autonomy-ladder
Decide whether an agent may take an action un-gated or must stop for a human or the Board, before any autonomous or multi-move execution.
Skill by CleanExpo
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/cleanexpo-autonomy-ladder
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/autonomy-ladder
What's inside
- Skill name
autonomy-ladder- Description
- Decide whether an agent may take an action un-gated or must stop for a human or the Board, before any autonomous or multi-move execution. Four tiers (L0 advise to L3 strategic/irreversible), each with an explicit gate, mapped from the DeepMind AGI-to-ASI continuum. Also used to design where a gate is ENFORCED. The capability-scaled form of the decision-rights matrix.
- License
- unknown
- Instructions
- 78 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from CleanExpo/Pi-Dev-Ops
- 0.598score
artlist-mcp
CleanExpo
Use when a task needs AI image or video generation — campaign visuals, hero shots, product or social video, thumbnails, ad creative, localized variants —…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
plan-to-done
CleanExpo
Plan and write an existing project's complete delivery specification without implementing the product.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
apify-research-connector
CleanExpo
Use when a project needs Apify-powered web, social, SERP, marketplace, or competitor research with credential, compliance, and dataset controls.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
jev
CleanExpo
Ask TypeSafe Jev typed yes/no, pick-one or pick-a-file questions about reviewed files without reading them into an expensive model's context (Levels 8–10), or…
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
adopt-gstack
CleanExpo
How gstack (garrytan/gstack) is installed and used in this estate — which gstack-* skill to reach for, what it must never do here, and how to move the pin.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
ai-website
CleanExpo
Build an "AI website" for a local business — a normal-looking site with an AI agent, lead capture, follow-up, and a CRM under the hood.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
ai-website-generate
CleanExpo
Generate an on-brand, schema-marked website section from a Google Business Profile location, gated by the estate's copy validators.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
spm
CleanExpo
Senior Project Manager spec command.
SkillAFreshness: A★ 2Claude Code +9 - 0.590score
adversarial-review
CleanExpo
Review a proposed fix with a different model in a fresh session that has no access to the builder's reasoning.
SkillAFreshness: A★ 2Claude Code +9 - 0.589score
readiness-architect
CleanExpo
Generates a complete SPM-ready readiness scope for any project, product, app, authority site, CRM, contractor network, training platform, marketing engine…
SkillAFreshness: A★ 2Claude Code +9 - 0.589score
brain-scope
CleanExpo
Scope a task by pulling the latest note from the user's Obsidian "2nd brain" vault, gather related context from the vault, run a client-friendly…
SkillAFreshness: A★ 2Claude Code +9 - 0.507score
skybridge
CleanExpo
Guide developers through creating and updating ChatGPT and MCP apps.
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 3
- Last commit (this folder)
- Sep 29, 2026 (29 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/CleanExpo/Pi-Dev-Ops
- Website
- pi-dev-ops.vercel.app
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from CleanExpo
- 0.598score
artlist-mcp
CleanExpo
Use when a task needs AI image or video generation — campaign visuals, hero shots, product or social video, thumbnails, ad creative, localized variants —…
SkillAFreshness: A★ 2Claude Code +9 - 0.598score
plan-to-done
CleanExpo
Plan and write an existing project's complete delivery specification without implementing the product.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
apify-research-connector
CleanExpo
Use when a project needs Apify-powered web, social, SERP, marketplace, or competitor research with credential, compliance, and dataset controls.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
adopt-gstack
CleanExpo
How gstack (garrytan/gstack) is installed and used in this estate — which gstack-* skill to reach for, what it must never do here, and how to move the pin.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
ai-website
CleanExpo
Build an "AI website" for a local business — a normal-looking site with an AI agent, lead capture, follow-up, and a CRM under the hood.
SkillAFreshness: A★ 2Claude Code +9 - 0.593score
jev
CleanExpo
Ask TypeSafe Jev typed yes/no, pick-one or pick-a-file questions about reviewed files without reading them into an expensive model's context (Levels 8–10), or…
SkillAFreshness: A★ 2Claude Code +9
Cite this page
autonomy-ladder skill. Agent Mart. https://agentmart.dev/skills/cleanexpo-autonomy-ladder (last updated 2026-10-24)