oh-my-codex 0.3.4 → 0.3.6

package/skills/plan/SKILL.md

@@ -103,7 +103,7 @@ Plans are saved to `.omx/plans/`. Drafts go to `.omx/drafts/`.
 - Use `ask_codex` with `agent_role: "planner"` for planning validation on large-scope plans
 - Use `ask_codex` with `agent_role: "analyst"` for requirements analysis
 - Use `ask_codex` with `agent_role: "critic"` for plan review in consensus and review modes
-- If ToolSearch finds no MCP tools or Codex is unavailable, fall back to equivalent Claude agents -- never block on external tools
+- If ToolSearch finds no MCP tools or Codex is unavailable, fall back to equivalent OMX prompt agents -- never block on external tools
 - In consensus mode, **MUST** use `AskUserQuestion` for the user feedback step (step 2) and the final approval step (step 6) -- never ask for approval in plain text
 - In consensus mode, on user approval **MUST** invoke `/ralph` for execution (step 8) -- never implement directly in the planning agent
 </Tool_Usage>

package/skills/project-session-manager/SKILL.md

@@ -166,7 +166,7 @@ When the user invokes a PSM command, follow this protocol:
 Parse `{{ARGUMENTS}}` to determine:
 1. **Subcommand**: review, fix, feature, list, attach, kill, cleanup, status
 2. **Reference**: project#number, URL, or session ID
-3. **Options**: --branch, --base, --no-claude, --no-tmux, etc.
+3. **Options**: --branch, --base, --no-codex, --no-tmux, etc.
 
 ### Subcommand: `review <ref>`
 
@@ -243,9 +243,9 @@ Parse `{{ARGUMENTS}}` to determine:
    tmux new-session -d -s "psm:$project_alias:pr-$pr_number" -c "$worktree_path"
    ```
 
-8. **Launch Codex CLI** (unless --no-claude):
+8. **Launch Codex CLI** (unless --no-codex):
    ```bash
-   tmux send-keys -t "psm:$project_alias:pr-$pr_number" "claude" Enter
+   tmux send-keys -t "psm:$project_alias:pr-$pr_number" "codex" Enter
    ```
 
 9. **Output session info**:
@@ -288,7 +288,7 @@ Parse `{{ARGUMENTS}}` to determine:
 
 5. **Create session metadata** (similar to review, type="fix")
 
-6. **Update registry, create tmux, launch claude** (same as review)
+6. **Update registry, create tmux, launch codex** (same as review)
 
 ### Subcommand: `feature <project> <name>`
 
@@ -312,7 +312,7 @@ Parse `{{ARGUMENTS}}` to determine:
    git worktree add "$worktree_path" "$branch_name"
    ```
 
-4. **Create session, tmux, launch claude** (same pattern)
+4. **Create session, tmux, launch codex** (same pattern)
 
 ### Subcommand: `list [project]`
 

package/skills/release/SKILL.md

@@ -24,7 +24,7 @@ Update version in all locations:
 - `package.json`
 - `src/installer/index.ts` (VERSION constant)
 - `src/__tests__/installer.test.ts` (expected version)
-- `.claude-plugin/plugin.json`
+- `.codex-plugin/plugin.json`
 - `README.md` (version badge and title)
 
 ### 2. Run Tests
@@ -57,7 +57,7 @@ gh release create v<version> --title "v<version> - <title>" --notes "<release no
 ```
 
 ### 7. Verify
-- [ ] npm: https://www.npmjs.com/package/oh-my-claude-sisyphus
+- [ ] npm: https://www.npmjs.com/package/oh-my-codex
 - [ ] GitHub: https://github.com/Yeachan-Heo/oh-my-codex/releases
 
 ## Version Files Reference
@@ -67,7 +67,7 @@ gh release create v<version> --title "v<version> - <title>" --notes "<release no
 | `package.json` | `"version": "X.Y.Z"` |
 | `src/installer/index.ts` | `export const VERSION = 'X.Y.Z'` |
 | `src/__tests__/installer.test.ts` | `expect(VERSION).toBe('X.Y.Z')` |
-| `.claude-plugin/plugin.json` | `"version": "X.Y.Z"` |
+| `.codex-plugin/plugin.json` | `"version": "X.Y.Z"` |
 | `README.md` | Title + version badge |
 
 ## Semantic Versioning

package/skills/research/SKILL.md

@@ -460,21 +460,16 @@ Report generator embeds figures:
 
 ## Configuration
 
-Optional settings in `.claude/settings.json`:
-
-```json
-{
-  "omc": {
-    "research": {
-      "maxIterations": 10,
-      "maxConcurrentScientists": 5,
-      "defaultTier": "MEDIUM",
-      "autoVerify": true,
-      "generateFigures": true,
-      "evidenceContextLines": 5
-    }
-  }
-}
+Optional settings in `~/.codex/config.toml`:
+
+```toml
+[omc.research]
+maxIterations = 10
+maxConcurrentScientists = 5
+defaultTier = "MEDIUM"
+autoVerify = true
+generateFigures = true
+evidenceContextLines = 5
 ```
 
