autonomous-execution

Persistent PLAN→EXECUTE→VERIFY→RECOVER loop for computer tasks.

IndexedAGPL-3.0★ 52

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/safiyev-autonomous-execution

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

Persistent PLAN→EXECUTE→VERIFY→RECOVER loop for computer tasks. USE WHEN: multi-step desktop/browser/file work, anything that can fail mid-way. DO NOT USE FOR: pure chat questions with no side effects.

Reviews

Write a review

No 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 and code. 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/autonomous-execution

What's inside

Skill name: autonomous-execution
Description: Persistent PLAN→EXECUTE→VERIFY→RECOVER loop for computer tasks. USE WHEN: multi-step desktop/browser/file work, anything that can fail mid-way. DO NOT USE FOR: pure chat questions with no side effects.
License: AGPL-3.0
Instructions: 24 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Autonomous execution

## Protocol
1. **PLAN** — numbered steps with expected outcome each.
2. **EXECUTE** — one meaningful tool action (prefer API/file/shell over UI).
3. **VERIFY** — screenshot / `file_exists` / URL / tool output must match intent.
4. **RECOVER** — on fail, diagnose; up to 3 alternatives; then escalate.
5. **FINISH** — report only verified paths/URLs; never invent DONE.

## Examples
- input: «открой блокнот и напиши рассказ о мальчике»
  tools: notepad.write content=проза-рассказ title=rasskaz_o_malchike destination=desktop
  never: short rhyme / файл «стишок»

- input: «открой мне дым сигарет с ментолом»
  tools: youtube.open.lesson mode=quick → first organic match
  never: scroll past the correct top video

- input: «пройди тест на вкладке»
  tools: browser.tabs.list → focus → answer → verify → Next (never Next blind)

Never stop after the first tool failure. Ask the owner only for CAPTCHA, login, payment, or irreversible choice.

From SAFIYEV/HeyAgent, AGPL-3.0.

Signals

Stars: 52
Forks: 6
Open issues: 0
Last commit (this folder): Jul 30, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: AGPL-3.0
Repository: github.com/SAFIYEV/HeyAgent
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from SAFIYEV

Cite this page

autonomous-execution skill. Agent Mart. https://agentmart.dev/skills/safiyev-autonomous-execution (last updated 2026-10-24)