oh-my-codex 0.4.3 → 0.5.0

package/skills/omx-setup/SKILL.md

@@ -10,36 +10,45 @@ Use this skill when users want to install or refresh oh-my-codex for the **curre
 ## Command
 
 ```bash
-omx setup [--force] [--dry-run] [--verbose]
+omx setup [--force] [--dry-run] [--verbose] [--scope <user|project-local|project>]
 ```
 
 Supported setup flags (current implementation):
 - `--force`: overwrite/reinstall managed artifacts where applicable
 - `--dry-run`: print actions without mutating files
 - `--verbose`: print per-file/per-step details
+- `--scope`: choose install scope (`user`, `project-local`, `project`)
 
 ## What this setup actually does
 
 `omx setup` performs these steps:
 
-1. Create directories:
-   - `~/.codex/`
-   - `~/.codex/prompts/`
-   - `~/.agents/skills/`
-   - `./.omx/state/`, `./.omx/plans/`, `./.omx/logs/`
-2. Install agent prompt files from repo `prompts/*.md` to `~/.codex/prompts/`
-3. Remove legacy skill-prompt shim files from `~/.codex/prompts/` when detected
-4. Install skills from repo `skills/*` to `~/.agents/skills/*`
-5. Merge OMX config into `~/.codex/config.toml`
+1. Resolve setup scope:
+   - `--scope` explicit value
+   - else persisted `./.omx/setup-scope.json`
+   - else interactive prompt on TTY (default `user`)
+   - else default `user` (safe for CI/tests)
+2. Create project OMX directories (`./.omx/state`, `./.omx/plans`, `./.omx/logs`) and persist effective scope
+3. For `user`/`project-local` scope:
+   - install prompts
+   - remove legacy prompt shims
+   - install native agent configs
+   - install skills
+   - merge OMX config.toml
+4. For `project` scope: skip prompt/skill/config/native-agent installs with console messages
 6. Verify required team MCP comm tool exports exist in built `dist/mcp/state-server.js`
 7. Generate project-root `./AGENTS.md` from `templates/AGENTS.md` (or skip when existing and no force)
 8. Configure notify hook references and write `./.omx/hud-config.json`
 
 ## Important behavior notes
 
-- `omx setup` is **not** an interactive wizard in current code.
+- `omx setup` only prompts for scope when no scope is provided/persisted and stdin/stdout are TTY.
 - Local project orchestration file is `./AGENTS.md` (project root).
-- Prompts/skills are installed to user directories (`~/.codex/prompts`, `~/.agents/skills`).
+- Scope targets:
+  - `user`: user directories (`~/.codex`, `~/.agents/skills`, `~/.omx/agents`)
+  - `project-local`: local directories (`./.codex`, `./.agents/skills`, `./.omx/agents`)
+  - `project`: project-only OMX setup (`./.omx/*`, `AGENTS.md`, HUD)
+- If persisted scope is `project-local`, `omx` launch automatically uses `CODEX_HOME=./.codex` unless user explicitly overrides `CODEX_HOME`.
 - With `--force`, AGENTS overwrite may still be skipped if an active OMX session is detected (safety guard).
 
 ## Recommended workflow
@@ -61,11 +70,11 @@ omx doctor
 ## Expected verification indicators
 
 From `omx doctor`, expect:
-- Prompts installed (30)
-- Skills installed (40)
+- Prompts installed (scope-dependent: user or project-local)
+- Skills installed (scope-dependent: user or project-local)
 - AGENTS.md found in project root
 - `.omx/state` exists
-- OMX MCP servers configured in `~/.codex/config.toml`
+- OMX MCP servers configured in scope target `config.toml` (`~/.codex/config.toml` or `./.codex/config.toml`)
 
 ## Troubleshooting
 

package/skills/research/SKILL.md

@@ -1,19 +1,19 @@
 ---
 name: research
-description: Orchestrate parallel scientist agents for comprehensive research with AUTO mode
+description: Orchestrate parallel researcher agents for comprehensive research with AUTO mode
 argument-hint: <research goal>
 ---
 
 # Research Skill
 
-Orchestrate parallel scientist agents for comprehensive research workflows with optional AUTO mode for fully autonomous execution.
+Orchestrate parallel researcher agents for comprehensive research workflows with optional AUTO mode for fully autonomous execution.
 
