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 ising-tech/isingq-toolkit --skill install-isingq-mcpgit clone --depth 1 https://github.com/ising-tech/isingq-toolkitWrote 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/ising-tech/isingq-toolkit/install-isingq-mcp)<a href="https://agentmods.dev/skills/ising-tech/isingq-toolkit/install-isingq-mcp"><img src="https://agentmods.dev/badge/skills/ising-tech/isingq-toolkit/install-isingq-mcp/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/ising-tech/isingq-toolkit/install-isingq-mcp"><img src="https://agentmods.dev/badge/skills/ising-tech/isingq-toolkit/install-isingq-mcp.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 | $0.00049 | $0.02089 |
| Opus 5.5 | $0.00020 | $0.00836 |
| Sonnet 5.5 | $0.00010 | $0.00418 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
install-isingq-mcp 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install IsingQ MCP
中文版本：SKILL.zh-CN.md
Outcome
Make IsingQ available in the one Agent Host named by the user. Select exactly one distribution path, configure a personal API Key through private local input, verify native tools inside that Host, report the observed version and stop.
Host-specific config boundaries and fallbacks are in HOSTS.md. Read only the section for the selected Host.
Non-negotiable boundaries
- Never receive an IsingQ API Key in chat, command arguments, environment variables, logs, Host config, or Agent-visible output.
- A Headless deployment administrator may preconfigure
ISINGQ_API_KEYbefore the Agent starts. Treat it only as an already-configured runtime source; never inspect, set, copy, or echo it. - If the user has no Key, direct them to
https://console.isingq.com/and Settings → API → Create API. Never register, read, copy, or expose it for them. - Ask before opening the operating system's private API Key prompt. Use
force=trueonly when the user explicitly asks to replace an existing Key. - Configure only the Host from the current request. Do not detect installed apps and configure all of them.
- Never bypass a Host sandbox or move credentials into a project directory. Request access only to the exact user install, private config, and selected Host config locations required by the chosen path.
- Use only the official npm organization and
https://github.com/ising-tech/isingq-toolkitas distribution origins. - Do not submit a real solve as an installation test. A hand-written NDJSON call proves process reachability, not Host integration.
isingq_solve_startsubmits immediately after the Host permits it. Before calling it, the Agent must show the model summary and matrix SHA-256 and obtain explicit user confirmation.
Choose one distribution path
Preserve an already working distribution when updating. Switch paths only when the user requests it or the existing path is unavailable.
What ships with it
5 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.
- 1mo ago First seen · 136 lines · 49 tokens per session scan A 89819a9d3424
install-isingq-mcp is a skill published in the GitHub repository ising-tech/isingq-toolkit (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,089 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
use-404-directory
Preflight a specific Polymarket observation or contemplated Yes/No action for settlement, timing, liquidity, slippage, geoblock, and execution risk; also assess an unfamiliar third-party Agent tool before installation or first use. Use when an exact Polymarket market reference or actual external-tool action is…
xcatcher
Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl…
mcp-gateway
Use when discovering or calling downstream tools through MCP Gateway without loading every tool schema.
cowork-review
Worker-prompt lifecycle and the Architect/Analyst review gates — prompt frontmatter (status, reviewround, outputstatus), the draft→in-review→approved loop, the append-only review logs, the output gate (review-output → promote), and the tasks/{todo,run,done} transitions. Use when drafting, reviewing, or executing a…
onboarding
Onboard a code project into RoadBoard — analyze the cloned repo and populate RoadBoard (project, phase, tasks, memory and the architecture graph / Atlas) via the RoadBoard MCP tools, then render the per-repo CLAUDE.md. Use when the user asks to onboard a project, or when a project that has a repo is not yet onboarded…
archive-artifact
Persist a substantive agent deliverable (audit report, analysis, design note, generated-asset reference, handoff) into RoadBoard as a memory entry via the MCP tools, with a standard envelope. Use whenever you produce an output worth keeping beyond the chat.