Skillget

autoprompt-skill

agent
Security Audit
Fail
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 205 GitHub stars
Code Fail
  • fs module — File system access in .github/workflows/label-sync.yml
  • fs module — File system access in agents/claude/workflow/agent-definitions-cli.js
  • os.homedir — User home directory access in agents/claude/workflow/model-casting.js
  • fs module — File system access in agents/claude/workflow/model-casting.js
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

README.md

Autoprompt Skill with 45% fewer failures on agentic coding tasks

Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.

Terminal-Bench 2.1: plus 14.61 points Version 1.0.0 Six supported providers License MIT

English | 中文 | 한국어 | Español | العربية

Contents

Install · Benchmarks · Invocation · Run controls · Workflow · Agents · Examples · FAQ · License

Install

Use the CLI below, or download an installer from GitHub Releases.

1. Install the CLI

npm install -g autoprompt-skill

2. Launch the installer

autoprompt

3. Install

Choose your coding agent, confirm its path, and install. N means enter another path.

For another CLI or IDE, choose Custom coding agent and use the compatibility guide.

Install from source 
git clone https://github.com/Spielewoy/autoprompt-skill
cd autoprompt-skill
npm install -g .
autoprompt

Requirements

Support

Status Coding agent Audited requirement Key
Working Claude Code 2.1.219+; audited 2.1.233 claude
Working Codex Subagent-capable build; audited 0.147.0 codex
Working OpenCode 1.18.7+; audited 1.18.18 opencode
Working Kilo Code 7.4.22+; audited 7.4.22 kilo
Working VS Code 1.133+; audited 1.133.0 with Copilot 0.61.0 vscode
Working Prime Agent 0.7.2; audited 0.7.2; native package adapter prime

See support and audit notes.

Check, update, or remove an installation

  • Check every detected installation: autoprompt doctor --strict
  • Check one provider: autoprompt doctor PROVIDER --strict
  • Update or repair: autoprompt, then choose an installed provider
  • Uninstall interactively: autoprompt uninstall
  • Uninstall one provider: autoprompt uninstall PROVIDER
  • Show every command: autoprompt help

Replace PROVIDER with a key from the support table, such as claude, codex, or prime.

Benchmarks

Terminal-Bench 2.1 leaderboard with 18 Artificial Analysis reference scores and measured DeepSeek V4 Flash 0731 scores with and without Autoprompt.

Measured OpenCode comparison

OpenCode 1.18.7 on Terminal-Bench 2.1: OpenCode solved 60 of 89 tasks and OpenCode with Autoprompt solved 73 of 89 tasks.

Track Solved Score Failed
OpenCode 60/89 67.42% 29
OpenCode + Autoprompt 73/89 82.02% 16
Change +13 solves +14.61 points 45% fewer

DeepSeek's 82.7% used its own test setup, so it is a reference point, not a comparable third run. Read the setup and evidence boundaries, or request another benchmark.

Expected trade-off: about 3x the time and 2x the tokens.

Timing and token logs were not retained, so these are planning estimates based on user experience reports, not measured benchmark results. The measured result was 29 to 16 failures (45% fewer) in this run, which translates to about 2x fewer mistakes. Note: for very small tasks, this may differ heavily.

Anatomy of an invocation

Anatomy of an Autoprompt invocation: trigger, concurrency mode, agent cap, model routing, and goal

Run controls

Use mode= to set concurrency. Use agents= to route models where the host supports it. Custom model setup

Control Claude Code Codex OpenCode Kilo VS Code Prime Agent
mode= ✓ ✓ ✓ ✓ ✓ ✓
Custom agents= routing ✓ ✓ ✕ Not available - inherits active model ✕ Not available - inherits active model ✕ Not available - inherits active model ✕ Not available - inherits selected parent model

How it works

Autoprompt workflow from prompt through planning, build, review, tests, sign-off, and sweep

The agents

Autoprompt agent hierarchy from prompt to coordinators, manager, execution lanes, and independent checks

Examples

Goal Prompt
Fix /autoprompt fix the registration race and add a regression test
Build /autoprompt mode=wide build the booking flow from API to checkout
Research /autoprompt compare job queues against this codebase and recommend one
Limit parallel work /autoprompt mode=custom max_subs=4 migrate every model

Use $autoprompt instead of /autoprompt in Codex.

FAQ

Does Autoprompt mean I literally do not have to prompt?

No. Give it a clear goal, constraints, and success criteria. Autoprompt handles the execution loop, so you do not have to prompt every step. Details

How autonomous is Autoprompt?

It can scope, implement, test, review, repair, and verify a goal. It stops for choices that change the result, actions that need your authority, or blockers it cannot safely resolve. Details

What are the layers for?

The layers separate coordination, management, execution, and independent judgment. That separation keeps one agent from planning, approving, and verifying its own work. Details

What do `mode`, `max_subs`, and `agents` do?

mode=tokensaver caps active subagents at six. mode=wide opens every ready lane. mode=custom max_subs=N sets your own ceiling. agents controls model routing where the host supports it. Details

Why does Autoprompt not start in the background?

Because it changes cost, time, and workflow. Start it explicitly with /autoprompt <goal>, or $autoprompt in Codex.

License

MIT. Copyright 2026 Spielewoy.

Community: Contributing, Code of Conduct, Security, and Support.

Reviews (0)

No results found