 ## Overview
 
 Research is a multi-stage workflow that decomposes complex research goals into parallel investigations:
 
 1. **Decomposition** - Break research goal into independent stages/hypotheses
-2. **Execution** - Run parallel scientist agents on each stage
+2. **Execution** - Run parallel researcher agents on each stage
 3. **Verification** - Cross-validate findings, check consistency
 4. **Synthesis** - Aggregate results into comprehensive report
 
@@ -57,19 +57,19 @@ When given a research goal, decompose into 3-7 independent stages:
 ...
 ```
 
-### Parallel Scientist Invocation
+### Parallel Researcher Invocation
 
 Fire independent stages in parallel via sub-agent spawning:
 
 ```
 // Stage 1 - Simple data gathering
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="haiku", prompt="[RESEARCH_STAGE:1] Investigate...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="haiku", prompt="[RESEARCH_STAGE:1] Investigate...")
 
 // Stage 2 - Standard analysis
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="sonnet", prompt="[RESEARCH_STAGE:2] Analyze...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="sonnet", prompt="[RESEARCH_STAGE:2] Analyze...")
 
 // Stage 3 - Complex reasoning
-spawn_sub_agent(subagent_type="oh-my-codex:scientist-high", model="opus", prompt="[RESEARCH_STAGE:3] Deep analysis of...")
+spawn_sub_agent(subagent_type="oh-my-codex:architect", model="opus", prompt="[RESEARCH_STAGE:3] Deep analysis of...")
 ```
 
 ### Smart Model Routing
@@ -78,9 +78,9 @@ spawn_sub_agent(subagent_type="oh-my-codex:scientist-high", model="opus", prompt
 
 | Task Complexity | Agent | Model | Use For |
 |-----------------|-------|-------|---------|
-| Data gathering | `scientist` (model=haiku) | haiku | File enumeration, pattern counting, simple lookups |
-| Standard analysis | `scientist` | sonnet | Code analysis, pattern detection, documentation review |
-| Complex reasoning | `scientist-high` | opus | Architecture analysis, cross-cutting concerns, hypothesis validation |
+| Data gathering | `researcher` (model=haiku) | haiku | File enumeration, pattern counting, simple lookups |
+| Standard analysis | `researcher` | sonnet | Code analysis, pattern detection, documentation review |
+| Complex reasoning | `architect` | opus | Architecture analysis, cross-cutting concerns, hypothesis validation |
 
 ### Routing Decision Guide
 
@@ -99,7 +99,7 @@ After parallel execution completes, verify findings:
 
 ```
 // Cross-validation stage
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="sonnet", prompt="
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="sonnet", prompt="
 [RESEARCH_VERIFICATION]
 Cross-validate these findings for consistency:
 
@@ -180,9 +180,9 @@ When stages analyze different data sources:
 
 ```
 // All fire simultaneously
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="haiku", prompt="[STAGE:1] Analyze src/api/...")
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="haiku", prompt="[STAGE:2] Analyze src/utils/...")
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="haiku", prompt="[STAGE:3] Analyze src/components/...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="haiku", prompt="[STAGE:1] Analyze src/api/...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="haiku", prompt="[STAGE:2] Analyze src/utils/...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="haiku", prompt="[STAGE:3] Analyze src/components/...")
 ```
 
 ### Hypothesis Battery (Parallel)
@@ -191,9 +191,9 @@ When testing multiple hypotheses:
 
 ```
 // Test hypotheses simultaneously
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="sonnet", prompt="[HYPOTHESIS:A] Test if caching improves...")
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="sonnet", prompt="[HYPOTHESIS:B] Test if batching reduces...")
-spawn_sub_agent(subagent_type="oh-my-codex:scientist", model="sonnet", prompt="[HYPOTHESIS:C] Test if lazy loading helps...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="sonnet", prompt="[HYPOTHESIS:A] Test if caching improves...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="sonnet", prompt="[HYPOTHESIS:B] Test if batching reduces...")
+spawn_sub_agent(subagent_type="oh-my-codex:researcher", model="sonnet", prompt="[HYPOTHESIS:C] Test if lazy loading helps...")
 ```
 
