oh-my-codex-cli 0.1.0

package/.agent/skills/electron-driver/scripts/driver-template.js

@@ -0,0 +1,71 @@
+const { chromium } = require('playwright-core');
+
+/**
+ * Electron Driver Template (Attach Mode)
+ * 
+ * Usage:
+ * 1. Ensure Electron is running with --remote-debugging-port=<PORT>
+ * 2. Set CDP_PORT env var if not 9222.
+ * 3. Run with `node script.cjs`
+ */
+
+const CDP_PORT = process.env.CDP_PORT || 9222;
+const CDP_URL = `http://localhost:${CDP_PORT}`;
+
+async function run() {
+  let browser;
+  try {
+    // 1. Connect to the running Electron app
+    // console.log(`Connecting to Electron at ${CDP_URL}...`);
+    browser = await chromium.connectOverCDP(CDP_URL);
+
+    // 2. Find the right context and page
+    // Electron apps typically have one default context.
+    const context = browser.contexts()[0];
+    if (!context) throw new Error('No browser context found.');
+
+    const pages = context.pages();
+
+    // FILTER: Ignore DevTools windows
+    const appPage = pages.find(p => !p.url().startsWith('devtools://'));
+
+    if (!appPage) {
+      throw new Error(`No app window found. Open pages: ${pages.map(p => p.url()).join(', ')}`);
+    }
+
+    // console.log(`Attached to page: "${await appPage.title()}"`);
+
+    // ---------------------------------------------------------
+    // INJECTED LOGIC START
+    // ---------------------------------------------------------
+
+    // Example Modern Usage:
+    // await appPage.getByRole('button', { name: 'Save' }).click();
+    // const status = await appPage.locator('.status-bar').textContent();
+
+    console.log(JSON.stringify({
+      status: 'success',
+      title: await appPage.title(),
+      url: appPage.url(),
+      message: 'Electron Driver connected successfully.'
+    }));
+
+    // ---------------------------------------------------------
+    // INJECTED LOGIC END
+    // ---------------------------------------------------------
+
+  } catch (error) {
+    console.error(JSON.stringify({
+      status: 'error',
+      message: error.message,
+      stack: error.stack
+    }));
+    process.exit(1);
+  } finally {
+    if (browser) {
+      await browser.close();
+    }
+  }
+}
+
+run();

package/.agent/skills/eval/SKILL.md

@@ -0,0 +1,140 @@
+---
+name: eval
+description: Imported from everything-codex command eval
+---
+
+# Eval Command
+
+
+## Native Subagent Protocol (Codex)
+
+Codex supports native subagents. Delegate with `spawn_agent`, coordinate with `send_input`, collect via `wait`, and clean up with `close_agent`.
+
+Execution preference:
+1. Use native subagents first for independent workstreams (parallel when possible).
+2. Merge results in main thread and run final verification.
+3. Fallback only when delegation is blocked: use the `[ANALYST]`/`[ARCHITECT]`/`[EXECUTOR]`/`[REVIEWER]` structure in a single response.
+
+Minimal orchestration pattern:
+```text
+spawn_agent -> send_input (optional) -> wait -> close_agent
+```
+
+Manage eval-driven development workflow.
+
+## Usage
+
+`$eval [define|check|report|list] [feature-name]`
+
+## Define Evals
+
+`$eval define feature-name`
+
+Create a new eval definition:
+
+1. Create `.codex/evals/feature-name.md` with template:
+
+```markdown
+## EVAL: feature-name
+Created: $(date)
+
+### Capability Evals
+- [ ] [Description of capability 1]
+- [ ] [Description of capability 2]
+
+### Regression Evals
+- [ ] [Existing behavior 1 still works]
+- [ ] [Existing behavior 2 still works]
+
+### Success Criteria
+- pass@3 > 90% for capability evals
+- pass^3 = 100% for regression evals
+```
+
+2. Prompt user to fill in specific criteria
+
+## Check Evals
+
+`$eval check feature-name`
+
+Run evals for a feature:
+
+1. Read eval definition from `.codex/evals/feature-name.md`
+2. For each capability eval:
+   - Attempt to verify criterion
+   - Record PASS/FAIL
+   - Log attempt in `.codex/evals/feature-name.log`
+3. For each regression eval:
+   - Run relevant tests
+   - Compare against baseline
+   - Record PASS/FAIL
+4. Report current status:
+
+```
+EVAL CHECK: feature-name
+========================
+Capability: X/Y passing
+Regression: X/Y passing
+Status: IN PROGRESS / READY
+```
+
+## Report Evals
+
+`$eval report feature-name`
+
+Generate comprehensive eval report:
+
+```
+EVAL REPORT: feature-name
+=========================
+Generated: $(date)
+
+CAPABILITY EVALS
+----------------
+[eval-1]: PASS (pass@1)
+[eval-2]: PASS (pass@2) - required retry
+[eval-3]: FAIL - see notes
+
+REGRESSION EVALS
+----------------
+[test-1]: PASS
+[test-2]: PASS
+[test-3]: PASS
+
+METRICS
+-------
+Capability pass@1: 67%
+Capability pass@3: 100%
+Regression pass^3: 100%
+
+NOTES
+-----
+[Any issues, edge cases, or observations]
+
+RECOMMENDATION
+--------------
+[SHIP / NEEDS WORK / BLOCKED]
+```
+
+## List Evals
+
+`$eval list`
+
+Show all eval definitions:
+
+```
+EVAL DEFINITIONS
+================
+feature-auth      [3/5 passing] IN PROGRESS
+feature-search    [5/5 passing] READY
+feature-export    [0/4 passing] NOT STARTED
+```
+
+## Arguments
+
+$ARGUMENTS:
+- `define <name>` - Create new eval definition
+- `check <name>` - Run and check evals
+- `report <name>` - Generate full report
+- `list` - Show all evals
+- `clean` - Remove old eval logs (keeps last 10 runs)

