What is opendev CLAUDE.md?

A set of project instructions for OpenDev, an open-source AI coding agent written in Rust. It explains the workspace, which is a group of related code packages, and the commands for building, testing, checking, and running its web interface.

Use it to build the Rust workspace, run selected or complete tests, enforce formatting and lint rules, create the release binary, watch for rebuilds, and build the React/Vite web interface.

It provides the exact commands needed to check the whole project and individual packages. This reduces guesswork when compiling code, running tests, fixing lint errors, or producing the release program.

opendev CLAUDE.md — Instructions file for coding agents by opendev-to: A set of project instructions for OpenDev, an open-source…

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/opendev-to/opendev/claude-md

Clone the repo

git clone --depth 1 https://github.com/opendev-to/opendev

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/opendev-to/opendev/claude-md.svg)](https://agentmods.dev/instructions/opendev-to/opendev/claude-md)

Your own site

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

Per session 1,247 This file is loaded in full into every session.

When invoked 1,247 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin 95% copy Near-identical to another mod 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	$0.01247	$0.01247
Opus 5	$0.00624	$0.00624
Sonnet 5	$0.00249	$0.00249
Haiku 4.5	$0.00125	$0.00125

Measured 5d ago against content hash deb616acbf23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

opendev 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 5d 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.

Origin

This is a copy

95% identical to opendev AGENTS.md — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 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.

Build & Development Commands

# Build the entire workspace
cargo build --workspace

# Run all tests (skip doc-tests that have 0 tests)
cargo test --workspace --lib --tests

# Type/lint checks
cargo check --workspace
cargo clippy --workspace -- -D warnings

# Format code
cargo fmt --all

# Run a specific crate's tests
cargo test -p opendev-tui

# Run a single test by name
cargo test -p opendev-tui test_render_thinking_expanded

# Build and install release binary
cargo build --release -p opendev-cli
# Binary outputs to target/release/opendev (not opendev-cli)

# Auto-rebuild on file changes (requires cargo-watch)
cargo watch -x 'build --release -p opendev-cli'

# Web UI (React/Vite frontend)
cd web-ui && npm ci && npm run build

Architecture Overview

OpenDev is a Rust workspace (edition 2024) with 21 crates under crates/. It is an open-source AI coding agent that spawns parallel agents, each bound to the LLM of your choice. The binary entry point is opendev-cli.

Crate Map

crates/
  opendev-cli         ← Binary entry point (clap CLI, dispatches to TUI/REPL/subcommands)
  opendev-tui         ← Terminal UI (ratatui + crossterm, async event loop)
  opendev-web         ← Web backend (axum + WebSocket, broadcasts agent events)
  opendev-repl        ← REPL loop, query enhancement (@file injection), message preparation
  opendev-agents      ← ReAct loop, thinking/critique phases, prompt composition
  opendev-runtime     ← Runtime services (approval, cost tracking, modes)
  opendev-config      ← Hierarchical config loading (project > user > env > defaults)
  opendev-models      ← Shared data types and models
  opendev-http        ← HTTP client, auth rotation, provider adapters (Anthropic, OpenAI, etc.)
  opendev-context     ← Context engineering (compaction stages, message validation)
  opendev-history     ← Session persistence (JSON per project, atomic writes)
  opendev-memory      ← Memory systems (embeddings, reflection, playbook)
  opendev-tools-core  ← Tool registry, BaseTool trait, dispatch
  opendev-tools-impl  ← 30+ tool implementations (bash, edit, file ops, web, agents)
  opendev-tools-lsp   ← LSP integration and language servers
  opendev-tools-symbol← AST-based symbol navigation
  opendev-mcp         ← Model Context Protocol integration
  opendev-channels    ← Channel routing
  opendev-hooks       ← Hook system
  opendev-plugins     ← Plugin manager
  opendev-docker      ← Docker runtime support

Read the full file on GitHub · 129 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.

5d ago First seen · 129 lines · 1,247 tokens per session scan A deb616acbf23

Subscribe to this mod's changes

opendev CLAUDE.md is an instructions file published in the GitHub repository opendev-to/opendev (832 stars, last pushed 27d ago), licensed MIT. It adds 1,247 tokens to every session, about $0.0062 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to opendev AGENTS.md, differing in 12 lines, and is treated as a copy.

Building agents Languages Rust

turso AGENTS.md

AGENTS.md instructions for tursodatabase/turso, covering turso agent guidelines, quick reference, testing, running tests and test organization.

tursodatabase/turso · 2,194 tokens

cli AGENTS.md

AGENTS.md instructions for googleworkspace/cli, covering agents.md, project overview, build & test, changesets and architecture.

googleworkspace/cli · 2,700 tokens

azure-sdk-for-rust resourcemanager.instructions.md

Instructions for Azure/azure-sdk-for-rust, a project described as: This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.

Azure/azure-sdk-for-rust · 400 tokens

opendev CLAUDE.md