholtomaud/ir-mcp/agents-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 | $0.00474 | $0.00474 |
| Opus 5 | $0.00237 | $0.00237 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
ir-mcp AGENTS.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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This document provides guidance for AI agents working on the Independent Reserve MCP Server codebase.
Project Structure
server.py: The main MCP server. It handles tool definitions (handle_list_tools) and tool calls (handle_call_tool) from the AI. When adding a new tool, you must update both of these functions.ir_client.py: The WebSocket client responsible for connecting to the Independent Reserve API, managing subscriptions, and caching data. All interactions with the WebSocket API should be handled in this file.requirements.txt: Python dependencies. Usepip install -r requirements.txtto install them..env: API keys and secrets are stored in a.envfile. A template is provided in.env.example.
Authentication
The client uses HMAC-SHA256 to authenticate with the Independent Reserve WebSocket API for private channels. The signature is generated using the API key, a nonce, and the channel name.
- The authentication logic is implemented in the
_subscribemethod inir_client.py. - The API key and secret must be set in the
.envfile for private channels to work.
Caching
The ir_client.py uses a caching mechanism to avoid redundant subscriptions.
- A subscription is cached for 5 minutes (
CACHE_TIMEOUT). - A background task (
_manage_subscriptions) runs periodically to unsubscribe from expired channels. - When adding new subscription-based tools, ensure they use the
_subscribemethod to take advantage of the caching logic.
Adding New Tools
To add a new tool:
- Add the tool definition to the list in the
handle_list_toolsfunction inserver.py. - Implement the tool's logic in
server.pyby adding a newelifblock in thehandle_call_toolfunction. - Add a corresponding method in
ir_client.pyto handle the data subscription and retrieval from the WebSocket API.
Testing
The tests/ directory contains tests for the server and client.
test_server.py: Tests for the MCP server logic.test_ir_client.py: Tests for the WebSocket client.
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 · 43 lines · 474 tokens per session scan A f9bd73864bc1
ir-mcp AGENTS.md is an instructions file published in the GitHub repository sholtomaud/ir-mcp (0 stars, last pushed 8mo ago), licensed MIT. It adds 474 tokens to every session, about $0.0024 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
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).
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.
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.
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).
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.
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.