package/.agent/skills/eval-harness/SKILL.md

@@ -0,0 +1,242 @@
+---
+name: eval-harness
+description: Formal evaluation framework for Codex sessions implementing eval-driven development (EDD) principles
+tools: Read, Write, Edit, Bash, Grep, Glob
+---
+
+# Eval Harness Skill
+
+
+## Native Subagent Protocol (Codex)
+
+Codex supports native subagents. Delegate with `spawn_agent`, coordinate with `send_input`, collect via `wait`, and clean up with `close_agent`.
+
+Execution preference:
+1. Use native subagents first for independent workstreams (parallel when possible).
+2. Merge results in main thread and run final verification.
+3. Fallback only when delegation is blocked: use the `[ANALYST]`/`[ARCHITECT]`/`[EXECUTOR]`/`[REVIEWER]` structure in a single response.
+
+Minimal orchestration pattern:
+```text
+spawn_agent -> send_input (optional) -> wait -> close_agent
+```
+
+A formal evaluation framework for Codex sessions, implementing eval-driven development (EDD) principles.
+
+## Philosophy
+
+Eval-Driven Development treats evals as the "unit tests of AI development":
+- Define expected behavior BEFORE implementation
+- Run evals continuously during development
+- Track regressions with each change
+- Use pass@k metrics for reliability measurement
+
+## Eval Types
+
+### Capability Evals
+Test if Codex can do something it couldn't before:
+```markdown
+[CAPABILITY EVAL: feature-name]
+Task: Description of what Codex should accomplish
+Success Criteria:
+  - [ ] Criterion 1
+  - [ ] Criterion 2
+  - [ ] Criterion 3
+Expected Output: Description of expected result
+```
+
+### Regression Evals
+Ensure changes don't break existing functionality:
+```markdown
+[REGRESSION EVAL: feature-name]
+Baseline: SHA or checkpoint name
+Tests:
+  - existing-test-1: PASS/FAIL
+  - existing-test-2: PASS/FAIL
+  - existing-test-3: PASS/FAIL
+Result: X/Y passed (previously Y/Y)
+```
+
+## Grader Types
+
+### 1. Code-Based Grader
+Deterministic checks using code:
+```bash
+# Check if file contains expected pattern
+grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"
+
+# Check if tests pass
+npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"
+
+# Check if build succeeds
+npm run build && echo "PASS" || echo "FAIL"
+```
+
+### 2. Model-Based Grader
+Use Codex to evaluate open-ended outputs:
+```markdown
+[MODEL GRADER PROMPT]
+Evaluate the following code change:
+1. Does it solve the stated problem?
+2. Is it well-structured?
+3. Are edge cases handled?
+4. Is error handling appropriate?
+
+Score: 1-5 (1=poor, 5=excellent)
+Reasoning: [explanation]
+```
+
+### 3. Human Grader
+Flag for manual review:
+```markdown
+[HUMAN REVIEW REQUIRED]
+Change: Description of what changed
+Reason: Why human review is needed
+Risk Level: LOW/MEDIUM/HIGH
+```
+
+## Metrics
+
+### pass@k
+"At least one success in k attempts"
+- pass@1: First attempt success rate
+- pass@3: Success within 3 attempts
+- Typical target: pass@3 > 90%
+
+### pass^k
+"All k trials succeed"
+- Higher bar for reliability
