autopilot

autopilot is a cursor rule for coding agents from Jkudjo/oh-my-cursor. It costs 12 tokens per session (300 once invoked), scanned A, original, MIT.

An autonomous coding workflow that clarifies a task, creates a plan, makes the changes, and checks the result with tests, linting, and a smoke check.

In plain words
What is it for?
Use it for clearly scoped coding tasks that should run from initial questions through implementation and verification with minimal interruption.
Why use it?
It removes the need to approve each step of a well-defined task. It still pauses when an important architecture decision needs your input.

Cursor rule

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 rules/jkudjo/oh-my-cursor/autopilot
Clone the repo
git clone --depth 1 https://github.com/Jkudjo/oh-my-cursor

Wrote 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.

agentmods badge for autopilot

README.md
[![agentmods](https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/autopilot.svg)](https://agentmods.dev/rules/jkudjo/oh-my-cursor/autopilot)
Your own site
<a href="https://agentmods.dev/rules/jkudjo/oh-my-cursor/autopilot"><img src="https://agentmods.dev/badge/rules/jkudjo/oh-my-cursor/autopilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 300 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 $0.00012 $0.00300
Opus 5 $0.00006 $0.00150
Sonnet 5 $0.00002 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 4d ago against content hash cd06ad797137, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autopilot 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 4d 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.

rules/autopilot.mdc · 31 lines

What it actually says

@autopilot

Trigger: When you want the full workflow (interview → plan → execute) to run autonomously without manual approval steps.

Protocol

  1. Call start_mode with mode=autopilot.
  2. Clarify phase — internally score ambiguity 0–10.
    • If score > 7: ask at most 2 focused questions, then proceed.
    • If score ≤ 7: proceed without questions.
  3. Plan phase — generate a full implementation plan (same format as @ralplan).
    • Call save_plan with approved=true (autopilot self-approves).
    • Call update_mode_state with phase=executing.
  4. Execute phase — follow @ralph protocol to execute every step.
  5. Verify phase — run tests, lint, smoke check.
  6. Call update_mode_state with status=completed.
  7. Report: files changed, tests passed, any issues found.

Rules

  • Autopilot self-approves plans. Use this only for well-scoped tasks.
  • Still persist all state — plans, memory, mode state.
  • If you encounter a decision with significant architectural impact: pause, surface it, wait for input.
  • Never delete data or make destructive changes without explicit instruction.
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. 4d ago First seen · 31 lines · 12 tokens per session scan A cd06ad797137

Subscribe to this mod's changes

autopilot is a cursor rule published in the GitHub repository Jkudjo/oh-my-cursor (1 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 300 once invoked, about $0.0001 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.