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 skills add shiaho777/turn-mcp --skill turn-mcp-webgit clone --depth 1 https://github.com/shiaho777/turn-mcpWrote 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/shiaho777/turn-mcp/turn-mcp-web)<a href="https://agentmods.dev/skills/shiaho777/turn-mcp/turn-mcp-web"><img src="https://agentmods.dev/badge/skills/shiaho777/turn-mcp/turn-mcp-web/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/shiaho777/turn-mcp/turn-mcp-web"><img src="https://agentmods.dev/badge/skills/shiaho777/turn-mcp/turn-mcp-web.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00064 | $0.00553 |
| Opus 5 | $0.00032 | $0.00277 |
| Sonnet 5 | $0.00013 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
turn-mcp-web 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn MCP Web
Use this skill to keep one agent run alive while a human replies in the Turn MCP browser console.
Verify Tool Access
Check whether turn.wait, turn_wait, or turn is available before first use.
If none of them exist, say that clearly and do not pretend the checkpoint loop is active.
Send Checkpoints Through Turn MCP
Call turn.wait whenever you need:
- approval before a consequential action
- missing information that blocks the next step
- a branch decision with a small, known option set
- a human handoff after finishing a meaningful step
Do not answer the human directly when the next reply should stay inside the same agent run.
Call Contract
turn.wait(
context="What you finished, what you found, and what happens next.",
question="The exact decision or information you need.",
options=["Proceed", "Revise", "Stop"],
agentName="ReleaseAgent"
)
contextis required. Write it for a cold reader.questionshould ask one concrete thing.optionsshould be used when the branch set is known.agentNameshould stay stable within the workflow.
Write for Cold Reads
Every wait message should let a human understand the situation without scrolling through prior logs.
- Summarize completed work.
- State the current blocker or decision.
- State the next action that follows each answer.
- Prefer short option buttons over free-form typing when possible.
Keep the Loop Alive
Follow this loop:
- Work until a human checkpoint exists.
- Call
turn.wait. - Resume from the returned reply.
- Call
turn.waitagain at the next meaningful checkpoint.
The human ends the session. Do not end it on your own while the task is still active.
Immediate Behavior
After loading this skill:
- Confirm that
turn.waitis available. - If the user has not already given a concrete task, call
turn.waitimmediately, say that you are ready, and ask what they want done. - If the user already gave a task, start work and call
turn.waitat the first real checkpoint.
What ships with it
2 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.
- 12d ago First seen · 72 lines · 64 tokens per session scan A a43fed627136
turn-mcp-web is a skill published in the GitHub repository shiaho777/turn-mcp (28 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 553 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
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
component-creation
Step-by-step workflow for creating accessible, tested UI components. Use when the user asks to create a new UI component.
audit-payment-system
Read-only audit for payment/money-movement systems, scope-gated so a Stripe-Checkout site and an in-house ledger each see only relevant findings. Use when "audit payment system", "double charge / idempotency", "ledger / reconciliation", "webhook / 3DS / PCI". Mobile IAP → audit-monetization-iap.
enhance-web-web3d
Add purposeful 3D/WebGL and scroll choreography to an existing site with Three.js/R3F, GSAP, or Motion. Use when "add 3D", "WebGL hero", "React Three Fiber", or "scroll-driven 3D". General UI polish → enhance-web-ui. Motion without 3D → enhance-motion.
mobile-rn-screen
Polish an existing React Native screen to feel intentional, native, and human-crafted. Use for "this screen looks off", "feels clunky on iOS", "Android version looks wrong", "jank when scrolling", "button is unreachable", or any RN-specific UX polish pass.