+- pass^3: 3 consecutive successes
+- Use for critical paths
+
+## Eval Workflow
+
+### 1. Define (Before Coding)
+```markdown
+## EVAL DEFINITION: feature-xyz
+
+### Capability Evals
+1. Can create new user account
+2. Can validate email format
+3. Can hash password securely
+
+### Regression Evals
+1. Existing login still works
+2. Session management unchanged
+3. Logout flow intact
+
+### Success Metrics
+- pass@3 > 90% for capability evals
+- pass^3 = 100% for regression evals
+```
+
+### 2. Implement
+Write code to pass the defined evals.
+
+### 3. Evaluate
+```bash
+# Run capability evals
+[Run each capability eval, record PASS/FAIL]
+
+# Run regression evals
+npm test -- --testPathPattern="existing"
+
+# Generate report
+```
+
+### 4. Report
+```markdown
+EVAL REPORT: feature-xyz
+========================
+
+Capability Evals:
+  create-user:     PASS (pass@1)
+  validate-email:  PASS (pass@2)
+  hash-password:   PASS (pass@1)
+  Overall:         3/3 passed
+
+Regression Evals:
+  login-flow:      PASS
+  session-mgmt:    PASS
+  logout-flow:     PASS
+  Overall:         3/3 passed
+
+Metrics:
+  pass@1: 67% (2/3)
+  pass@3: 100% (3/3)
+
+Status: READY FOR REVIEW
+```
+
+## Integration Patterns
+
+### Pre-Implementation
+```
+$eval define feature-name
+```
+Creates eval definition file at `.codex/evals/feature-name.md`
+
+### During Implementation
+```
+$eval check feature-name
+```
+Runs current evals and reports status
+
+### Post-Implementation
+```
+$eval report feature-name
+```
+Generates full eval report
+
+## Eval Storage
+
+Store evals in project:
+```
+.codex/
+  evals/
+    feature-xyz.md      # Eval definition
+    feature-xyz.log     # Eval run history
+    baseline.json       # Regression baselines
+```
+
+## Best Practices
+
+1. **Define evals BEFORE coding** - Forces clear thinking about success criteria
+2. **Run evals frequently** - Catch regressions early
+3. **Track pass@k over time** - Monitor reliability trends
+4. **Use code graders when possible** - Deterministic > probabilistic
+5. **Human review for security** - Never fully automate security checks
+6. **Keep evals fast** - Slow evals don't get run
+7. **Version evals with code** - Evals are first-class artifacts
+
+## Example: Adding Authentication
+
+```markdown
+## EVAL: add-authentication
+
+### Phase 1: Define (10 min)
+Capability Evals:
+- [ ] User can register with email/password
+- [ ] User can login with valid credentials
+- [ ] Invalid credentials rejected with proper error
+- [ ] Sessions persist across page reloads
+- [ ] Logout clears session
+
+Regression Evals:
+- [ ] Public routes still accessible
+- [ ] API responses unchanged
+- [ ] Database schema compatible
+
+### Phase 2: Implement (varies)
+[Write code]
+
+### Phase 3: Evaluate
+Run: $eval check add-authentication
+
+### Phase 4: Report
+EVAL REPORT: add-authentication
+==============================
+Capability: 5/5 passed (pass@3: 100%)
+Regression: 3/3 passed (pass^3: 100%)
+Status: SHIP IT
+```

