What is obot CLAUDE.md?

Repository instructions for Obot, an AI governance platform that manages MCP servers, model access, agent skills, audit logs, and device policies.

Use them when working on the Go backend, SvelteKit interface, MCP features, governance tools, documentation, or integration tests.

They give developers the project overview, technology choices, and standard commands for running, building, and testing the application.

obot CLAUDE.md — Instructions file for coding agents by obot-platform: Repository instructions for Obot, an AI governance platform that…

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/obot-platform/obot/claude-md

Clone the repo

git clone --depth 1 https://github.com/obot-platform/obot

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/obot-platform/obot/claude-md.svg)](https://agentmods.dev/instructions/obot-platform/obot/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/obot-platform/obot/claude-md"><img src="https://agentmods.dev/badge/instructions/obot-platform/obot/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,535 This file is loaded in full into every session.

When invoked 1,535 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.

Model	Per session	Once invoked
Fable 5	$0.01535	$0.01535
Opus 5	$0.00767	$0.00767
Sonnet 5	$0.00307	$0.00307
Haiku 4.5	$0.00153	$0.00153

Measured today against content hash 2a27bc2f5778, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

obot 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 today.

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 · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to AI agents when working with code in this repository.

Project Overview

Obot is an open source AI governance platform with the following features:

MCP registry
MCP server hosting and management
LLM gateway and audit logs
Agent Skills registry
Device Management for scanning, auditing, and enforcing policies on local AI agents

Tech Stack

Backend: Go with PostgreSQL (pgx), MCP protocol (github.com/modelcontextprotocol/go-sdk), Kubernetes client libraries
Frontend: SvelteKit 5 with Vite, Tailwind CSS 4, TypeScript, CodeMirror 6, Milkdown (markdown editor)
Documentation: Docusaurus 3 (in /docs)

Common Commands

Development

make dev              # Run full dev environment (Go server + SvelteKit UI) with hot reload
make dev-open         # Same as above, but opens browser automatically

Building

make build            # Build Go binary to bin/obot
make ui               # Build user UI (both browser and Node targets)
make all              # Build UI + Go binary

Testing

make test             # Run all Go tests (excludes integration tests)
make test-integration # Run integration tests

Linting & Formatting

make lint             # Run Go linters (golangci-lint)
make tidy             # Tidy Go modules
make validate-go-code # Run tidy, generate, lint, and check for uncommitted changes

UI Development (in ui/user/)

pnpm install          # Install dependencies
pnpm run dev          # Start dev server
pnpm run check        # TypeScript type checking
pnpm run lint         # ESLint + Prettier check
pnpm run format       # Auto-format code
pnpm run ci           # Run format, lint, and check
pnpm run test         # Run UI integration tests

Documentation (in docs/)

make serve-docs       # Start local docs server

Design Proposals and Architecture Decisions

Design significant or architecturally important changes first in the Obot Design Proposals repository. A merged ODP is the signal that implementation may proceed.
When an implementation introduces a meaningful architectural decision, include an ADR in the implementation pull request and follow the adr/README.md guidance. The ADR records the decision that shipped and links to its related issues and ODP when applicable.
If implementation differs materially from the accepted ODP, resolve the change through a follow-up ODP rather than documenting the surprise only in the ADR.

Read the full file on GitHub · 151 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.

today Changed · +4 lines · +43 tokens per session 2a27bc2f5778
4d ago First seen · 147 lines · 1,492 tokens per session scan A 9557cb470329

Subscribe to this mod's changes

obot CLAUDE.md is an instructions file published in the GitHub repository obot-platform/obot (974 stars, last pushed today), licensed MIT. It adds 1,535 tokens to every session, about $0.0077 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.

ai chat mcp modelcontextprotocol

AionUi AGENTS.md

AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.

iOfficeAI/AionUi · 1,663 tokens

ida-pro-mcp CLAUDE.md

Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.

mrexodia/ida-pro-mcp · 1,135 tokens

converse.js AGENTS.md

Instructions for conversejs/converse.js, covering converse.js agent guidelines, project overview, monorepo, key entry points and directory structure.

conversejs/converse.js · 4,569 tokens

octo-server AGENTS.md

AGENTS.md instructions for Mininglamp-OSS/octo-server, covering agents.md, project overview, common commands, build and run tests for a module.

Mininglamp-OSS/octo-server · 2,429 tokens

tableau-mcp CLAUDE.md

Claude Code instructions for tableau/tableau-mcp, covering claude.md, build & development commands, building, running the server and testing.

tableau/tableau-mcp · 2,610 tokens

vscode-unify-chat-provider AGENTS.md

Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…

smallmain/vscode-unify-chat-provider · 271 tokens