@plaited/acp 0.1.0 → 0.2.1
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 +22 -7
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -42,9 +42,9 @@ console.log(summary.text, summary.completedToolCalls)
|
|
|
42
42
|
await client.disconnect()
|
|
43
43
|
```
|
|
44
44
|
|
|
45
|
-
## Recommended: Use the Bundled
|
|
45
|
+
## Recommended: Use the Bundled Plugin
|
|
46
46
|
|
|
47
|
-
This package includes a comprehensive **
|
|
47
|
+
This package includes a comprehensive **eval-harness plugin** designed for AI-assisted evaluation development. The plugin provides:
|
|
48
48
|
|
|
49
49
|
- Complete API reference for `createACPClient` and helpers
|
|
50
50
|
- Harness CLI usage with all options and examples
|
|
@@ -53,21 +53,36 @@ This package includes a comprehensive **acp-harness skill** designed for AI-assi
|
|
|
53
53
|
- Downstream integration patterns (Braintrust, jq, custom scorers)
|
|
54
54
|
- Docker execution guidance
|
|
55
55
|
|
|
56
|
-
### Install the
|
|
56
|
+
### Install the Plugin
|
|
57
|
+
|
|
58
|
+
**Claude Code:**
|
|
59
|
+
|
|
60
|
+
```bash
|
|
61
|
+
claude plugins add github:plaited/marketplace
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
Or install directly:
|
|
57
65
|
|
|
58
66
|
```bash
|
|
59
|
-
|
|
60
|
-
|
|
67
|
+
claude plugins add github:plaited/acp-harness/.claude
|
|
68
|
+
```
|
|
69
|
+
|
|
70
|
+
**Other AI coding agents:**
|
|
71
|
+
|
|
72
|
+
```bash
|
|
73
|
+
curl -fsSL https://raw.githubusercontent.com/plaited/marketplace/main/install.sh | bash -s -- --agent <agent-name> --plugin acp-harness
|
|
74
|
+
|
|
75
|
+
Supported agents: gemini, copilot, cursor, opencode, amp, goose, factory
|
|
61
76
|
```
|
|
62
77
|
|
|
63
|
-
Once installed, the
|
|
78
|
+
Once installed, the plugin auto-activates when working on evaluation tasks. Ask your AI agent to help you:
|
|
64
79
|
|
|
65
80
|
- Set up evaluation prompts
|
|
66
81
|
- Configure the harness CLI
|
|
67
82
|
- Design scoring pipelines
|
|
68
83
|
- Integrate with Braintrust or custom analysis tools
|
|
69
84
|
|
|
70
|
-
The
|
|
85
|
+
The plugin contains everything needed to build agent evaluations - use it as your primary reference.
|
|
71
86
|
|
|
72
87
|
## Development
|
|
73
88
|
|