oh-my-customcodex 0.1.0

package/templates/.claude/contexts/dev.md

@@ -0,0 +1,20 @@
+# Development Context
+
+Mode: Active development
+Focus: Implementation, coding, building features
+
+## Behavior
+- Write code first, explain after
+- Prefer working solutions over perfect solutions
+- Run tests after changes
+- Keep commits atomic
+
+## Priorities
+1. Get it working
+2. Get it right
+3. Get it clean
+
+## Tools to favor
+- Edit, Write for code changes
+- Bash for running tests/builds
+- Grep, Glob for finding code

package/templates/.claude/contexts/ecomode.md

@@ -0,0 +1,110 @@
+# Ecomode Context
+
+> Activated when token efficiency is critical
+
+## When Active
+
+This context is loaded when ecomode is activated (4+ parallel tasks, batch operations, or near compaction).
+
+## Instructions for Agents
+
+### Output Rules
+
+1. **Status first**: Always start with status indicator
+2. **One-liner summary**: Compress results to 1-2 sentences
+3. **Skip verbose**: No intermediate steps, no repeated context
+4. **Use references**: File paths instead of contents
+
+### Format Template
+
+```
+[{agent-name}] {status_icon} {target}: {summary}
+```
+
+### Status Icons
+
+| Icon | Meaning |
+|------|---------|
+| ✓ | Success |
+| ✗ | Failed |
+| ⚠ | Partial/Warning |
+| ⏳ | In progress |
+
+### Examples
+
+Good (ecomode):
+```
+[lang-golang-expert] ✓ src/main.go: 3 issues found (2 style, 1 error handling)
+```
+
+Bad (verbose):
+```
+I have completed the review of src/main.go. The file contains...
+[long explanation]
+```
+
+## Aggregation
+
+When secretary aggregates results:
+
+```
+[Batch Complete] 4/4
+├── lang-golang-expert: ✓ 3 issues in 2 files
+├── lang-python-expert: ✓ Clean, no issues
+├── lang-rust-expert: ⚠ 1 warning (unsafe block)
+└── lang-typescript-expert: ✓ 5 suggestions
+```
+
+## Exit Conditions
+
+Ecomode deactivates when:
+- User requests "verbose" or "full details"
+- Single task execution
+- Explicit "ecomode off"
+
+## Effort Level Integration
+
+Agent frontmatter `effort` field maps to runtime behavior:
+
+| Effort | Model Preference | Output Length | Detail Level | Token Budget |
+|--------|-----------------|---------------|--------------|--------------|
+| `low` | haiku | ≤100 tokens | Minimal — result only | Conservative |
+| `medium` | sonnet | ≤200 tokens | Summary + key details | Balanced |
+| `high` | opus | ≤500 tokens | Full reasoning + examples | Generous |
+
+### Effort ↔ Ecomode Interaction
+
+| Condition | Behavior |
+|-----------|----------|
+| Ecomode ON + effort: high | Ecomode wins — compress output regardless |
+| Ecomode OFF + effort: low | Low effort wins — concise output |
+| Ecomode OFF + effort: high | Full detailed output |
+| Ecomode ON + effort: low | Maximum compression |
+
+### Effort-Based Configuration
+
+```yaml
+effort_levels:
+  low:
+    result_format: minimal
+    max_result_length: 100
+    skip_intermediate_steps: true
+    output_style: concise
+  medium:
+    result_format: summary
+    max_result_length: 200
+    skip_intermediate_steps: false
+    output_style: balanced
+  high:
+    result_format: detailed
+    max_result_length: 500
+    skip_intermediate_steps: false
+    output_style: explanatory
+```
+
+### Application
+
+When spawning agents, the orchestrator should consider the agent's effort level:
+- `effort: low` agents → Assign to simple tasks (validation, search, formatting)
+- `effort: medium` agents → Assign to standard tasks (implementation, review)
+- `effort: high` agents → Assign to complex tasks (architecture, security, design)

package/templates/.claude/contexts/index.yaml

@@ -0,0 +1,41 @@
+# Claude Code Contexts Configuration
+# Source: https://github.com/affaan-m/everything-claude-code
+
+contexts:
+  dev:
+    file: dev.md
+    mode: Active development
+    focus: Implementation, coding, building features
+    priority: Working > Correct > Clean
+
+  review:
+    file: review.md
+    mode: PR review and code analysis
+    focus: Quality, security, maintainability
+    checklist:
+      - Logic correctness
+      - Error handling
+      - Security
+      - Performance
+      - Readability
+      - Test coverage
+
+  research:
+    file: research.md
+    mode: Exploration and investigation
+    focus: Understanding before acting
+    process:
+      - Understand question
+      - Explore code/docs
+      - Form hypotheses
+      - Validate with evidence
+      - Summarize findings
+
+usage:
+  description: |
+    Use contexts to change Claude's behavior mode.
+    Include the context file content in your prompt or
+    reference it at the start of a session.
+  example: |
+    "Using review context, analyze this PR..."
+    "In dev mode, implement this feature..."

package/templates/.claude/contexts/research.md

@@ -0,0 +1,28 @@
+# Research Context
+
+Mode: Exploration and investigation
+Focus: Understanding before acting
+
+## Behavior
+- Read widely before concluding
+- Ask clarifying questions
+- Document findings as you go
+- Understand before writing code
+
+## Research Process
+1. Understand the question
+2. Explore relevant code/docs
+3. Form hypotheses
+4. Validate with evidence
+5. Summarize findings
+
+## Tools to favor
+- Read for understanding code
+- Grep, Glob for pattern discovery
+- WebFetch for external docs
+- Task (Explore) for codebase queries
+
+## Output Format
+- Findings first
+- Recommendations second
+- Uncertainties noted

package/templates/.claude/contexts/review.md

@@ -0,0 +1,23 @@
+# Code Review Context
+
+Mode: PR review and code analysis
+Focus: Quality, security, maintainability
+
+## Behavior
+- Read thoroughly before commenting
+- Organize findings by severity
+- Suggest fixes, not just problems
+- Check for security vulnerabilities
+
+## Review Checklist
+1. Logic correctness and edge cases
+2. Error handling and exceptions
+3. Security concerns (injection, credentials)
+4. Performance implications
+5. Code readability
+6. Test coverage
+
+## Output Format
+- Group by file
+- Sort by severity (critical > high > medium > low)
+- Provide actionable suggestions