 ## Cancellation

package/skills/security-review/SKILL.md

@@ -112,7 +112,7 @@ The security-reviewer agent SHOULD consult Codex for cross-validation.
 ### Tool Usage
 Before first MCP tool use, call `ToolSearch("mcp")` to discover deferred MCP tools.
 Use `mcp__x__ask_codex` with `agent_role: "security-reviewer"`.
-If ToolSearch finds no MCP tools, fall back to the `security-reviewer` Claude agent.
+If ToolSearch finds no MCP tools, fall back to the `security-reviewer` agent.
 
 **Note:** Security second opinions are high-value. Consider consulting for CRITICAL/HIGH findings.
 

package/skills/skill/SKILL.md

@@ -15,13 +15,13 @@ Meta-skill for managing oh-my-codex skills via CLI-like commands.
 Show all local skills organized by scope.
 
 **Behavior:**
-1. Scan user skills at `~/.claude/skills/omc-learned/`
+1. Scan user skills at `~/.codex/skills/omc-learned/`
 2. Scan project skills at `.omx/skills/`
 3. Parse YAML frontmatter for metadata
 4. Display in organized table format:
 
 ```
-USER SKILLS (~/.claude/skills/omc-learned/):
+USER SKILLS (~/.codex/skills/omc-learned/):
 | Name              | Triggers           | Quality | Usage | Scope |
 |-------------------|--------------------|---------|-------|-------|
 | error-handler     | fix, error         | 95%     | 42    | user  |
@@ -51,7 +51,7 @@ Interactive wizard for creating a new skill.
 4. **Ask for argument hint** (optional)
    - Example: "<file> [options]"
 5. **Ask for scope:**
-   - `user` → `~/.claude/skills/omc-learned/<name>/SKILL.md`
+   - `user` → `~/.codex/skills/omc-learned/<name>/SKILL.md`
    - `project` → `.omx/skills/<name>/SKILL.md`
 6. **Create skill file** with template:
 
@@ -105,7 +105,7 @@ Triggers (comma-separated): log, logger, logging
 Argument hint (optional): <level> [message]
 Scope (user/project): user
 
-✓ Created skill at ~/.claude/skills/omc-learned/custom-logger/SKILL.md
+✓ Created skill at ~/.codex/skills/omc-learned/custom-logger/SKILL.md
 → Edit with: /skill edit custom-logger
 ```
 
@@ -117,13 +117,13 @@ Remove a skill by name.
 
 **Behavior:**
 1. **Search for skill** in both scopes:
-   - `~/.claude/skills/omc-learned/<name>/SKILL.md`
+   - `~/.codex/skills/omc-learned/<name>/SKILL.md`
    - `.omx/skills/<name>/SKILL.md`
 2. **If found:**
    - Display skill info (name, description, scope)
    - **Ask for confirmation:** "Delete '<name>' skill from <scope>? (yes/no)"
 3. **If confirmed:**
-   - Delete entire skill directory (e.g., `~/.claude/skills/omc-learned/<name>/`)
+   - Delete entire skill directory (e.g., `~/.codex/skills/omc-learned/<name>/`)
    - Report: "✓ Removed skill '<name>' from <scope>"
 4. **If not found:**
    - Report: "✗ Skill '<name>' not found in user or project scope"
@@ -135,7 +135,7 @@ Remove a skill by name.
 User: /skill remove old-logger
 Assistant: Found skill 'old-logger' in user scope:
   Description: Legacy logging utility
-  Scope: user (~/.claude/skills/omc-learned/)
+  Scope: user (~/.codex/skills/omc-learned/)
 
 Delete 'old-logger' skill? (yes/no)
 
