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 smk-labs/claude-plugins/plugin install cursor-delegateWrote 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/smk-labs/claude-plugins/cursor-delegate)<a href="https://agentmods.dev/skills/smk-labs/claude-plugins/cursor-delegate"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/cursor-delegate/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/smk-labs/claude-plugins/cursor-delegate"><img src="https://agentmods.dev/badge/skills/smk-labs/claude-plugins/cursor-delegate.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 | $0.03193 |
| Opus 5.5 | $0.00020 | $0.01277 |
| Sonnet 5.5 | $0.00010 | $0.00639 |
| Haiku 4.5 | $0.00005 | $0.00319 |
Grade D, and why
cursor-delegate scanned grade D with 3 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Auth (key-based, the normal path): put Cursor API keys in `~/.claude-deck/cursor/agent-keys.json` (chmod 600) and name the default account: Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Install the CLI: `curl https://cursor.com/install -fsS | bash`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Install the CLI: `curl https://cursor.com/install -fsS | bash`. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate to Cursor (agent calling)
Hand a self-contained slice to cursor-agent; it runs on the Cursor plan's quota while Claude keeps the context and the plan. This is agent calling, not a model swap: Cursor sells no Anthropic-shaped API for its subscription, so Claude's own engine can't point at it, but the two run side by side.
Pick the runner first
One measured fact drives this choice: flaky networks (VPNs especially) kill any single cursor-agent stream older than ~5 minutes. Long runs die at minute ~6 with "Connection lost" while short requests keep succeeding.
- Quick task — the worker will plausibly finish in under ~4 minutes (one focused edit, a lookup, a small test fix): call
cursor_run. - Anything else — multi-file work, builds, test loops, refactors, research that reads a lot: use the legged runner. Never start a long single stream.
Quick tasks: the cursor_run MCP tool
Call cursor_run (from this plugin) with the task:
task(required) — the self-contained instruction.account(optional) — omit it in the normal case. With no account, auth comes from thedefaultentry of~/.claude-deck/cursor/agent-keys.json(a stable API key — deterministic, no browser login involved). Pass an account name only when the user keeps several Cursor seats and names one.model(optional). Cursor meters two separate pools: first-party (auto,composer-*,cursor-*) has the large allowance; API pass-through (claude-*,gpt-*) has a small one that empties fast. Preferautofor mechanical work; spend an API-pool model on prose, judgment or review. Say which you used. Full rule: the cursor-orchestrate skill, "Model routing".extraArgs(optional) — flags passed straight to cursor-agent (e.g.["--resume", "<session_id>"]). Approval flags are not needed: every runner already passes--force --approve-mcps, so workers edit files, run shell, and use MCPs without prompting.dryRun: true— print the exact command (key redacted) without running, to show the user first.
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 Changed · +3 lines · -60 tokens per session 21848f5c6f90
- 1mo ago First seen · 102 lines · 109 tokens per session scan D d085a7db9fa1
cursor-delegate is a skill published in the GitHub repository smk-labs/claude-plugins (11 stars, last pushed 28d ago), licensed MIT. It adds 49 tokens to every session and 3,193 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pmm-resume
Reviews and tailors a PMM resume (IC to VP, including AI PMM roles): dissects the job description, ranks bullets by impact fit and rebuilds the complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for [company]", "review my PMM resume", "reframe for…
product-marketing-context
Builds and maintains the shared GTM brain (product context, ICP, positioning, voice, market context, proof points, plus optional strategy and execution sections and the deal-reality fields) that every other skill reads before producing output. Works standalone from your own answers, and gets stronger when you connect…
competitor-deep-dive
Builds a long-form, fully sourced deep-dive on one competitor for a named decision (strategy call, RFP, pricing change, roadmap bet), with dated reviews, deal evidence, a head-to-head per offering and where they win. Triggers: "deep-dive on [competitor]", "full competitor write-up", "what do users really say about…
workflow-orchestrator
Chains positioning, competitive, GTM strategy, campaign briefs, stakeholder maps and retros into one coherent PMM program with a master document and brain updates. Trigger on: "run full GTM workflow", "run a full launch", "launch [product] end to end", "positioning refresh", "quarterly PMM cycle", "competitive…
positioning-messaging
Builds or audits positioning statements, messaging hierarchies, homepage copy and persona cards using April Dunford's Obviously Awesome framework, in five modes (build, audit, fletch, sales-enablement, homepage). Refuses to generate without a named primary persona and 3+ alternatives including status quo, and blocks…
writing-assistant
Rewrites, sharpens and drafts B2B writing in the writer's real voice: Slack messages, emails, memos, PRDs, decks, plus marketing content (blog posts, landing pages, press releases, case studies, newsletters, social posts). Use whenever someone wants to rewrite, tighten, draft or audit copy, asks why copy isn't landing…