@Spielewoy/autoprompt-skillPublic

Skills#Claude Code #Codex #Copilot #Any agent#Coding #Testing #Code review

Coding-agent skill for review, fix, and recheck loops

Autoprompt wraps a coding agent in a workflow that plans work, builds it, checks it, and retries when needed. It supports multiple providers and lets you choose paths and concurrency so the agent’s work stays coordinated.

1,057 stars•69 forks•JavaScript•Updated 7d ago

Who it's for

Builders who use coding agents and want a repeatable loop for implementing, testing, and reviewing changes.

What it delivers

You can cut down failed agent runs by having the agent review, repair, and verify its own work.

What it does

Provider installs

Installs and configures supported providers such as Claude Code, Codex, OpenCode, Kilo, VS Code, Prime, Oh My Pi, DeepSeek, Reasonix, Hermes, and Grok.

Activation command

Starts a task with `autoprompt activate PROVIDER --target /absolute/project -- "<goal>"` and supports optional path modes like `auto`, `direct`, `light`, and `roadmap`.

Concurrency controls

Lets you choose `tokensaver`, `wide`, or a custom subagent limit with `--concurrency custom --max-subs N`.

Model and agent selection

Provides `autoprompt configure` commands to pick provider models, effort levels, and model maps.

Independent verification loop

Separates coordination, execution, and checking so one agent does not approve its own work.

Benchmarked workflow

Includes benchmark results, comparison assets, and evidence notes showing fewer failures on Terminal-Bench tasks.

How to get it

1Run

npm install -g https://github.com/Spielewoy/autoprompt-skill/releases/download/v2.0.0/autoprompt-skill-2.0.0.tgz

2Run
```
autoprompt
```

3For another CLI or IDE, choose Custom coding agent and use the compatibility guide.

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

README

Autoprompt is a coding-agent workflow that cuts failures by 45% by reviewing, fixing, and rechecking its work.

English | 中文 | 한국어 | Español | العربية

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 https://github.com/Spielewoy/autoprompt-skill/releases/download/v2.0.0/autoprompt-skill-2.0.0.tgz

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

Node.js 20+
Python 3.11+ available as python3 or python, with PyYAML
Bash 4.3+ on macOS or Linux
Git only for the GitHub checkout method

Support

Status	Coding agent	Tested version	Key
Working	Claude Code	2.1.263	`claude`
Working	Codex	0.148.0	`codex`
Working	OpenCode	1.18.29	`opencode`
Working	Kilo Code	7.5.15	`kilo`
Working	VS Code	1.136.1	`vscode`
Working	Prime Agent	0.7.2	`prime`
Working	Oh My Pi	18.1.14	`omp`
Working	DeepSeek Harness	0.1.2-rc.1	`deepseek`
Working	Reasonix	1.30.0	`reasonix`
Working	Hermes Agent	0.21.1	`hermes`
Working	Grok Build	1.0.13	`grok`

These versions passed Linux runs. Model and platform availability varies by provider.

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

These are version 1 benchmarks. Version 2 benchmarks will follow.

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 significantly.

Anatomy of an invocation

autoprompt activate PROVIDER --target /absolute/project -- "<goal>"

Part	What it does
`PROVIDER`	A key from the support table, such as `claude`, `codex`, or `grok`.
`--target`	The project to work on. Omit it to use the current directory.
`--`	Separates launcher options from the request.
`<goal>`	The result you want, constraints, and how to check success.
`path=`	Optional `auto`, `direct`, `light`, or `roadmap`, before the quoted goal. See work paths.

autoprompt activate codex -- path=light "add retries and test the edge cases"

Run controls

The same controls apply to all eleven providers. Custom model setup

Control	What it does
`--concurrency tokensaver`	Runs at most six subagents at once.
`--concurrency wide`	Starts ready, independent work up to the host limit.
`--concurrency custom --max-subs N`	Sets your own concurrency limit.
`configure PROVIDER --agents off`	Uses the provider's configured model.
`configure PROVIDER --agents MODEL`	Selects one model. Add `--effort LEVEL` where supported.
`configure PROVIDER --agents auto --model-map FILE`	Chooses from a measured model registry. A comma-separated model list also requires `--model-map`.

Pass concurrency controls after --, before the quoted goal:

autoprompt activate codex -- --concurrency custom --max-subs 4 "add retries and tests"
autoprompt configure claude --agents provider/model --effort low

How it works

The agents

Examples

Goal	Prompt
Fix	`autoprompt activate claude -- "fix the registration race and add a regression test"`
Build	`autoprompt activate codex -- --concurrency wide "build the booking flow from API to checkout"`
Research	`autoprompt activate hermes -- "compare job queues against this codebase and recommend one"`
Limit parallel work	`autoprompt activate grok -- --concurrency custom --max-subs 4 "migrate every model"`

Run these commands from your project, or supply --target /absolute/project before --.

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 are the paths?

path=auto selects a route for the task. direct starts focused work, light adds a short plan, and roadmap organizes dependent work before execution. Every path includes independent verification. Details

What do concurrency, models, and paths control?

--concurrency and --max-subs set parallel work limits. configure --agents selects models, and path= selects how work is planned and coordinated. Details

Why does Autoprompt not start in the background?

Because it changes cost, time, and workflow. Start it explicitly with autoprompt activate PROVIDER -- "<goal>".

License

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

Contributors

johnatag · rollingdice · AincradBot · lunar-me · fatinghenji · c8dhjp4tyv-bit · Alexis-Fiolleau-LaPoste-BGPN

Files in the repo

Repository payload•12 top-level entries

.github— GitHub workflows and templates
agents— Provider-specific agent packs and manifests for supported tools.
assets— Workflow diagrams, benchmark images, and release visuals.
bin— 2 items
docs— Guides, FAQ, benchmark notes, and support documents.
scripts— Install, configure, benchmark, and workflow scripts for providers and harnesses.
tests— Source and benchmark tests for the workflow and provider behavior.
.gitattributes
LICENSE— License
package-lock.json
package.json— Node package: install with npm
README.md— The README

Discussion (0)

Ask about usage, or say what you built with it

No comments yet. Be the first to say what this is good for.

More skills

obra/

superpowers

obra/superpowersSkills

An agentic skills framework & software development methodology that works.

285k

1 add

Graphify-Labs/graphifySkills

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

117k

1 add

Vincentwei1021/

anything2explainer

Vincentwei1021/anything2explainerSkills

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

666

anthropics/skillsSkills

Public repository for Agent Skills

176k

career-ops-hq/career-opsSkills

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

71k

addyosmani/agent-skillsSkills

Production-grade engineering skills for AI coding agents.

93k

What it does

Provider installs

Activation command

Concurrency controls

Model and agent selection

Independent verification loop

Benchmarked workflow

How to get it

README

Contents

Install

1. Install the CLI

2. Launch the installer

3. Install

Requirements

Support

Check, update, or remove an installation

Benchmarks

Anatomy of an invocation

Run controls

How it works

The agents

Examples

FAQ

License

Contributors

Files in the repo

Discussion (0)

More skills