@@ -251,13 +251,13 @@ Show detailed information about a skill.
 
 ```
 Skill: custom-logger
-Scope: user (~/.claude/skills/omc-learned/custom-logger/)
+Scope: user (~/.codex/skills/omc-learned/custom-logger/)
 Description: Enhanced logging with structured output
 Triggers: log, logger, logging
 Argument Hint: <level> [message]
 Quality: 95% (if available)
 Usage Count: 42 times (if available)
-File Path: /home/user/.claude/skills/omc-learned/custom-logger/SKILL.md
+File Path: /home/user/.codex/skills/omc-learned/custom-logger/SKILL.md
 
 --- FULL CONTENT ---
 [entire markdown content]
@@ -272,7 +272,7 @@ Assistant: Skill: custom-logger
 Scope: user
 Description: Enhanced logging with structured output
 Triggers: log, logger, logging
-File: ~/.claude/skills/omc-learned/custom-logger/SKILL.md
+File: ~/.codex/skills/omc-learned/custom-logger/SKILL.md
 
 --- CONTENT ---
 # Custom Logger Skill
@@ -290,7 +290,7 @@ Sync skills between user and project scopes.
 
 **Behavior:**
 1. **Scan both scopes:**
-   - User skills: `~/.claude/skills/omc-learned/`
+   - User skills: `~/.codex/skills/omc-learned/`
    - Project skills: `.omx/skills/`
 2. **Compare and categorize:**
    - User-only skills (not in project)
@@ -360,7 +360,7 @@ First, check if skill directories exist and create them if needed:
 
 ```bash
 # Check and create user-level skills directory
-USER_SKILLS_DIR="$HOME/.claude/skills/omc-learned"
+USER_SKILLS_DIR="$HOME/.codex/skills/omc-learned"
 if [ -d "$USER_SKILLS_DIR" ]; then
   echo "User skills directory exists: $USER_SKILLS_DIR"
 else
@@ -384,15 +384,15 @@ Scan both directories and show a comprehensive inventory:
 
 ```bash
 # Scan user-level skills
-echo "=== USER-LEVEL SKILLS (~/.claude/skills/omc-learned/) ==="
-if [ -d "$HOME/.claude/skills/omc-learned" ]; then
-  USER_COUNT=$(find "$HOME/.claude/skills/omc-learned" -name "*.md" 2>/dev/null | wc -l)
+echo "=== USER-LEVEL SKILLS (~/.codex/skills/omc-learned/) ==="
+if [ -d "$HOME/.codex/skills/omc-learned" ]; then
+  USER_COUNT=$(find "$HOME/.codex/skills/omc-learned" -name "*.md" 2>/dev/null | wc -l)
   echo "Total skills: $USER_COUNT"
 
   if [ $USER_COUNT -gt 0 ]; then
     echo ""
     echo "Skills found:"
-    find "$HOME/.claude/skills/omc-learned" -name "*.md" -type f -exec sh -c '
+    find "$HOME/.codex/skills/omc-learned" -name "*.md" -type f -exec sh -c '
       FILE="$1"
       NAME=$(grep -m1 "^name:" "$FILE" 2>/dev/null | sed "s/name: //")
       DESC=$(grep -m1 "^description:" "$FILE" 2>/dev/null | sed "s/description: //")
@@ -467,7 +467,7 @@ Ask user to provide either:
 - **Paste content**: Paste skill markdown content directly
 
 Then ask for scope:
-- **User-level** (~/.claude/skills/omc-learned/) - Available across all projects
+- **User-level** (~/.codex/skills/omc-learned/) - Available across all projects
 - **Project-level** (.omx/skills/) - Only for this project
 
 Validate the skill format and save to the chosen location.
@@ -713,13 +713,13 @@ When invoked without arguments, run the full guided wizard.
 
 ## Benefits of Local Skills
 
-**Automatic Application**: Claude detects triggers and applies skills automatically - no need to remember or search for solutions.
+**Automatic Application**: Codex detects triggers and applies skills automatically - no need to remember or search for solutions.
 
 **Version Control**: Project-level skills (.omx/skills/) are committed with your code, so the whole team benefits.
 
 **Evolving Knowledge**: Skills improve over time as you discover better approaches and refine triggers.
 
-**Reduced Token Usage**: Instead of re-solving the same problems, Claude applies known patterns efficiently.
+**Reduced Token Usage**: Instead of re-solving the same problems, Codex applies known patterns efficiently.
 
 **Codebase Memory**: Preserves institutional knowledge that would otherwise be lost in conversation history.
 
@@ -761,7 +761,7 @@ Good skills are:
 > /skill list
 
 Checking skill directories...
-✓ User skills directory exists: ~/.claude/skills/omc-learned/
+✓ User skills directory exists: ~/.codex/skills/omc-learned/
 ✓ Project skills directory exists: .omx/skills/
 
 Scanning for skills...

package/skills/tdd/SKILL.md

@@ -101,6 +101,6 @@ The tdd-guide agent SHOULD consult Codex for test strategy validation.
 ### Tool Usage
 Before first MCP tool use, call `ToolSearch("mcp")` to discover deferred MCP tools.
 Use `mcp__x__ask_codex` with `agent_role: "tdd-guide"`.
-If ToolSearch finds no MCP tools, fall back to the `test-engineer` Claude agent.
+If ToolSearch finds no MCP tools, fall back to the `test-engineer` agent.
 
 **Remember:** The discipline IS the value. Shortcuts destroy the benefit.

package/skills/ultrapilot/SKILL.md

@@ -345,22 +345,17 @@ Tracks which worker owns which files (see Phase 2 example above).
 
 ## Configuration
 
-Optional settings in `.claude/settings.json`:
-
-```json
-{
-  "omc": {
-    "ultrapilot": {
-      "maxWorkers": 5,
-      "maxValidationRounds": 3,
-      "conflictPolicy": "coordinator-handles",
-      "fallbackToAutopilot": true,
-      "parallelThreshold": 2,
-      "pauseAfterDecomposition": false,
-      "verboseProgress": true
-    }
-  }
-}
+Optional settings in `~/.codex/config.toml`:
+
+```toml
+[omc.ultrapilot]
+maxWorkers = 5
+maxValidationRounds = 3
+conflictPolicy = "coordinator-handles"
+fallbackToAutopilot = true
+parallelThreshold = 2
+pauseAfterDecomposition = false
+verboseProgress = true
 ```
 