package/.agent/skills/evolve/SKILL.md

@@ -0,0 +1,213 @@
+---
+name: evolve
+description: Imported from everything-codex command evolve
+---
+
+---
+name: evolve
+description: Cluster related instincts into skills, commands, or agents
+command: true
+---
+
+# Evolve Command
+
+
+## Native Subagent Protocol (Codex)
+
+Codex supports native subagents. Delegate with `spawn_agent`, coordinate with `send_input`, collect via `wait`, and clean up with `close_agent`.
+
+Execution preference:
+1. Use native subagents first for independent workstreams (parallel when possible).
+2. Merge results in main thread and run final verification.
+3. Fallback only when delegation is blocked: use the `[ANALYST]`/`[ARCHITECT]`/`[EXECUTOR]`/`[REVIEWER]` structure in a single response.
+
+Minimal orchestration pattern:
+```text
+spawn_agent -> send_input (optional) -> wait -> close_agent
+```
+
+## Implementation
+
+Run the instinct CLI using the Codex home path:
+
+```bash
+python3 "${CODEX_HOME}/skills/continuous-learning-v2/scripts/instinct-cli.py" evolve [--generate]
+```
+
+Or if `CODEX_HOME` is not set (manual installation):
+
+```bash
+python3 ~/.codex/skills/continuous-learning-v2/scripts/instinct-cli.py evolve [--generate]
+```
+
+Analyzes instincts and clusters related ones into higher-level structures:
+- **Commands**: When instincts describe user-invoked actions
+- **Skills**: When instincts describe auto-triggered behaviors
+- **Agents**: When instincts describe complex, multi-step processes
+
+## Usage
+
+```
+$evolve                    # Analyze all instincts and suggest evolutions
+$evolve --domain testing   # Only evolve instincts in testing domain
+$evolve --dry-run          # Show what would be created without creating
+$evolve --threshold 5      # Require 5+ related instincts to cluster
+```
+
+## Evolution Rules
+
+### → Command (User-Invoked)
+When instincts describe actions a user would explicitly request:
+- Multiple instincts about "when user asks to..."
+- Instincts with triggers like "when creating a new X"
+- Instincts that follow a repeatable sequence
+
+Example:
+- `new-table-step1`: "when adding a database table, create migration"
+- `new-table-step2`: "when adding a database table, update schema"
+- `new-table-step3`: "when adding a database table, regenerate types"
+
+→ Creates: `$new-table` command
+
+### → Skill (Auto-Triggered)
+When instincts describe behaviors that should happen automatically:
+- Pattern-matching triggers
+- Error handling responses
+- Code style enforcement
+
+Example:
+- `prefer-functional`: "when writing functions, prefer functional style"
+- `use-immutable`: "when modifying state, use immutable patterns"
+- `avoid-classes`: "when designing modules, avoid class-based design"
+
+→ Creates: `functional-patterns` skill
+
+### → Agent (Needs Depth/Isolation)
+When instincts describe complex, multi-step processes that benefit from isolation:
+- Debugging workflows
+- Refactoring sequences
+- Research tasks
+
+Example:
+- `debug-step1`: "when debugging, first check logs"
+- `debug-step2`: "when debugging, isolate the failing component"
+- `debug-step3`: "when debugging, create minimal reproduction"
+- `debug-step4`: "when debugging, verify fix with test"
+
+→ Creates: `debugger` agent
+
+## What to Do
+
+1. Read all instincts from `~/.codex/homunculus/instincts/`
+2. Group instincts by:
+   - Domain similarity
+   - Trigger pattern overlap
+   - Action sequence relationship
+3. For each cluster of 3+ related instincts:
+   - Determine evolution type (command/skill/agent)
+   - Generate the appropriate file
+   - Save to `~/.codex/homunculus/evolved/{commands,skills,agents}/`
+4. Link evolved structure back to source instincts
+
+## Output Format
+
+```
+🧬 Evolve Analysis
+==================
+
+Found 3 clusters ready for evolution:
+
+## Cluster 1: Database Migration Workflow
+Instincts: new-table-migration, update-schema, regenerate-types
+Type: Command
+Confidence: 85% (based on 12 observations)
+
+Would create: $new-table command
+Files:
+  - ~/.codex/homunculus/evolved/commands/new-table.md
+
+## Cluster 2: Functional Code Style
+Instincts: prefer-functional, use-immutable, avoid-classes, pure-functions
+Type: Skill
+Confidence: 78% (based on 8 observations)
+
+Would create: functional-patterns skill
+Files:
+  - ~/.codex/homunculus/evolved/skills/functional-patterns.md
+
+## Cluster 3: Debugging Process
+Instincts: debug-check-logs, debug-isolate, debug-reproduce, debug-verify
+Type: Agent
+Confidence: 72% (based on 6 observations)
+
+Would create: debugger agent
+Files:
+  - ~/.codex/homunculus/evolved/agents/debugger.md
+
+---
+Run `$evolve --execute` to create these files.
+```
+
+## Flags
+
+- `--execute`: Actually create the evolved structures (default is preview)
+- `--dry-run`: Preview without creating
+- `--domain <name>`: Only evolve instincts in specified domain
+- `--threshold <n>`: Minimum instincts required to form cluster (default: 3)
+- `--type <command|skill|agent>`: Only create specified type
+
+## Generated File Format
+
+### Command
+```markdown
+---
+name: new-table
+description: Create a new database table with migration, schema update, and type generation
+command: $new-table
+evolved_from:
+  - new-table-migration
+  - update-schema
+  - regenerate-types
+---
+
+# New Table Command
+
+[Generated content based on clustered instincts]
+
+## Steps
+1. ...
+2. ...
+```
+
+### Skill
+```markdown
+---
+name: functional-patterns
+description: Enforce functional programming patterns
+evolved_from:
+  - prefer-functional
+  - use-immutable
+  - avoid-classes
+---
+
+# Functional Patterns Skill
+
+[Generated content based on clustered instincts]
+```
+
+### Agent
+```markdown
+---
+name: debugger
+description: Systematic debugging agent
+model: sonnet
+evolved_from:
+  - debug-check-logs
+  - debug-isolate
+  - debug-reproduce
+---
+
+# Debugger Agent
+
+[Generated content based on clustered instincts]
+```

