autoprompt-skill
Autoprompt is a coding-agent skill that cuts failures by 45% on agentic coding tasks.
Runs with mockssource: GitHubhomepageJavaScriptMITcommit b6516cf52a78
JavaScript, MIT licensed. The project labels itself: agent orchestration, agent skills, agentic workflows, ai agents, ai coding, automated testing, autonomous agents and claude code.
autoprompt-skill runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
autoprompt-skill v2.0.0 CLI installs globally, all 256 core/provider/benchmark tests pass cleanly on Node.js 20.20.2 with Python 3.12 + PyYAML 6.0.3 + jsonschema 4.26.0
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 88.3 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js v18 unmet engine requirement (needs >=20)3 minutes
- PyYAML not found in system site-packages; per-user install skipped by test HOME override1 minute
- python command not on PATH (only python3 exists)1 minute
- test 109: packed global package configure command failed because subprocess with overridden HOME could not find PyYAML1 minute
- Install time
- 5 minutes
- Cold machine to finish
- 31 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- npm run test:cli returned 133 pass, 0 fail; npm run test:providers returned 101 pass, 0 fail; npm run test:benchmark returned 22 pass, 0 fail
- Model tokens used
- 198,157
- Exact commit tested
- b6516cf52a78
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
All three core test suites pass cleanly. Let me compile the final result. **CLI tests**: 133 pass, 0 fail (was 132/1 before fix) **Provider tests**: 101 pass, 0 fail **Benchmark tests**: 22 pass, 0 fail The only failure was in test 109 (`the packed global package exposes a working Argusic Agent config… tokens used 198,157 All three core test suites pass cleanly. Let me compile the final result. **CLI tests**: 133 pass, 0 fail (was 132/1 before fix) **Provider tests**: 101 pass, 0 fail **Benchmark tests**: 22 pass, 0 fail The only failure was in test 109 (`the packed global package exposes a working Argusic Agent config…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 5 minutes.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Of the 22 agent-orchestration projects Argusic has installed and timed, autoprompt-skill was the 10th fastest to reach a running state, and 15 of 22 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 84.50 | 0.19 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.18 |
Topics (from GitHub)
agent-orchestrationagent-skillsagentic-workflowsai-agentsai-codingautomated-testingautonomous-agentsclaude-codeclicode-reviewcodexcoding-agentdeveloper-toolsgithub-copilotmulti-agent-systemsopencodeprompt-engineeringsubagentstest-driven-developmentworkflow-automation
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/autoprompt-skill)Questions
- Does autoprompt-skill run?
- autoprompt-skill runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test autoprompt-skill?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit b6516cf52a78. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test autoprompt-skill?
- The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does autoprompt-skill take to install?
- 5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does autoprompt-skill need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing autoprompt-skill?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does autoprompt-skill compare with the alternatives?
- Of the 22 agent-orchestration projects Argusic has installed and timed, autoprompt-skill was the 10th fastest to reach a running state, and 15 of 22 reached one at all.
- Where is the evidence for autoprompt-skill?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.