What is local-gh-dev?

A local-development workflow for running the Open SWE dashboard with real GitHub data through the GitHub CLI, a command-line tool for GitHub.

Use it to run the dashboard locally, test changes against real pull requests, reproduce a screenshot issue, or fix local sign-in problems.

It lets local development use the developer's existing GitHub sign-in instead of requiring a separate GitHub App setup, while documenting ports, access limits, and required settings.

How langchain-ai/open-swe configures Claude Code

About the project

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.

langchain-ai/open-swe · 11,133 stars · on GitHub · langchain.com

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/langchain-ai/open-swe/main/.claude/skills/local-gh-dev/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/langchain-ai/open-swe

Made for: Claude Code.

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/skills/langchain-ai/open-swe/local-gh-dev/github.svg)](https://agentmods.dev/skills/langchain-ai/open-swe/local-gh-dev)

Your own site

<a href="https://agentmods.dev/skills/langchain-ai/open-swe/local-gh-dev"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/local-gh-dev/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/langchain-ai/open-swe/local-gh-dev"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/local-gh-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,841 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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 5.1	$0.00072	$0.01841
Opus 5.5	$0.00029	$0.00736
Sonnet 5.5	$0.00014	$0.00368
Haiku 4.5	$0.00007	$0.00184

Measured yesterday against content hash f84fed69cf4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-gh-dev scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sS -c /tmp/osw.txt -o /dev/null 'http://127.0.0.1:2026/dashboard/api/auth/dev-login?redirect_to=/review'

.claude/skills/local-gh-dev/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local dashboard on real GitHub data

The dashboard's per-user reads — the PR list, one PR's details, a PR preview — run on the signed-in person's own OAuth token. gh already holds one, so local development needs no GitHub App: /dashboard/api/auth/dev-login turns gh's credentials into a session. It is refused unless langgraph dev is the runtime, and the ALLOWED_GITHUB_USERS gate still applies.

Start it

Confirm gh is logged in. gh auth status — if not, gh auth login.
Check the ports. The backend wants 2024 and Vite wants 3000:
```
lsof -nP -iTCP:3000,2024 -sTCP:LISTEN
```
Other worktrees run their own backends and E2E harnesses on 2024. Never kill one without asking. Use another port instead and point Vite at it — every command below takes PORT for exactly that reason.

Make sure .env has these. The GitHub App keys are not needed; these are:

Key	Why
`DASHBOARD_JWT_SECRET`	signs the session; any random string
`ALLOWED_GITHUB_USERS`	your `gh api user --jq .login`
`POSTGRES_URI`	skips the container step when one is already up
`DASHBOARD_BASE_URL`	`http://localhost:3000`
`DASHBOARD_API_BASE_URL`	`http://localhost:3000`

Startup aborts with ALLOWED_GITHUB_ORGS or ALLOWED_GITHUB_USERS must be configured when the allowlist is missing.

Start the backend. make dev covers this when 2024 is free and you want its postgres container; otherwise run it directly:
```
uv run langgraph dev --no-browser --port 2026 --n-jobs-per-worker 10
```

Start Vite against it:

DASHBOARD_API_URL=http://127.0.0.1:2026 pnpm run dev

Open http://localhost:3000 and press Continue with GitHub. With no App configured it redirects to the gh login and lands you signed in. To skip the page, go straight to /dashboard/api/auth/dev-login?redirect_to=/agents/reviews.

Postgres

make dev starts an open-swe-postgres container unless POSTGRES_URI is set, and fails with a name conflict when another worktree already started one. Reuse it:

Read the full file on GitHub · 148 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.

yesterday Changed · -16 lines f84fed69cf4c
21d ago Changed 0f963c20a151
1mo ago Changed · +58 lines f9911885d8da
1mo ago First seen · 106 lines · 72 tokens per session scan A 528a9ded4b77

Subscribe to this mod's changes

local-gh-dev is a skill published in the GitHub repository langchain-ai/open-swe (11,133 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,841 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.

Cloud DevOps and cloud LLM agent ai anthropic claudecode openai

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…

langbot-app/LangBot · 104 tokens

litellm-setup

Set up a self-hosted LiteLLM proxy, the OpenAI-compatible LLM gateway, on this machine, from install through provider keys, config.yaml, a master key, optional Postgres and Admin UI, and a verified chat completion. Use when the user asks to set up LiteLLM, install the LiteLLM proxy, self-host an LLM gateway, or put…

BerriAI/litellm · 120 tokens

open-swe: Skill for Claude Code