local-workspace-server

local-workspace-server is a skill for Claude Code, Codex from sonichi/sutando. It costs 57 tokens per session (321 once invoked), scanned A, original, MIT.

A hardened local web server for showing presentation files in a browser on the same computer.

In plain words
What is it for?
Use it to load a local presentation in a development panel through a temporary capability URL, with only GET and HEAD requests allowed.
Why use it?
It limits access to one directory and adds checks against unauthorized requests, path traversal, unsafe browser behavior, and expired links. It serves files read-only.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sonichi/sutando/local-workspace-server
Any agent
npx skills add sonichi/sutando --skill local-workspace-server
Clone the repo
git clone --depth 1 https://github.com/sonichi/sutando

Made for: Claude Code, Codex.

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 local-workspace-server

README.md
[![agentmods](https://agentmods.dev/badge/skills/sonichi/sutando/local-workspace-server.svg)](https://agentmods.dev/skills/sonichi/sutando/local-workspace-server)
Your own site
<a href="https://agentmods.dev/skills/sonichi/sutando/local-workspace-server"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/local-workspace-server.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 321 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00321
Opus 5 $0.00028 $0.00161
Sonnet 5 $0.00011 $0.00064
Haiku 4.5 $0.00006 $0.00032

Measured 5d ago against content hash 57f3e12468f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

local-workspace-server 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/serve.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/local-workspace-server/SKILL.md · 27 lines

What it actually says

Local workspace server

Serves ONE directory, read-only, to the trusted Presentation panel's dev mode. Loopback binding is not treated as trust: the owner's hardening checklist (2026-08-26) is the spec, and every guard is pinned in tests/local-workspace-server.test.py over real HTTP.

python3 skills/local-workspace-server/scripts/serve.py --root <deck-dir> [--port 8899] [--ttl 3600]

Prints a capability URL (http://127.0.0.1:<port>/<token>/). Paste it into the panel's device-local dev override — it never goes into room state (logical local_workspace descriptors only; see the Presentation protocol thread).

Guards: 127.0.0.1 bind only · random capability path segment (constant-time compare) · TTL expiry → 403 · GET/HEAD only, anything else 405 · no directory listing · traversal-safe resolve containment · explicit MIME + nosniff · sandbox allow-scripts CSP on HTML · Host header must be loopback (DNS- rebinding defense, computed from the BOUND port) · no-store caching · stdout logging only.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 27 lines · 57 tokens per session scan A 57f3e12468f9

Subscribe to this mod's changes

local-workspace-server is a skill published in the GitHub repository sonichi/sutando (391 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 321 once invoked, about $0.0003 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.