autoprompt-skill
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Aug 2026
Autoprompt is a skill that runs the loop for your coding agent. You hand it a goal, constraints, and success criteria, and it scopes, implements, tests, reviews, repairs, and verifies without you prompting each step. It installs into Claude Code, Codex, Copilot, OpenCode, and others through a single npm CLI. MIT licensed.
The install story is the polished part. `npm install -g autoprompt-skill`, run `autoprompt`, pick your agent, confirm the path. A `doctor --strict` command checks every detected installation and uninstall is clean per provider, which is more lifecycle care than most agent skills bother with. It needs Node 20+, Python 3.11+ with PyYAML, and Bash 4.3+, so macOS and Linux unless you are in WSL.
Free with no paid tier above it. The cost is tokens. A loop that implements, tests, reviews, and repairs makes many more model calls than you would by hand, and the project's own docs warn that on very small tasks the overhead works against you.
The catch is how much weight the benchmark headline carries. The 45% fewer failures figure comes from a single Terminal-Bench 2.1 run, and the README says outright that timing and token logs were not retained, making the speed and cost numbers estimates from user reports. Credit for disclosing it. Measure on your own repo first.
Free vs Self-Hosted vs Paid
fully freeFree
MIT licensed, the whole skill and the installer CLI. Every supported provider, the agent definitions, the run controls, and the docs. No paid tier and no hosted service.
Self-Hosted Costs
None beyond your machine. It is prompt orchestration plus shell scripts, not a server.
The Real Cost: Tokens
This is the entire economics. Autoprompt trades your prompting time for model calls, and it spends a lot of them: scope, implement, test, review, repair, verify, each as its own agent pass, with concurrency you set through mode=. Expect a multiple of what the same task costs when you drive the agent yourself. On a Claude Max or comparable flat plan that is absorbed. On metered API pricing it is a line item you should measure before turning it loose on a backlog.
When to Pay
There is nothing to buy. The decision is whether the token multiple is worth not babysitting the loop, and that answer changes with task size. The project itself says small tasks may come out worse.
Free and MIT with nothing to buy. The real cost is a multiple of your usual token spend, which matters on metered API pricing and disappears on a flat plan.
What to do by team size
- Solo
- free; best value on a flat-rate agent plan rather than metered API keys
- Small team
- free; measure the token multiple on one real task before standardizing on it
- Medium team
- free, but set `mode=` concurrency deliberately or the bill scales with the team
- Large team
- free; pilot it against your own benchmark, the published numbers are a single run
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
License: MIT License
Use freely, including commercial. Just keep the license.
Commercial use: ✓ Yes
About
- Owner
- Max (User)
- Stars
- 961
- Forks
- 63
Also by Max
Explore Further
More tools in the directory
everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
245.9k ★hermes-agent
The agent that grows with you
239.6k ★cc-switch
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
130.6k ★