Open SWE is an open-source software factory that gives coding tasks to an asynchronous agent, which investigates repositories, changes code, validates the results, and delivers pull requests. Engineering teams use it to automate code changes, reviews, CI follow-up, and related repository work from dashboards and connected tools.
Borrowing it
Nothing to install: this file belongs to langchain-ai/open-swe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/langchain-ai/open-swe/main/AGENTS.mdgit clone --depth 1 https://github.com/langchain-ai/open-sweWrote 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/langchain-ai/open-swe/agents-md)<a href="https://agentmods.dev/instructions/langchain-ai/open-swe/agents-md"><img src="https://agentmods.dev/badge/instructions/langchain-ai/open-swe/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/langchain-ai/open-swe/agents-md"><img src="https://agentmods.dev/badge/instructions/langchain-ai/open-swe/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02256 | $0.02256 |
| Opus 5.5 | $0.00902 | $0.00902 |
| Sonnet 5.5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
open-swe 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 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Open SWE is an asynchronous coding agent and software factory.
Graphs and the FastAPI app are registered in langgraph.json.
JS packages form a pnpm/turbo workspace (pnpm-workspace.yaml); use pnpm for them.
Local setup: docs/DEVELOPMENT.md.
Constant gardening
Before making any change, first till the soil: refactor the surrounding code so the change slots in naturally and the result reads as if it had always been designed that way. Spend real effort here rather than bolting features onto whatever shape the code happens to be in.
Every agent, reviewer and review-scout thread runs on Managed Deep Agents, as one graph, open-swe, from the project in mda/; the backend refuses to start without MDA_RUNTIME_URL and REMOTE_RUNTIME_TOKEN_SECRET.
openswe/threads/router.py serves the Agent Server's thread API from the PostgreSQL thread index and sends those threads' runs there; every new thread is created there, and threads created before that are read-only (openswe/graphs/read_only.py).
MDA owns the run: the model loop, checkpoints, the thread's sandbox, every tool call, and every hook and middleware around them.
The backend is a set of stateless APIs MDA calls: typed endpoints at /agent-api/{endpoint} (packages/runtime-api, imported by both sides), each answered from the run token the router signs and the request alone, on whichever replica it lands.
Shape new behavior to fit:
- Control flow (when to nudge, route, stop, refresh) is middleware in
mda/rt; checks around the file and shell tools go inrt/file_tools.py. - Work that needs the backend's credentials or data is a named
Endpointfor that work (route_model,task_context), never a generic phase call or an untyped body. - Data fixed for a run is worked out once when the backend starts it and sent in the run context (
Catalog,openswe/agent_api/client.py); a call that needs a fact derives it from the token. - State kept between calls lives in MDA's run state or PostgreSQL, never in backend memory.
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 · +7 lines · +162 tokens per session b1839564e5fe
- yesterday Changed · +42 lines · +108 tokens per session 6d8b234dba98
- 3d ago Changed · +9 lines · +31 tokens per session 47707a948d49
- 4d ago Changed · +1 lines · +54 tokens per session 9ef536b43beb
- 5d ago Changed · +1 lines · +191 tokens per session 7cafa35b4528
- 6d ago Changed · +2 lines · +109 tokens per session 3c1f51fe0384
- 10d ago Changed · +4 tokens per session 1f996b2125c5
- 12d ago Changed · -6 tokens per session b6e2286548a0
- 13d ago Changed · -21 tokens per session 5144bafd8349
- 14d ago First seen · 65 lines · 1,624 tokens per session scan A 6895f27dce0e
open-swe AGENTS.md is an instructions file published in the GitHub repository langchain-ai/open-swe (11,133 stars, last pushed today), licensed MIT. It adds 2,256 tokens to every session, about $0.0090 per session on Opus 5.5. 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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.