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.
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 skills add langchain-ai/open-swe --skill environmentsgit 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/skills/langchain-ai/open-swe/environments)<a href="https://agentmods.dev/skills/langchain-ai/open-swe/environments"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/environments/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/skills/langchain-ai/open-swe/environments"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/environments.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 | $0.00084 | $0.01227 |
| Opus 5 | $0.00042 | $0.00613 |
| Sonnet 5 | $0.00017 | $0.00245 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
environments 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Environments
An environment is two things: a record (name, prompt, repos, sizing, optional scripts) and a published sandbox image, <prefix>-environment-<slug>:latest. Runs in that environment boot from the image and get the prompt appended to their system prompt. The environment named default is what every run uses unless the thread picked another one.
Only workspace admins can change environments, and only from an admin thread. Anyone can read them on Workspace settings → Environments. If the asker is not an admin, tell them what would need to happen and who can do it; do not try the tools.
The one rule: build here, publish from here
You do not write an environment as a script and hope. You build it in the admin thread's own sandbox with ordinary tools — execute, the file tools — and when it works you call publish_environment. That captures this sandbox as the image and writes the record only after the capture succeeded. Nothing is half-written on failure, and the environment is usable the moment the call returns.
Everything on the sandbox filesystem is captured, so provision it fully and leave no tokens, credentials, or proxy secrets on disk.
Which image to start from
The image you publish is whatever you are sitting on plus your changes, so start the admin thread on the right one:
| You want to… | Start the admin thread… | Then |
|---|---|---|
| Edit an environment | in that environment (composer → Environment picker) | change it, publish_environment under the same name |
| Fork one into a new environment | in the parent | change what differs, publish_environment under a new name |
| Build from scratch | in no environment, or sandbox_reset with the base snapshot_id |
provision everything, publish |
Already in a thread and need a different image? sandbox_reset(snapshot_id=…) with an id from list_environments, or sandbox_reset(snapshot="<prefix>-environment-<slug>:latest"). The old sandbox is detached, not deleted.
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 First seen · 60 lines · 84 tokens per session scan A cd3227088840
environments is a skill published in the GitHub repository langchain-ai/open-swe (10,688 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,227 once invoked, about $0.0004 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 2026-09-10.
Other skills, from other repositories
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
serving-llms-vllm
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.