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/langchain-ai/open-swe/claude-mdgit clone --depth 1 https://github.com/langchain-ai/open-sweWhat 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 | $0.02954 | $0.02954 |
| Opus 5 | $0.01477 | $0.01477 |
| Sonnet 5 | $0.00591 | $0.00591 |
| Haiku 4.5 | $0.00295 | $0.00295 |
Grade A, and why
open-swe 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 yesterday.
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.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project
Open SWE is an open-source coding-agent framework built on LangGraph + Deep Agents (deepagents.create_deep_agent). It runs as a LangGraph app: each thread spawns its own isolated cloud sandbox, and the agent is invoked from Slack, Linear, or GitHub (PR comments, plus auto-review on opened / ready-for-review).
A separate reviewer graph runs read-only code reviews on PRs, and a review-style analyzer graph learns per-repo review style from historical PRs.
Commands
Dependencies are managed with uv. Tests use pytest (asyncio_mode = "auto"). Lint/format is ruff (line-length 100, target py311). Type checking is basedpyright (typeCheckingMode = "standard"). requires-python = ">=3.11"; langgraph.json pins the runtime to 3.12.
make install # uv sync --extra dev (pytest, ruff, …)
make dev # uv run langgraph dev — serves all three graphs + the FastAPI app from langgraph.json
make run # uvicorn agent.webapp:app --reload --port 8000 (FastAPI only, no LangGraph runtime)
make test # uv run pytest -vvv tests/
make test TEST_FILE=tests/github/test_open_pull_request.py # single test file
uv run pytest -vvv tests/github/test_open_pull_request.py::test_name # single test
make lint # ruff check + ruff format --diff
make format # ruff format + ruff check --fix
make typecheck # basedpyright agent tests
langgraph.json declares three graph entrypoints and the FastAPI app, all served together by langgraph dev:
| Graph | Entrypoint | Purpose |
|---|---|---|
agent |
agent.server:traced_agent (wraps get_agent) |
Main coding agent (Slack/Linear/GitHub-triggered). |
reviewer |
agent.reviewer:traced_reviewer_agent (wraps get_reviewer_agent) |
Read-only PR reviewer. Findings model + publish_review. |
analyzer |
agent.analyzer:traced_analyzer (wraps get_analyzer) |
Learns per-repo reviewer style from historical PRs and this reviewer's own finding outcomes. |
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.
- yesterday First seen · 127 lines · 2,954 tokens per session scan A ffd2a8f5decc
open-swe CLAUDE.md is an instructions file published in the GitHub repository langchain-ai/open-swe (10,633 stars, last pushed 2d ago), licensed MIT. It adds 2,954 tokens to every session, about $0.0148 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
LangBot AGENTS.md
Instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
awesome-ChatGPT-repositories CLAUDE.md
Instructions for taishi-i/awesome-ChatGPT-repositories, covering awesome-chatgpt-repositories — claude code guide, repository structure, plugin skill (when installed via /plugin), local standalone command (when repo is cloned) and compact data format (plugins/awesome-chatgpt-search/data/).
dify AGENTS.md
AGENTS.md instructions for langgenius/dify, covering agents.md and repository gotchas.
dify CLAUDE.md
Claude Code instructions for langgenius/dify, a project described as: Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
flock AGENTS.md
Instructions for Onelevenvy/flock, covering agents.md, project overview, build & development commands, rust backend and build the cli.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.