 ### Cross-Validation (Sequential)
@@ -205,7 +205,7 @@ When verification depends on all findings:
 [stages complete]
 
 // Then sequential verification
-spawn_sub_agent(subagent_type="oh-my-codex:scientist-high", model="opus", prompt="
+spawn_sub_agent(subagent_type="oh-my-codex:architect", model="opus", prompt="
 [CROSS_VALIDATION]
 Validate consistency across all findings:
 - Finding 1: ...
@@ -216,7 +216,7 @@ Validate consistency across all findings:
 
 ### Concurrency Limit
 
-**Maximum 20 concurrent scientist agents** to prevent resource exhaustion.
+**Maximum 20 concurrent researcher agents** to prevent resource exhaustion.
 
 If more than 20 stages, batch them:
 ```
@@ -237,7 +237,7 @@ Batch 2: Stages 6-7 (parallel)
     stage-2.md            # Stage 2 findings
     ...
   findings/
-    raw/                  # Raw findings from scientists
+    raw/                  # Raw findings from researchers
     verified/             # Post-verification findings
   figures/
     figure-1.png          # Generated visualizations
@@ -289,7 +289,7 @@ Batch 2: Stages 6-7 (parallel)
 
 ## Tag Extraction
 
-Scientists use structured tags for findings. Extract them with these patterns:
+Research agents use structured tags for findings. Extract them with these patterns:
 
 ### Finding Tags
 
@@ -427,7 +427,7 @@ Findings must meet quality threshold:
 
 ### Figure Embedding Protocol
 
-Scientists generate visualizations using this marker:
+Research agents generate visualizations using this marker:
 
 ```
 [FIGURE:path/to/figure.png]
@@ -452,11 +452,11 @@ Report generator embeds figures:
 
 | Type | Use For | Generated By |
 |------|---------|--------------|
-| Architecture diagram | System structure | scientist-high |
-| Flow chart | Process flows | scientist |
-| Dependency graph | Module relationships | scientist |
-| Timeline | Sequence of events | scientist |
-| Comparison table | A vs B analysis | scientist |
+| Architecture diagram | System structure | architect |
+| Flow chart | Process flows | researcher |
+| Dependency graph | Module relationships | researcher |
+| Timeline | Sequence of events | researcher |
+| Comparison table | A vs B analysis | researcher |
 
 ## Configuration
 
@@ -489,7 +489,7 @@ Progress is preserved in `.omx/research/{session-id}/` for resume.
 - Review state.json for specific conflicts
 - May need to re-run specific stages with different approach
 
-**Scientists returning low-quality findings?**
+**Research agents returning low-quality findings?**
 - Check tier assignment - complex analysis needs HIGH tier
 - Ensure prompts include clear scope and expected output format
 - Review if research goal is too broad

package/skills/security-review/SKILL.md

@@ -256,11 +256,11 @@ The security-reviewer agent verifies:
 
 ## Use with Other Skills
 
-**With Pipeline:**
+**With Team:**
 ```
-/pipeline security "review authentication module"
+/team "run security review on authentication module"
 ```
-Uses: explore → security-reviewer → executor → security-reviewer-low (re-verify)
+Uses: explore → security-reviewer → executor → security-reviewer (re-verify)
 
