oh-my-agent 18.0.2 → 19.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +2 -30
- package/bin/cli-main.js +976 -976
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -10,7 +10,7 @@ Spawning parallel agents is the easy part. The hard part is knowing whether they
|
|
|
10
10
|
|
|
11
11
|
oh-my-agent makes the claim falsifiable. A Stop hook refuses to end your session until your project's own `typecheck` / `test` / `lint` script exits 0. A gate command decides whether a workflow really ran by looking for the artifacts it must have left behind — and its JSON verdict, not the agent's summary, is the result. An independent judge with a fresh context re-verifies every criterion each round, including the ones that already passed. Every gate decision lands on an append-only event log you can read after the fact. Then it runs that same discipline across a dozen agent runtimes from one portable `.agents/` directory.
|
|
12
12
|
|
|
13
|
-
|
|
13
|
+
Follow [Quick Start](https://github.com/first-fluke/oh-my-agent/blob/main/web/docs/getting-started/quick-start.md) to choose a skill preset, run `oma doctor`, and ask a named skill for one scoped change. Record the file, check command, and exit status.
|
|
14
14
|
|
|
15
15
|
|
|
16
16
|
|
|
@@ -18,17 +18,7 @@ Start with the existing [Quick Start](https://github.com/first-fluke/oh-my-agent
|
|
|
18
18
|
|
|
19
19
|
## Quick Start
|
|
20
20
|
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
```bash
|
|
24
|
-
npx skills add first-fluke/oh-my-agent
|
|
25
|
-
```
|
|
26
|
-
|
|
27
|
-
That installs the OMA skill pack into detected agent runtimes. Skills teach the agent how to work; the full harness (below) is what checks whether the work actually happened — stop-hook gates, artifact verification, independent judges, and an append-only event log.
|
|
28
|
-
|
|
29
|
-
### Full harness (gates, hooks, CLI)
|
|
30
|
-
|
|
31
|
-
Use this when you want workflows, rules, `oma-config.yaml`, keyword-detection hooks, and `oma agent spawn` — not just skills.
|
|
21
|
+
Run the OMA installer and choose a skill preset for your project.
|
|
32
22
|
|
|
33
23
|
The install scripts auto-install bun, uv, and serena if they're missing.
|
|
34
24
|
|
|
@@ -47,24 +37,6 @@ irm https://raw.githubusercontent.com/first-fluke/oh-my-agent/main/cli/install.p
|
|
|
47
37
|
bunx oh-my-agent@latest
|
|
48
38
|
```
|
|
49
39
|
|
|
50
|
-
<details>
|
|
51
|
-
<summary>Or install skills with Microsoft's <a href="https://github.com/microsoft/apm">Agent Package Manager</a> (APM). Click to expand.</summary>
|
|
52
|
-
|
|
53
|
-
> Not to be confused with `oma-observability`'s APM (Application Performance Monitoring).
|
|
54
|
-
|
|
55
|
-
```bash
|
|
56
|
-
# All skills, deployed to every detected runtime
|
|
57
|
-
# (.claude, .cursor, .codex, .opencode, .github, .agents)
|
|
58
|
-
apm install first-fluke/oh-my-agent
|
|
59
|
-
|
|
60
|
-
# A single skill
|
|
61
|
-
apm install first-fluke/oh-my-agent/.agents/skills/oma-frontend
|
|
62
|
-
```
|
|
63
|
-
|
|
64
|
-
APM ships skills only. For the full harness, use `bunx oh-my-agent@latest` (or the scripts above). Prefer one distribution path per project to avoid drift — if you already used `npx skills add`, stick with skills-only unless you need gates/hooks/CLI.
|
|
65
|
-
|
|
66
|
-
</details>
|
|
67
|
-
|
|
68
40
|
Pick a preset and you're ready:
|
|
69
41
|
|
|
70
42
|
| Preset | What You Get |
|