package/.agent/skills/frontend-design/SKILL.md

@@ -0,0 +1,42 @@
+---
+name: frontend-design
+description: Design and implement modern frontend interfaces. Covers React, Vue, state management, routing, and component architecture patterns.
+license: Complete terms in LICENSE.txt
+---
+
+This skill guides creation of distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. Implement real working code with exceptional attention to aesthetic details and creative choices.
+
+The user provides frontend requirements: a component, page, application, or interface to build. They may include context about the purpose, audience, or technical constraints.
+
+## Design Thinking
+
+Before coding, understand the context and commit to a BOLD aesthetic direction:
+- **Purpose**: What problem does this interface solve? Who uses it?
+- **Tone**: Pick an extreme: brutally minimal, maximalist chaos, retro-futuristic, organic/natural, luxury/refined, playful/toy-like, editorial/magazine, brutalist/raw, art deco/geometric, soft/pastel, industrial/utilitarian, etc. There are so many flavors to choose from. Use these for inspiration but design one that is true to the aesthetic direction.
+- **Constraints**: Technical requirements (framework, performance, accessibility).
+- **Differentiation**: What makes this UNFORGETTABLE? What's the one thing someone will remember?
+
+**CRITICAL**: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.
+
+Then implement working code (HTML/CSS/JS, React, Vue, etc.) that is:
+- Production-grade and functional
+- Visually striking and memorable
+- Cohesive with a clear aesthetic point-of-view
+- Meticulously refined in every detail
+
+## Frontend Aesthetics Guidelines
+
+Focus on:
+- **Typography**: Choose fonts that are beautiful, unique, and interesting. Avoid generic fonts like Arial and Inter; opt instead for distinctive choices that elevate the frontend's aesthetics; unexpected, characterful font choices. Pair a distinctive display font with a refined body font.
+- **Color & Theme**: Commit to a cohesive aesthetic. Use CSS variables for consistency. Dominant colors with sharp accents outperform timid, evenly-distributed palettes.
+- **Motion**: Use animations for effects and micro-interactions. Prioritize CSS-only solutions for HTML. Use Motion library for React when available. Focus on high-impact moments: one well-orchestrated page load with staggered reveals (animation-delay) creates more delight than scattered micro-interactions. Use scroll-triggering and hover states that surprise.
+- **Spatial Composition**: Unexpected layouts. Asymmetry. Overlap. Diagonal flow. Grid-breaking elements. Generous negative space OR controlled density.
+- **Backgrounds & Visual Details**: Create atmosphere and depth rather than defaulting to solid colors. Add contextual effects and textures that match the overall aesthetic. Apply creative forms like gradient meshes, noise textures, geometric patterns, layered transparencies, dramatic shadows, decorative borders, custom cursors, and grain overlays.
+
+NEVER use generic AI-generated aesthetics like overused font families (Inter, Roboto, Arial, system fonts), cliched color schemes (particularly purple gradients on white backgrounds), predictable layouts and component patterns, and cookie-cutter design that lacks context-specific character.
+
+Interpret creatively and make unexpected choices that feel genuinely designed for the context. No design should be the same. Vary between light and dark themes, different fonts, different aesthetics. NEVER converge on common choices (Space Grotesk, for example) across generations.
+
+**IMPORTANT**: Match implementation complexity to the aesthetic vision. Maximalist designs need elaborate code with extensive animations and effects. Minimalist or refined designs need restraint, precision, and careful attention to spacing, typography, and subtle details. Elegance comes from executing the vision well.
+
+Remember: Claude is capable of extraordinary creative work. Don't hold back, show what can truly be created when thinking outside the box and committing fully to a distinctive vision.