autopilot-patterns

A set of patterns for letting GitHub Copilot carry out a reviewed, multi-step plan with limited interruption. It describes guardrails, safety boundaries, and different levels of autonomy.

In plain words
What is it for?
Use it for clearly scoped migrations, formatting jobs, refactors, overnight tasks, or other work with defined completion criteria, starting from a reviewed plan.
Why use it?
It provides a structured way to decide when repetitive or well-defined work can run without approval after every step.

Skill for Claude CodeCodex

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 skills/drvoss/everything-copilot-cli/autopilot-patterns
Any agent
npx skills add drvoss/everything-copilot-cli --skill autopilot-patterns
Clone the repo
git clone --depth 1 https://github.com/drvoss/everything-copilot-cli

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,909 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 $0.00041 $0.02909
Opus 5 $0.00020 $0.01455
Sonnet 5 $0.00008 $0.00582
Haiku 4.5 $0.00004 $0.00291

Measured 2d ago against content hash 2e5c31103fc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autopilot-patterns 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/copilot-native-workflows/skills/autopilot-patterns/SKILL.md · 353 lines

How it starts

The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autopilot Mode Patterns

Why This is Copilot-Exclusive

Copilot CLI's Autopilot mode lets the agent work autonomously through a plan without stopping for approval at each step. Combined with Plan Mode's structured todos and Fleet's parallelism, this creates a spectrum of autonomy levels — from fully interactive to fully autonomous — that you can dial in per task. Claude Code always requires you to approve every tool call (or use a limited "auto-accept" that lacks structured planning).

When to Use

  • Well-defined tasks with clear acceptance criteria
  • Repetitive operations across many files (migrations, formatting, refactors)
  • After you've reviewed and approved a plan in Plan Mode
  • When the cost of review per step exceeds the risk of autonomous execution
  • Overnight or long-running tasks you want to fire-and-forget

Workflow

1. Start with a Plan

Always begin in Plan Mode for autopilot tasks:

[Shift+Tab to enter Plan Mode]
You: "Convert all React class components to functional components with hooks"

2. Review the Plan Carefully

This is your guardrail moment. The plan should include:

  • Clear scope (which files, which patterns)
  • Defined completion criteria
  • Test verification steps
  • Rollback approach (e.g., git branch)

3. Select Autopilot Execution

When presented with the approval menu, choose Autopilot:

exit_plan_mode:
  summary: "Convert 12 class components to functional components..."
  recommendedAction: "autopilot"

4. Monitor Progress

Even in autopilot, you can:

  • Watch the output stream in real-time
  • Check todo status via SQL queries
  • Interrupt if something goes wrong (Ctrl+C)

Continuation Boundaries and Permissions

Autopilot keeps working until the task completes, you interrupt it, a blocker stops progress, or a configured continuation limit is reached.

Set explicit checkpoints when you want them

If you want autopilot to pause after a bounded number of autonomous steps, set a continuation limit up front:

Read the full file on GitHub · 353 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 · 353 lines · 41 tokens per session scan A 2e5c31103fc7

Subscribe to this mod's changes

autopilot-patterns is a skill published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 2,909 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

winui-session-report

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use only when the user explicitly asks for session feedback, agent debugging, or a review of what happened during a build session. Do not inspect session data automatically.

microsoft/win-dev-skills · 61 tokens

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session.

ivfarias/ceo · 17 tokens

skill-creator

Skill development lifecycle: create, edit, test, benchmark, and optimize SKILL.md files. Evals, assertions, description triggering optimization, variance analysis, iteration loops. Use when creating a skill from scratch, improving an existing skill, running evals, or optimizing a skill description.

Poorgramer-Zack/copilot-cli-things · 61 tokens

Skill Development

Copilot CLI skill creation and authoring. Covers SKILL.md structure, YAML frontmatter, description writing, progressive disclosure, bundled resources (scripts/references/assets), imperative writing style, validation, and iteration. Use for creating, improving, or organizing plugin skills.

Poorgramer-Zack/copilot-cli-things · 56 tokens

paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

paperclipai/paperclip · 43 tokens

omni-mcp

Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.

diegosouzapw/OmniRoute · 48 tokens