open-swe: Skill for Claude Code

.claude/skills/dashboard-preview/SKILL.md

dashboard-preview is a skill for Claude Code from langchain-ai/open-swe. It costs 55 tokens per session (924 once invoked), scanned A, original, MIT.

A workflow for running this checkout's dashboard in a browser against a shared preview deployment, with real threads and no local backend. It also supports checking page requests and comparing behaviour before and after a change.

In plain words
What is it for?
Use it to start the dashboard, inspect it in a browser, count its requests, and compare UI behaviour across changes.
Why use it?
It lets you verify frontend changes using realistic preview data without setting up the backend locally or using production.

Skill for Claude Code ✓ vendor

Written for Claude Code: installed under .claude/.

This is langchain-ai/open-swe's own configuration. It tells Claude Code how to work on open-swe itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-swe configures →

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/dashboard-preview/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.

agentmods badge for dashboard-preview

README.md
[![agentmods](https://agentmods.dev/badge/skills/langchain-ai/open-swe/dashboard-preview/github.svg)](https://agentmods.dev/skills/langchain-ai/open-swe/dashboard-preview)
Your own site
<a href="https://agentmods.dev/skills/langchain-ai/open-swe/dashboard-preview"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/dashboard-preview/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.

agentmods 80×15 button for dashboard-preview

Your own site · 80×15
<a href="https://agentmods.dev/skills/langchain-ai/open-swe/dashboard-preview"><img src="https://agentmods.dev/badge/skills/langchain-ai/open-swe/dashboard-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00924
Opus 5.5 $0.00022 $0.00370
Sonnet 5.5 $0.00011 $0.00185
Haiku 4.5 $0.00006 $0.00092

Measured yesterday against content hash f58668e90282, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dashboard-preview 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.

.claude/skills/dashboard-preview/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dashboard against preview

pnpm run dev:prod serves this checkout's ui/ from Vite and proxies the API to a deployment with a real session, so every page shows real threads. Point it at preview, never production:

DASHBOARD_API_URL=https://open-swe-preview-cc53e8fbe667565d843d0843f84ee92c.us.langgraph.app pnpm run dev:prod

The first run opens the user's browser for a GitHub handoff. When they are signed in to GitHub it completes on its own, and the session is cached in ~/.cache/open-swe/dev-session.json for a week. If pnpm fails with No version is set for shim: pnpm, run it as mise exec pnpm@<version> -- pnpm run dev:prod, taking the version from packageManager in package.json.

Browser pane

The in-app Browser pane needs a launch configuration that starts the server; one that only names a URL is refused. Write .claude/launch.json (leave it uncommitted), then preview_start dashboard-preview:

{
  "version": "0.0.1",
  "configurations": [
    {
      "name": "dashboard-preview",
      "runtimeExecutable": "pnpm",
      "runtimeArgs": ["run", "dev:prod"],
      "env": { "DASHBOARD_API_URL": "https://open-swe-preview-cc53e8fbe667565d843d0843f84ee92c.us.langgraph.app" },
      "port": 3000
    }
  ]
}

Vite holds port 3000 strictly: stop any dev:prod you started from Bash first. The ego-browser skill works too, and it carries the user's real login for both preview and production.

The session is real

Reading is free. A message sent from the composer starts a real run, and opening a pull request's review page creates its chat thread. Ask the user before either.

Finding a thread to test on

Only threads with transcript: "v2" read the transcript log; older ones answer /transcript with 404 and go through the SDK stream. Rank candidates by size from the page:

const { items } = await (await fetch("/dashboard/api/threads/page?limit=40")).json()
for (const t of items.filter((t) => t.transcript === "v2")) {
  const s = await (await fetch(`/dashboard/api/threads/${t.id}/transcript`)).json()
  console.log(t.id, t.status, s.tool_calls.length, t.title)
}

Read the full file on GitHub · 90 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.

  1. yesterday Changed · -8 lines f58668e90282
  2. 3d ago First seen · 98 lines · 55 tokens per session scan A 0398ce185c12

Subscribe to this mod's changes

dashboard-preview is a skill published in the GitHub repository langchain-ai/open-swe (11,133 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 924 once invoked, about $0.0002 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 2026-10-26.