pi-herdsman 0.5.2 → 0.6.0

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 CHANGED
@@ -47,20 +47,29 @@ chief
47
47
 
48
48
  ```sh
49
49
  pi install npm:pi-herdsman
50
+ herdr integration install pi
50
51
  ```
51
52
 
52
- The lead Pi session must run inside herdr.
53
+ Start Herdr in your project:
54
+
55
+ ```sh
56
+ herdr
57
+ ```
53
58
 
54
- ## Try it
59
+ Then run Pi in the Herdr pane:
60
+
61
+ ```sh
62
+ pi
63
+ ```
55
64
 
56
65
  Ask Pi normally:
57
66
 
58
67
  ```text
59
- Use an implementer agent to implement the approved change.
68
+ Use scout to inspect this repository.
60
69
  ```
61
70
 
62
- That is enough. The implementer runs asynchronously while the lead conversation
63
- remains available.
71
+ That's enough. The agent runs asynchronously while the lead conversation remains
72
+ available.
64
73
 
65
74
  Other useful requests look the same:
66
75
 
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: generalist
3
3
  description: General-purpose execution agent for scoped tasks that do not fit scout, researcher, implementer, or reviewer
4
- model: openai-codex/gpt-5.6-luna
5
- thinking: medium
6
4
  agents: ["scout", "researcher"]
7
5
  systemPromptMode: replace
8
6
  inheritProjectContext: true
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: implementer
3
3
  description: Focused implementation agent for a resolved change; use when the required behavior is already decided and the task is to edit, test, and report
4
- model: openai-codex/gpt-5.6-luna
5
- thinking: high
6
4
  agents: ["scout"]
7
5
  systemPromptMode: replace
8
6
  inheritProjectContext: true
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: researcher
3
3
  description: External research specialist for questions that require web, documentation, standards, vendor, or other authoritative evidence beyond the repository; use for current facts, API behavior, comparisons, and source-backed recommendations
4
- model: openai-codex/gpt-5.6-luna
5
- thinking: medium
6
4
  systemPromptMode: replace
7
5
  inheritProjectContext: true
8
6
  inheritGlobalContext: false
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: reviewer
3
3
  description: Independent read-only reviewer for plans, diffs, implementations, and codebase health; use when work needs verification, missing-case analysis, or regression review rather than modification
4
- model: openai-codex/gpt-5.6-luna
5
- thinking: medium
6
4
  agents: ["scout", "researcher"]
7
5
  systemPromptMode: replace
8
6
  inheritProjectContext: true
@@ -1,8 +1,6 @@
1
1
  ---
2
2
  name: scout
3
3
  description: Read-only codebase reconnaissance for unfamiliar areas; use to find entry points, trace flows, dependencies, constraints, and risks before deciding or editing
4
- model: openai-codex/gpt-5.6-luna
5
- thinking: medium
6
4
  systemPromptMode: replace
7
5
  inheritProjectContext: true
8
6
  inheritGlobalContext: false