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 agentmods add skills/andreilungeanu/cursor-delegate-mcp/delegatenpx skills add andreilungeanu/cursor-delegate-mcp --skill delegategit clone --depth 1 https://github.com/andreilungeanu/cursor-delegate-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/andreilungeanu/cursor-delegate-mcp/delegate)<a href="https://agentmods.dev/skills/andreilungeanu/cursor-delegate-mcp/delegate"><img src="https://agentmods.dev/badge/skills/andreilungeanu/cursor-delegate-mcp/delegate.svg" alt="Measured on agentmods" 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 | $0.00102 | $0.01966 |
| Opus 5 | $0.00051 | $0.00983 |
| Sonnet 5 | $0.00020 | $0.00393 |
| Haiku 4.5 | $0.00010 | $0.00197 |
Grade A, and why
delegate 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 3d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delegate to Cursor
You orchestrate; Cursor implements. Use the cursor-delegate-mcp MCP server — never run
cursor-agent from the shell.
When to delegate
Delegate when the user wants Cursor to edit the repo (they may say Cursor,
Composer, or cursor-agent — same handoff). Not for the MCP host's own subagents —
use the delegate MCP tool to reach cursor-agent only.
Scale effort to the task:
- Trivial (one-liner, rename, typo): do it yourself — delegation overhead exceeds the task.
- Medium (multi-file feature or refactor): one
delegatecall. - Large or risky (architecture, wide rewrites):
mode: "plan"first; implement after approval. - Never delegate a task you cannot write acceptance criteria for.
- Purely advisory questions →
mode: "ask"; plan with no file writes →mode: "plan". For these, state what form the answer or plan should take — there's no diff, so the output format is the deliverable.
Workflow
-
Build the brief inline — pass task text in
specthat answers all four, and asks for one thing back:- Goal — the outcome, precisely.
- Scope — which files/directories are in play.
- Decisions already made — constraints and fixed choices the user stated or implied. This is what prevents wrong assumptions and clarifying questions. Transmit them faithfully; don't invent constraints the user didn't state.
- Done when — verifiable acceptance criteria, stated as end state. Have Cursor run tests as it works; that loop is what makes the code good. Its report is not evidence, though — you re-check in step 3, because command output never crosses the ACP wire and the author of a change is not an independent verifier of it.
- Gaps to report back — close the brief by asking for any acceptance criterion it could not meet and any assumption it had to make. Assumptions are the one thing no response field captures.
Point, don't paste: reference files to read or mimic ("follow the middleware pattern in src/api/middleware/auth.js") instead of pasting code — Cursor reads the repo itself; the brief carries judgment, not content. For images, and for documents outside the repo, prose cannot point at all — attach those with
contextFiles.
What ships with it
1 file 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.
- 3d ago First seen · 149 lines · 102 tokens per session scan A 8ddd6d9a7d88
delegate is a skill published in the GitHub repository andreilungeanu/cursor-delegate-mcp (4 stars, last pushed 13d ago), licensed MIT. It adds 102 tokens to every session and 1,966 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
upstream-sync
Periodically sync new commits from microsoft/terminal into this manually-forked intelligent-terminal repo by cherry-picking commit-by-commit onto a dated sync branch, auto-skipping revert pairs and empty commits, auto-resolving known take-upstream files, and stopping cleanly on genuine conflicts. The agent (you…
release-notes
Generate user-facing release notes for Intelligent Terminal. Use when asked to write release notes, changelog, what-is-new summary, or prepare a release. Compares git commits between releases, looks up PR-linked issues and community contributors, then outputs formatted notes with "Verbed + Impact + Scenario" style…
add-acp-agent-support
Add first-class support for an ACP-compatible agent CLI to Intelligent Terminal. Use when integrating a new built-in AI agent, ACP server command, authentication flow, model selection, interactive delegation, session hooks, onboarding, Settings, branding, GPO policy, documentation, tests, build, deployment, or live…
pr-integration-test
Design, implement, and validate Intelligent Terminal integration tests for a target pull request or regression. Use when asked to add PR integration tests, convert a bug fix into E2E coverage, prove existing behavior still works, map tests to the release checklist, or verify E2E reports mark checklist cases complete.
store-listing-localizer
Automate Microsoft Store (Partner Center) listing localization for Intelligent Terminal (Store ID 9NMQC2SSJX24). Use when asked to export/import Store listings, localize release notes / descriptions / captions / features into 80+ languages, update listingData CSV, or push Store listing translations without manually…
configure-coddy
Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands and commits only after the user confirms saving. Load when the user explicitly asks to change a Coddy setting, or…