autopilot-charter

autopilot-charter is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 80 tokens per session (1,057 once invoked), scanned A, original, MIT.

A framework for deciding which recurring reports, briefings, and reviews should be automated, assisted by an agent, or kept manual.

In plain words
What is it for?
It is for planning scheduled AI runs, reviewing team rituals, choosing automation candidates, and ordering an automation rollout.
Why use it?
It helps teams avoid automating unsuitable work and sets review, failure, and escalation rules for recurring processes.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit It is for planning scheduled AI runs, reviewing team rituals, choosing automation candidates, and ordering an automation rollout.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/autopilot-charter
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,352 stars · on GitHub · mohitagw15856.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

Made for: 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-charter

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/autopilot-charter/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/autopilot-charter)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/autopilot-charter"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/autopilot-charter/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.

agentmods 80×15 button for autopilot-charter

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/autopilot-charter"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/autopilot-charter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,057 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00080 $0.01057
Opus 5 $0.00040 $0.00528
Sonnet 5 $0.00016 $0.00211
Haiku 4.5 $0.00008 $0.00106

Measured 8d ago against content hash d81317ceb1c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

autopilot-charter 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 8d 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.

exports/cursor/pm-autopilot/autopilot-charter/autopilot-charter.mdc · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autopilot Charter Skill

Inventory the reports, briefings, and reviews you produce on a rhythm, and decide — deliberately — which ones an AI should run on a schedule, which it should only draft, and which stay human.

What This Skill Produces

  • A ritual inventory: every recurring artifact, its cadence, audience, and inputs
  • An automate / assist / keep-manual call per ritual, with the reason
  • Guardrails for each automated ritual (review gate, failure behaviour, escalation)
  • A rollout order — which ritual to automate first and why

Required Inputs

Ask for (if not already provided):

  • The recurring outputs the user or team produces (weekly updates, monthly reviews, monitors, digests)
  • Who consumes each one and what they do with it
  • Where the inputs live (git, analytics, CRM, inbox, notes) and whether an agent can reach them
  • Tolerance for error per artifact — what happens if a run is wrong or missing?

Classification Framework

Score each ritual on four questions, then classify:

Question Points toward automating
Inputs reachable? Can an agent read the sources without a human fetching them? Yes
Structure stable? Does the output look the same every cycle? Yes
Cost of a bad run? Would a wrong or stale edition mislead a decision? Low cost
Delta-shaped? Is the value "what changed since last time" rather than fresh judgement? Yes
  • Automate — all four favourable. Schedule it end-to-end; the human sees the result, not the work.
  • Assist — structure is stable but judgement or unreachable inputs remain. Schedule a draft; a human finishes it.
  • Keep manual — high cost of error, or the ritual's value is the human thinking (performance feedback, strategy). Do not automate; record why so nobody re-litigates it.

Guardrails (required for every "Automate")

For each automated ritual, define:

  • Review gate — does an edition ship unreviewed, or land as a draft for approval? Default to draft for anything audience-facing.
  • Failure behaviour — if a run fails or a source is unreachable, does it skip, retry, or alert? A silent gap is worse than an error message.
  • Staleness marker — every edition states when it ran and which sources it read.
  • Kill criteria — what result (two wrong editions? a complaint from the audience?) takes it off autopilot.

Read the full file on GitHub · 80 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. 8d ago First seen · 80 lines · 80 tokens per session scan A d81317ceb1c3

Subscribe to this mod's changes

autopilot-charter is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 1,057 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 2026-09-03.