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/opendev-to/opendev/agents-mdgit clone --depth 1 https://github.com/opendev-to/opendevWrote 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/opendev-to/opendev/agents-md)<a href="https://agentmods.dev/instructions/opendev-to/opendev/agents-md"><img src="https://agentmods.dev/badge/instructions/opendev-to/opendev/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 | $0.01189 | $0.01189 |
| Opus 5 | $0.00594 | $0.00594 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
opendev 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- opendev CLAUDE.md — 95% identical, 12 lines differ
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents 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
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 · 121 lines · 1,189 tokens per session scan A 12128a7c825b
opendev AGENTS.md is an instructions file published in the GitHub repository opendev-to/opendev (832 stars, last pushed 26d ago), licensed MIT. It adds 1,189 tokens to every session, about $0.0059 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.