Borrowing it
Nothing to install: this file belongs to ai-ecoverse/slicc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-ecoverse/slicc/main/.agents/skills/cdp-smoke-test/SKILL.mdgit clone --depth 1 https://github.com/ai-ecoverse/sliccWrote 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/ai-ecoverse/slicc/cdp-smoke-test)<a href="https://agentmods.dev/skills/ai-ecoverse/slicc/cdp-smoke-test"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/cdp-smoke-test/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.
<a href="https://agentmods.dev/skills/ai-ecoverse/slicc/cdp-smoke-test"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/cdp-smoke-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 65 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 45 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 66 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00180 | $0.02399 |
| Opus 5 | $0.00090 | $0.01200 |
| Sonnet 5 | $0.00036 | $0.00480 |
| Haiku 4.5 | $0.00018 | $0.00240 |
Grade A, and why
cdp-smoke-test 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CDP Smoke Test
Boot the standalone harness with the latest local build, attach over CDP,
and work through the two test tiers. Manual local-harness driving goes through
scripts/slicc-cdp (zero-dependency, Node 22+).
Setup
Production safety boundary: :5710 (bridge) and :9222 (Chrome CDP)
belong to the developer's production SLICC. Never bind, reap, or kill either
port. The smoke-test lane uses bridge :5715; its Chrome CDP port is
auto-resolved.
Default mode — hosted origin (recommended)
Chrome opens https://www.sliccy.ai with a ?bridge=ws://localhost:5715/cdp
parameter that routes it back to the local node-server. No wrangler needed.
OAuth, IMS (Adobe), and all provider relays work out of the box because they
are hosted on the production origin.
Important: in this mode the browser loads the deployed production webapp from
sliccy.ai, not your local checkout. Changes topackages/webapp/are not exercised. Use this mode for: smoke-testing the node-server bridge, provider login flows, tray and scoops features, and CDP automation. Use the local-wrangler mode below when you need to verify a webapp change end-to-end before deploying.
# 1. Record production listeners before doing anything else.
PROD_BRIDGE_PIDS=$(lsof -nP -tiTCP:5710 -sTCP:LISTEN 2>/dev/null | sort -n | paste -sd, -)
PROD_CDP_PIDS=$(lsof -nP -tiTCP:9222 -sTCP:LISTEN 2>/dev/null | sort -n | paste -sd, -)
printf 'production preflight: :5710=%s :9222=%s\n' "${PROD_BRIDGE_PIDS:-none}" "${PROD_CDP_PIDS:-none}"
# 2. Build only node-server (no webapp build required — UI loads from sliccy.ai).
npm install
npm run build -w @slicc/node-server
# 3. Launch — hosted origin, isolated bridge :5715, ephemeral profile.
# CHROME_PATH is optional; default is a labeled Chrome for Testing clone.
export SLICC_HARNESS_LOG=/tmp/slicc-dev-harness-5715.log
CHROME_PATH="/Applications/Google Chrome Canary.app" \
PORT=5715 \
nohup npm run dev:standalone:fresh > "$SLICC_HARNESS_LOG" 2>&1 &
# 4. Wait for boot and export the auto-resolved CDP port from this lane's log.
sleep 20 && grep "Chrome CDP listening" "$SLICC_HARNESS_LOG"
export SLICC_CDP_PORT=$(sed -nE 's/.*Chrome CDP listening on port ([0-9]+).*/\1/p' "$SLICC_HARNESS_LOG" | tail -1)
test -n "$SLICC_CDP_PORT"
.agents/skills/cdp-smoke-test/scripts/slicc-cdp targets
# 5. Pass criterion: production listeners are exactly the preflight PIDs.
POST_BRIDGE_PIDS=$(lsof -nP -tiTCP:5710 -sTCP:LISTEN 2>/dev/null | sort -n | paste -sd, -)
POST_CDP_PIDS=$(lsof -nP -tiTCP:9222 -sTCP:LISTEN 2>/dev/null | sort -n | paste -sd, -)
test "$POST_BRIDGE_PIDS" = "$PROD_BRIDGE_PIDS" && test "$POST_CDP_PIDS" = "$PROD_CDP_PIDS"
What ships with it
4 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.
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.
- yesterday Changed · +47 lines afcd80a0e37e
- 5d ago First seen · 140 lines · 180 tokens per session scan A 79d976b2416c
cdp-smoke-test is a skill published in the GitHub repository ai-ecoverse/slicc (30 stars, last pushed today), licensed Apache-2.0. It adds 180 tokens to every session and 2,399 once invoked, about $0.0009 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 2026-09-05.
Other skills, from other repositories
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
browser-viz-verify
Verifies that a NetClaw-generated visualization HTML file (three.js, canvas, drawio, UML, markmap) actually renders correctly — screenshot, console-error check, and an optional Lighthouse audit. Use immediately after generating any browser-based visualization output, to close the QA gap that otherwise requires a human…
BrowserBash Browser Automation
BrowserBash is a vendor-independent, natural-language browser automation CLI. Drive a real browser from plain-English objectives or committable Markdown tests, run on local Chrome, CDP/Playwright MCP, Browserbase, LambdaTest, or BrowserStack, and stream NDJSON results with CI exit codes — using free local Ollama…
Geb Testing
Browser automation testing with Geb framework for Groovy/JVM using jQuery-like content DSL, Page Object pattern, Spock integration, and WebDriver abstraction.
playwright-cli
Use when a task needs Playwright-backed browser automation from the shell: open or attach to browser sessions, inspect snapshots and element refs, click/type/fill forms, debug Playwright tests, inspect console/network/storage, run Playwright snippets, capture screenshots/traces/videos, or generate reliable test code.…
ui-automation
A tool for managing browser-based tests in the WHartTest testing platform, including pages, page elements, steps, and test cases.