 **With Swarm:**
 ```

package/templates/AGENTS.md

@@ -39,7 +39,7 @@ Use delegation when it improves quality, speed, or correctness:
 Work directly only for trivial operations where delegation adds disproportionate overhead:
 - Small clarifications, quick status checks, or single-command sequential operations.
 
-For substantive code changes, delegate to `executor` (default for both standard and complex implementation work; `deep-executor` is deprecated).
+For substantive code changes, delegate to `executor` (default for both standard and complex implementation work).
 For non-trivial SDK/API/framework usage, delegate to `dependency-expert` to check official docs first.
 </delegation_rules>
 
@@ -106,7 +106,6 @@ Build/Analysis Lane:
 - `/prompts:architect`: System design, boundaries, interfaces, long-horizon tradeoffs
 - `/prompts:debugger`: Root-cause analysis, regression isolation, failure diagnosis
 - `/prompts:executor`: Code implementation, refactoring, feature work
-- `/prompts:deep-executor`: Deprecated — use `/prompts:executor` for complex autonomous goal-oriented tasks
 - `/prompts:verifier`: Completion evidence, claim validation, test adequacy
 
 Review Lane:
@@ -125,7 +124,6 @@ Domain Specialists:
 - `/prompts:designer`: UX/UI architecture, interaction design
 - `/prompts:writer`: Docs, migration notes, user guidance
 - `/prompts:qa-tester`: Interactive CLI/service runtime validation
-- `/prompts:scientist`: Data/statistical analysis
 - `/prompts:git-master`: Commit strategy, history hygiene
 - `/prompts:researcher`: External documentation and reference research
 
@@ -154,10 +152,8 @@ Do not ask for confirmation — just read the skill file and follow its instruct
 | "plan this", "plan the", "let's plan" | `$plan` | Read `~/.agents/skills/plan/SKILL.md`, start planning workflow |
 | "ralplan", "consensus plan" | `$ralplan` | Read `~/.agents/skills/ralplan/SKILL.md`, start consensus planning |
 | "team", "swarm", "coordinated team", "coordinated swarm" | `$team` | Read `~/.agents/skills/team/SKILL.md`, start team orchestration (swarm compatibility alias) |
-| "pipeline", "chain agents" | `$pipeline` | Read `~/.agents/skills/pipeline/SKILL.md`, start agent pipeline |
 | "ecomode", "eco", "budget" | `$ecomode` | Read `~/.agents/skills/ecomode/SKILL.md`, enable token-efficient mode |
 | "research", "analyze data" | `$research` | Read `~/.agents/skills/research/SKILL.md`, start parallel research |
-| "deepinit" | `$deepinit` | Read `~/.agents/skills/deepinit/SKILL.md`, initialize codebase docs |
 | "cancel", "stop", "abort" | `$cancel` | Read `~/.agents/skills/cancel/SKILL.md`, cancel active modes |
 | "tdd", "test first" | `$tdd` | Read `~/.agents/skills/tdd/SKILL.md`, start test-driven workflow |
 | "fix build", "type errors" | `$build-fix` | Read `~/.agents/skills/build-fix/SKILL.md`, fix build errors |
@@ -183,12 +179,10 @@ Workflow Skills:
 - `ecomode`: Token-efficient execution using lightweight models
 - `team`: N coordinated agents on shared task list
 - `swarm`: N coordinated agents on shared task list (compatibility facade over team)
-- `pipeline`: Sequential agent chaining with data passing
 - `ultraqa`: QA cycling -- test, verify, fix, repeat
 - `plan`: Strategic planning with optional consensus mode
 - `ralplan`: Iterative consensus planning (planner + architect + critic)
 - `research`: Parallel research agents for comprehensive analysis
-- `deepinit`: Deep codebase initialization with documentation
 
 Agent Shortcuts:
 - `analyze` -> debugger: Investigation and root-cause analysis
@@ -349,7 +343,6 @@ Recommended mode fields:
 - `ultrawork`: `active`, `reinforcement_count`, `started_at`
 - `team`: `active`, `current_phase` (`team-plan|team-prd|team-exec|team-verify|team-fix|complete`), `agent_count`, `team_name`
 - `ecomode`: `active`
-- `pipeline`: `active`, `current_phase`, `started_at`, `completed_at`
 - `ultraqa`: `active`, `current_phase`, `iteration`, `started_at`, `completed_at`
 </state_management>