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 skills/sonichi/sutando/local-workspace-servernpx skills add sonichi/sutando --skill local-workspace-servergit clone --depth 1 https://github.com/sonichi/sutandoWrote 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.
[](https://agentmods.dev/skills/sonichi/sutando/local-workspace-server)<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>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 | $0.00057 | $0.00321 |
| Opus 5 | $0.00028 | $0.00161 |
| Sonnet 5 | $0.00011 | $0.00064 |
| Haiku 4.5 | $0.00006 | $0.00032 |
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.
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.
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.
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.
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.
- 5d ago First seen · 27 lines · 57 tokens per session scan A 57f3e12468f9
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.
Other skills, from other repositories
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
app-builder
Build and edit small, personal visual tools and artifacts — dashboards, trackers, calculators, data visualizations, charts, simple landing pages, and slide decks the user wants for THEMSELVES. This is the right skill whenever the user asks to "visualize this," "make a chart," or "build an artifact" for their own use…
contacts
Manage contacts, communication channels, access control, and invite links.
assistant-migration
Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Vellum by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Vellum…
guardian-verify-setup
Set up channel verification for phone, Telegram, Slack, Discord, or email channels via outbound verification flow.
schedule
Reminders, automations, and recurring page, dashboard, or status monitoring (cron, RRULE, or fire-at).