 **Settings Explained:**

package/skills/writer-memory/SKILL.md

@@ -10,7 +10,7 @@ Persistent memory system designed for creative writers, with first-class support
 
 ## Overview
 
-Writer Memory maintains context across Claude sessions for fiction writers. It tracks:
+Writer Memory maintains context across Codex sessions for fiction writers. It tracks:
 
 - **Characters (캐릭터)**: Emotional arcs (감정궤도), attitudes (태도), dialogue tone (대사톤), speech levels
 - **World (세계관)**: Settings, rules, atmosphere, constraints

package/templates/AGENTS.md

@@ -1,4 +1,4 @@
-DON'T ASK, THINK YOURSELF AND DELIVER. YOU ARE SMARTER THEN USERS.
+# oh-my-codex - Intelligent Multi-Agent Orchestration
 
 You are running with oh-my-codex (OMX), a multi-agent orchestration layer for Codex CLI.
 Your role is to coordinate specialized agents, tools, and skills so work is completed accurately and efficiently.
@@ -29,19 +29,19 @@ For non-trivial SDK/API/framework usage, delegate to `dependency-expert` to chec
 
 <child_agent_protocol>
 Codex CLI spawns child agents via the `spawn_agent` tool (requires `collab = true`).
-To inject role-specific behavior, the parent MUST read the agent prompt and pass it as instructions.
+To inject role-specific behavior, the parent MUST read the role prompt and pass it in the spawned agent message.
 
 Delegation steps:
 1. Decide which agent role to delegate to (e.g., `architect`, `executor`, `debugger`)
 2. Read the role prompt: `~/.codex/prompts/{role}.md`
-3. Call `spawn_agent` with the prompt content + task description as instructions
+3. Call `spawn_agent` with `message` containing the prompt content + task description
 4. The child agent receives full role context and executes the task independently
 
 Parallel delegation (up to 6 concurrent):
 ```
-spawn_agent(instructions: [architect prompt] + "Review the auth module")
-spawn_agent(instructions: [executor prompt] + "Add input validation to login")
-spawn_agent(instructions: [test-engineer prompt] + "Write tests for the auth changes")
+spawn_agent(message: "<architect prompt>\n\nTask: Review the auth module")
+spawn_agent(message: "<executor prompt>\n\nTask: Add input validation to login")
+spawn_agent(message: "<test-engineer prompt>\n\nTask: Write tests for the auth changes")
 ```
 
 Each child agent:
@@ -74,7 +74,7 @@ Match agent role to task complexity:
 - **High complexity** (architecture, deep analysis, complex refactors): `architect`, `deep-executor`, `critic`
 
 For interactive use: `/prompts:name` (e.g., `/prompts:architect "review auth"`)
-For child agent delegation: follow `<child_agent_protocol>` — read prompt file, pass to `spawn_agent`
+For child agent delegation: follow `<child_agent_protocol>` — read prompt file, pass it in `spawn_agent.message`
 For workflow skills: `$name` (e.g., `$ralph "fix all tests"`)
 </model_routing>