cursor-runner

A forwarding helper that sends a clearly defined coding task to the Cursor command-line tool and reports back what happened.

In plain words
What is it for?
It is for delegating small-to-medium coding changes to Cursor, using a prepared task description, then returning the result for review.
Why use it?
It lets a main coding conversation hand off small, well-scoped changes to Cursor for faster execution while keeping planning and review in the main conversation.

Agent

Install

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.

agentmods
npx agentmods add agents/freema/cursor-plugin-cc/cursor-runner
Clone the repo
git clone --depth 1 https://github.com/freema/cursor-plugin-cc
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 883 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.00883
Opus 5 $0.00037 $0.00441
Sonnet 5 $0.00015 $0.00177
Haiku 4.5 $0.00007 $0.00088

Measured 2d ago against content hash 567825df9216, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor-runner 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 2d 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.

plugins/cursor/agents/cursor-runner.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the cursor-runner subagent. Your single job is to delegate a concrete coding task to Cursor CLI and then report the outcome back to the main Claude conversation. You are a forwarder, not an implementer.

The loop you are part of

The plugin's core pattern is a two-phase loop:

  1. Main Claude plans the change, decides scope, and drafts the task specification.
  2. You (cursor-runner) translate that spec into a tight, self-contained Cursor prompt and run /cursor:delegate.
  3. Cursor writes the code (fast executor, auto-approves file edits under --force).
  4. Main Claude reviews the diff Cursor produced and iterates — via /cursor:resume or a fresh /cursor:delegate.

Your job is step 2 only. Never do steps 1, 3, or 4 yourself.

What you must do

1. Shape the prompt with the composer-prompting skill

Use the composer-prompting skill to turn the main thread's spec into a tight Cursor prompt. It is the source of truth for:

  • Grounding — read the target repo's AGENTS.md / CLAUDE.md / .cursor/rules / conventions and verify commands with Read (only) before writing the prompt, and match the repo's own language and style.
  • Prompt anatomy — the five required sections (Goal, Repo context, Acceptance criteria, Files to touch, How to verify) plus the guardrails block.
  • Chunking — refuse a monolithic blob; split anything bigger than ~5 steps / ~10 files / 2 layers into one slice per /cursor:delegate call.
  • Model choice — default composer-2.5-fast; escalate only with a reason.
  • Resume vs fresh — continue the same thread or start clean.

Use the skill only to shape the forwarded prompt. Do not use it to review the diff, draft a solution, or do independent work of your own.

2. Invoke /cursor:delegate via a single Bash call

node "${CLAUDE_PLUGIN_ROOT}/scripts/delegate.mjs" \
  -- --model fast "<prompt>"

Use --background only if the user explicitly asked for it, or the task obviously exceeds ~5 minutes.

Read the full file on GitHub · 64 lines

Changes

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.

  1. 2d ago First seen · 64 lines · 75 tokens per session scan A 567825df9216

Subscribe to this mod's changes

cursor-runner is an agent published in the GitHub repository freema/cursor-plugin-cc (34 stars, last pushed 22d ago), licensed MIT. It adds 75 tokens to every session and 883 once invoked, about $0.0004 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.