Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zebbern/agent-collab/plugin install cursorWrote 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/zebbern/agent-collab/cursor-cli-runtime)<a href="https://agentmods.dev/skills/zebbern/agent-collab/cursor-cli-runtime"><img src="https://agentmods.dev/badge/skills/zebbern/agent-collab/cursor-cli-runtime/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/zebbern/agent-collab/cursor-cli-runtime"><img src="https://agentmods.dev/badge/skills/zebbern/agent-collab/cursor-cli-runtime.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 | $0.00017 | $0.00774 |
| Opus 5.5 | $0.00007 | $0.00310 |
| Sonnet 5.5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
cursor-cli-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Cursor Runtime
Use this skill only inside the cursor:cursor-rescue subagent.
Primary helper:
node "${CLAUDE_PLUGIN_ROOT}/scripts/cursor-companion.mjs" task "<raw arguments>"
Execution rules:
- The rescue subagent is a forwarder, not an orchestrator. Its only job is to invoke
taskonce and return that stdout unchanged. - Prefer the helper over hand-rolled
git, directcursor-agentCLI strings, or any other Bash activity. - Do not call
setup,review,adversarial-review,status,result, orcancelfromcursor:cursor-rescue. - Use
taskfor every rescue request, including diagnosis, planning, research, and explicit fix requests. - You may use the
cursor-promptingskill to rewrite the user's request into a tighter Cursor prompt before the singletaskcall. - That prompt drafting is the only Claude-side work allowed. Do not inspect the repo, solve the task yourself, or add independent analysis outside the forwarded prompt text.
- Leave the model unset by default (Cursor routes
autoserver-side). Add--modelonly when the user explicitly asks for one, and pass the name through unchanged. - If the forwarded request names a task profile (
--profile deepor--profile fast), pass--profile <name>through totaskunchanged and strip it from the task text, mirroring how--modelis handled. An explicit--modeloverrides the profile's model — pass both through and lettaskresolve which wins. - There is no
--effortflag: Cursor encodes depth in model names (for examplegpt-5.3-codex-high,claude-opus-5-thinking-high) or in thedeep/fasttask profiles. If the user asks for more or less depth, choose via--modelor--profile, not an effort flag. - Default to a write-capable Cursor run by adding
--writeunless the user explicitly asks for read-only behavior or only wants review, diagnosis, or research without edits.
Command selection:
- Use exactly one
taskinvocation per rescue handoff. - If the forwarded request includes
--backgroundor--wait, treat that as Claude-side execution control only. Strip it before callingtask, and do not treat it as part of the natural-language task text. - If the forwarded request includes
--model <name>, pass it through totaskand strip it from the task text. - If the forwarded request includes
--profile <deep|fast>, pass it through totaskand strip it from the task text. - If the forwarded request includes
--resume <chat-id>, pass it through totaskand strip it from the task text. Cursor resume always needs the explicit chat id — there is no resume-last shortcut. - Without
--resume, every rescue is a fresh Cursor session.
Safety rules:
- Default to write-capable Cursor work in
cursor:cursor-rescueunless the user explicitly asks for read-only behavior. - Preserve the user's task text as-is apart from stripping routing flags.
- Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
- Return the stdout of the
taskcommand exactly as-is. - If the Bash call fails or Cursor cannot be invoked, return nothing.
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 · 40 lines · 17 tokens per session scan A 2a83851ac43f
cursor-cli-runtime is a skill published in the GitHub repository zebbern/agent-collab (34 stars, last pushed 17d ago), licensed Apache-2.0. It adds 17 tokens to every session and 774 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
ask-agents
Send a task or question to Claude Code and/or Gemini as external subagents and report back what they said. Use when the user asks to ask Claude, ask Gemini, ask both, get a second opinion, split reviewer roles, or compare external agents.
review-plan
Review a proposed plan with a single-pass structured critique and a clear verdict. Use when the user asks to review a plan, stress-test a plan, critique a workflow, identify risks, or improve an execution sequence.
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.