oh-my-agent
Mechanical verification for AI coding agents, skills pack or full harness (stop-hook gates, artifact checks, independent judges).
Runssource: GitHubhomepageTypeScriptMITcommit c7417362f8f9
TypeScript, MIT licensed. The project labels itself: agent harness, agent skills, claude code, cli, codex, cursor, developer tools and multi agent.
oh-my-agent runs. An Argusic agent installed it in 8 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
oh-my-agent v13.2.1 builds successfully, the oma CLI binary prints version 13.2.1, and all 4264 tests in 323 test files pass with no failures.
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 100 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.
- transport.test.ts used cwd: "/tmp" which triggered state-boundary hook creating /tmp/.agents/state/sessions/. This contaminated backup.test.ts findProjectRoot (walked up tmpdirs and wrongly found /tmp as project root). Caused backup.test.ts (1) + opt.test.ts (6) to fail.10 minutes
- mawk cannot handle multi-byte UTF-8 chars inside awk bracket expressions [✓√✔] in filter-test-output.sh. 12 tests in filter-test-output.test.ts had 1 failure.3 minutes
- Node.js v18.19.1 too old for vitest 4.x (needs node:util.styleText from node >=26). Bun install succeeded but vitest died at startup.2 minutes
- Install time
- 8 minutes
- Cold machine to finish
- 53 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- vitest run → 323 test files passed, 4264 tests passed, 4 skipped, 1 todo. Build: bun run build → bundled 1704 modules → cli.js 5.22 MB. CLI: node bin/cli.js --version → 13.2.1
- Model tokens used
- 444,769
- Exact commit tested
- c7417362f8f9
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**oh-my-agent v13.2.1** installed, built, and ran its full test suite successfully. ### Errors encountered and fixed 1. **Node.js too old (v18 → v26)** — vitest 4.x needs `node:util.styleText` from Node ≥26. Fixed by… 2. **mawk + UTF-8 in filter-test-output.sh** — `mawk` (this system's awk) cannot handle multi-byte … 3. **transport.test.ts contamination of /tmp/.agents** — Two tests used `cwd: "/tmp"`, which trigge… ### Final verification | Check | Result | |-------|--------| | `bun install` | 1497 packages installed | | `bun run build` | Bundled 1704 modules → `cli.js` 5.22 MB | | `node bin/cli.js --version` | `13.2.1` | | `vitest run` (323 files) | **4264 passed**, 4 skipped, 1 todo, **0 failures** |
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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 8 minutes.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 8 minutes after the clone.
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
Topics (from GitHub)
agent-harnessagent-skillsclaude-codeclicodexcursordeveloper-toolsmulti-agent
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/oh-my-agent)Questions
- Does oh-my-agent run?
- Yes. oh-my-agent runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test oh-my-agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c7417362f8f9. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test oh-my-agent?
- The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does oh-my-agent take to install?
- 8 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 oh-my-agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing oh-my-agent?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for oh-my-agent?
- 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.