@graypark/ralph-codex 0.4.1 → 0.4.3

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/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@graypark/ralph-codex",
3
- "version": "0.4.1",
3
+ "version": "0.4.3",
4
4
  "type": "module",
5
5
  "description": "Ralph Loop for Codex CLI & Claude Code — iterative dev loops with multi-agent orchestration, interactive interview, and stop hooks",
6
6
  "license": "MIT",
@@ -5,7 +5,7 @@ description: "Interactive interview that generates optimized /ralph-loop command
5
5
 
6
6
  # Ralph Interview — Command Generator
7
7
 
8
- You are an expert at crafting `/ralph-loop:ralph-loop` commands for Claude Code's Ralph Loop plugin.
8
+ You are an expert at crafting `/ralph-loop:ralph-loop` commands for the Ralph Loop plugin.
9
9
  When the user describes a task, conduct a brief interview to gather missing context, then generate a copy-paste-ready command.
10
10
 
11
11
  ## Core Principles
@@ -68,7 +68,7 @@ Evaluate the task against the ralph-orchestrator decision matrix:
68
68
  - **Score 0–2** → Sequential loop, optional scout phase
69
69
  - **Score < 0** → Single sequential Ralph Loop
70
70
 
71
- When subagents are recommended, embed subagent spawn instructions directly in the generated ralph-loop prompt using the Agent tool (Claude Code) or experimental multi-agent config (Codex CLI).
71
+ When subagents are recommended, embed subagent spawn instructions directly in the generated ralph-loop prompt using Codex's experimental multi-agent capabilities.
72
72
 
73
73
  ### Recommended max-iterations
74
74
 
@@ -131,7 +131,7 @@ When the orchestrator score is >= 3, embed subagent instructions in the prompt:
131
131
  [Task summary]
132
132
 
133
133
  ## Phase 1 — Parallel Exploration
134
- Spawn these subagents simultaneously using the Agent tool:
134
+ Spawn these subagents simultaneously:
135
135
 
136
136
  1. Agent 'scan-frontend' (subagent_type: Explore, run_in_background: true):
137
137
  Search src/frontend/** for [pattern]. Write findings to .ralph/reports/frontend.md
@@ -146,25 +146,6 @@ Execute Phase (Ralph Loop):
146
146
 
147
147
  ## Subagent Configuration Reference
148
148
 
149
- ### Claude Code (Agent tool)
150
-
151
- ```
152
- Agent tool parameters:
153
- - description: "short task description"
154
- - prompt: "detailed instructions"
155
- - subagent_type: "general-purpose" | "Explore" | "Plan" | "coder-fe" | "coder-be" | etc.
156
- - isolation: "worktree" (optional — gives agent an isolated repo copy)
157
- - run_in_background: true (for parallel execution)
158
- - model: "sonnet" | "opus" | "haiku" (optional model override)
159
- ```
160
-
161
- **Best practices:**
162
-
163
- - Use `subagent_type: "Explore"` for read-only scanning — faster and safer
164
- - Use `isolation: "worktree"` when agents write to files — prevents merge conflicts
165
- - Launch parallel agents in a single message with multiple Agent tool calls
166
- - Use `run_in_background: true` for truly independent work streams
167
-
168
149
  ### Codex CLI (experimental)
169
150
 
170
151
  Codex spawns subagents via natural language prompts with keywords: "spawn", "parallel", "delegate", "one agent per".