What is surf-skill-run?

A sandboxed demo runner for a skill card. It runs one planned task in a restricted environment, decides which named websites or hosts may be reached, checks the result, and records a review.

Use it to run and verify a card’s sample task, inspect allowed or denied network hosts, and save the result for later card and video steps.

It lets you test a skill without giving the agent unrestricted access to the computer or network. Code checks and a separate AI reviewer help determine whether the demo worked.

surf-skill-run — Skill for Claude Code and Codex by eph5xx

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.

Any agent

npx skills add eph5xx/surfskills.surf --skill surf-skill-run

Clone the repo

git clone --depth 1 https://github.com/eph5xx/surfskills.surf

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/eph5xx/surfskills.surf/surf-skill-run/github.svg)](https://agentmods.dev/skills/eph5xx/surfskills.surf/surf-skill-run)

Your own site

<a href="https://agentmods.dev/skills/eph5xx/surfskills.surf/surf-skill-run"><img src="https://agentmods.dev/badge/skills/eph5xx/surfskills.surf/surf-skill-run/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/eph5xx/surfskills.surf/surf-skill-run"><img src="https://agentmods.dev/badge/skills/eph5xx/surfskills.surf/surf-skill-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,734 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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.01734
Opus 5.5	$0.00030	$0.00694
Sonnet 5.5	$0.00015	$0.00347
Haiku 4.5	$0.00007	$0.00173

Measured 3d ago against content hash eb1815463788, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

surf-skill-run 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 3d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/run-agent.mjs, scripts/run-check.mjs, scripts/run-hosts.mjs, …), 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.

.agents/skills/surf-skill-run/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 3: Run

Run the demo task from plan.json with the skill, in a locked-down agent on this Mac, and keep only the result. Then check it with code and with an AI reviewer.

Reads: plan.json, skill/, inputs/.
Writes: hosts.json (hosts.schema.json), result/, run.log, run.jsonl, review/, and last run.json (run.schema.json).

You are the run operator: one agent, one card. Scripts do the work. You decide which hosts the agent may reach, and you read only what the scripts print.

Run the scripts from this skill's folder.

What to do

Hosts (code). Run node scripts/run-hosts.mjs <card>. It lists every host named in the skill, the inputs and the prompt, and denies the ones the rules catch. hosts.md has the rules.
Decide hosts (you). If it prints pending:, decide each listed host with hosts.md, then save all decisions in one call: node scripts/run-hosts.mjs <card> --allow fonts.googleapis.com:"fonts in the theme files" --deny github.com:"only a User-Agent string in theme.mjs". Repeat until it prints ok:.
Self-test (code). Run node scripts/run-selftest.mjs. It proves the lockdown still holds; a pass is cached per agy version and agent model, so it is usually instant. Anything but ok means stop: reply blocked: with its line.
Run the agent (code). Run node scripts/run-agent.mjs <card> in the background (it takes up to 11 minutes, longer than most tool calls wait), and wait for it to finish. It sets up a fresh workspace, runs agy with the plan's prompt, answers the agent's questions through a stand-in, copies out result/, and deletes the workspace.
Check (code). Run node scripts/run-check.mjs <card>. It runs every check in plan.json done, then takes the screenshots and gathers the evidence for the review.
Review (code + AI). Run node scripts/run-review.mjs <card>. An AI reviewer judges the result on four criteria (review.md) and the script writes run.json only if the review passes.

Read the full file on GitHub · 76 lines

Files

What ships with it

15 files 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.

3d ago Changed · +1 lines eb1815463788
5d ago First seen · 75 lines · 75 tokens per session scan A 796223e3423c

Subscribe to this mod's changes

surf-skill-run is a skill published in the GitHub repository eph5xx/surfskills.surf (2 stars, last pushed 4d ago), licensed MIT. It adds 75 tokens to every session and 1,734 once invoked, about $0.0003 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 2026-10-31.

Security Testing agent-skills ai-skills claude-skills directory

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens

playwright-frontend

For frontend engineers authoring UI — how to make components reliably locatable by tests and AI agents. Covers the official Playwright locator priority, semantic/accessible markup first, and how to add valid, unique, stable data-testid attributes (naming convention, uniqueness in lists, stability rules) for React…

testdino-hq/playwright-skill · 92 tokens

playwright-qa

QA engineering workflows on top of Playwright. Use when a QA engineer asks to design test cases from a ticket, PRD or acceptance criteria, decide what to automate, write a bug report from a failing test or trace, convert manual test cases (TestRail, Xray, CSV) into Playwright specs with case-ID traceability, or review…

testdino-hq/playwright-skill · 83 tokens

synthetic-test-data-generator

Generate fictional, reproducible test datasets and labeled valid, boundary, missing, malformed, and relationship cases from a schema, test goals, or the instructions and resources of another AI skill. Use for fixtures, mocks, demos, and validation tests, not for anonymizing production data or claiming statistical or…

mickpletcher/AI-Skills · 68 tokens

fictional-ticket-router

Classify fictional support tickets for a local test.

mickpletcher/AI-Skills · 15 tokens

mirrord-db-branching

Helps users configure mirrord.json for database branching, enabling isolated database copies for safe development and testing. Use when the user wants to set up MySQL, MariaDB, PostgreSQL, MSSQL, MongoDB, Redis, DynamoDB, ClickHouse, Google Spanner, Amazon S3, or generic branches, configure copy modes, connection…

aiskillstore/marketplace · 91 tokens