What is run-local-freestyle?

A local-development guide for running Studio with chats and task runs inside real Freestyle sandboxes. It explains how to expose the local app through an ngrok public tunnel and configure Studio and its browser.

Use it to run Studio locally, test coding-agent chats end to end, and try daemon or harness-runner changes in a real sandbox.

It removes setup uncertainty when testing sandbox or harness changes locally, including the requirement that the browser and app use the same public address.

How decocms/studio configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to decocms/studio. 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/decocms/studio/main/.claude/skills/run-local-freestyle/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/decocms/studio

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/decocms/studio/run-local-freestyle/github.svg)](https://agentmods.dev/skills/decocms/studio/run-local-freestyle)

Your own site

<a href="https://agentmods.dev/skills/decocms/studio/run-local-freestyle"><img src="https://agentmods.dev/badge/skills/decocms/studio/run-local-freestyle/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/decocms/studio/run-local-freestyle"><img src="https://agentmods.dev/badge/skills/decocms/studio/run-local-freestyle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,379 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	$0.00071	$0.01379
Opus 5.5	$0.00028	$0.00552
Sonnet 5.5	$0.00014	$0.00276
Haiku 4.5	$0.00007	$0.00138

Measured 10d ago against content hash 23ce98d9732f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

run-local-freestyle 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 10d ago.

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.

URL=$(curl -s localhost:4040/api/tunnels | grep -o '"public_url":"https[^"]*' | cut -d'"' -f4)

.claude/skills/run-local-freestyle/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Studio locally on Freestyle

Freestyle VMs call back into Studio (the studio MCP, org-fs), so a local Studio needs a public URL. The browser must use that same URL: auth trusts only BASE_URL.

Prerequisites

FREESTYLE_API_KEY in the repo-root .env.
ngrok with an auth token (ngrok config add-authtoken <token>).
Docker with buildx and Go, only if you changed packages/sandbox/daemon-go or packages/harness-runner.

1. Tunnel

ngrok http 4000
URL=$(curl -s localhost:4040/api/tunnels | grep -o '"public_url":"https[^"]*' | cut -d'"' -f4)

Use ngrok. Do not use a cloudflared quick tunnel: it buffers server-sent events until the stream closes, so chat output never streams and queued messages look stuck.
Point the tunnel at Vite (4000), not the API (3000). Vite proxies /api.

2. Start Studio

KUBECONFIG=/dev/null \
STUDIO_AGENT_SANDBOX_ENABLED=true \
STUDIO_SANDBOX_FREESTYLE_SHARE=1 \
STUDIO_PUBLIC_URL=$URL MESH_PUBLIC_URL=$URL \
__VITE_ADDITIONAL_SERVER_ALLOWED_HOSTS=.ngrok-free.app \
bun run dev --base-url $URL --no-tui

Always set KUBECONFIG=/dev/null. Without it the Kubernetes provider is built from your default context, and a Freestyle fallback could provision there.
Always override STUDIO_PUBLIC_URL and MESH_PUBLIC_URL. A stale value in .env wins over BASE_URL for minted MCP URLs, and runs fail with studio MCP is unusable.
Open $URL in the browser and log in there, not on localhost. Click through ngrok's one-time warning page.
If you change the tunnel URL, restart Studio with the new one.

3. Sandbox image (only for daemon or runner changes)

Freestyle runs ghcr.io/decocms/studio/studio-sandbox-go:<packages/sandbox version> by default. To run local daemon or runner code, overlay it on that image:

O=$(mktemp -d); mkdir $O/runner
(cd packages/sandbox/daemon-go && CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -trimpath -ldflags="-s -w" -o $O/daemon-go .)
cp packages/harness-runner/package.json $O/runner/
for f in packages/harness-runner/*.ts; do [[ $f == *.test.ts ]] || cp "$f" $O/runner/; done
cat > $O/Dockerfile <<'EOF'
FROM ghcr.io/decocms/studio/studio-sandbox-go:<version>
COPY --chown=sandbox:sandbox daemon-go /opt/sandbox-daemon/daemon-go
COPY --chown=sandbox:sandbox --chmod=755 runner/ /usr/local/lib/node_modules/@decocms/harness-runner/
EOF
TAG=ttl.sh/studio-sandbox-$(uuidgen | tr A-Z a-z | cut -c1-12):24h
docker buildx build --platform linux/amd64 -t $TAG --load $O && docker push $TAG

Read the full file on GitHub · 94 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.

10d ago Changed · +1 lines 23ce98d9732f
18d ago Changed ddcae48a1c69
29d ago First seen · 93 lines · 71 tokens per session scan A 16799b89af67

Subscribe to this mod's changes

run-local-freestyle is a skill published in the GitHub repository decocms/studio (415 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,379 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 2026-10-09.

Cloud DevOps and cloud LLM agents ai deco mcp mcp-client

run-local-freestyle next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
run-local-freestyledecocms/studio	Skill	415	yesterday	MIT	A	71	Claude Code
routineSnowflake-Labs/cocoplus	Skill	727	2d ago	MIT	A	44	Claude Code, Codex
devyonatangross/orchestkit	Skill	299	yesterday	MIT	A	45	Claude Code
aws-strands-agents-agentcoresammcj/agentic-coding	Skill	168	2d ago	Apache-2.0	A	55	Claude Code, Codex
private-software-distributionsammcj/agentic-coding	Skill	168	2d ago	Apache-2.0	A	34	Claude Code, Codex
aws-cdkAdamBien/airails	Skill	62	yesterday	MIT	A	210	Claude Code, Codex
tailscalejmagar/claude-homelab	Skill	87	1mo ago	MIT	A	93	Claude Code

studio: Skill for Claude Code