oh-my-customcodex 0.1.0

package/templates/.claude/skills/go-best-practices/SKILL.md

@@ -0,0 +1,204 @@
+---
+name: go-best-practices
+description: Idiomatic Go patterns from Effective Go
+scope: core
+user-invocable: false
+---
+
+## Purpose
+
+Apply idiomatic Go patterns and best practices from official Go documentation.
+
+## Rules
+
+### 1. Formatting
+
+```yaml
+rules:
+  - Use gofmt for all code formatting
+  - Indentation uses tabs, not spaces
+  - No line length limit, but break long lines sensibly
+  - Let gofmt handle alignment
+```
+
+### 2. Naming Conventions
+
+```yaml
+package_names:
+  - Short, concise, lowercase, single-word
+  - No underscores or mixedCaps
+  - Name is basename of source directory
+  - Example: bufio, not bufIO or buf_io
+
+getters:
+  - No "Get" prefix for getters
+  - obj.Owner() not obj.GetOwner()
+  - Setter can use "Set": obj.SetOwner(user)
+
+interface_names:
+  - One-method interfaces: method name + "er"
+  - Reader, Writer, Formatter, CloseNotifier
+  - Avoid stealing standard names unless same signature
+
+mixedCaps:
+  - Use MixedCaps or mixedCaps, never underscores
+  - Exported: MixedCaps (uppercase first)
+  - Unexported: mixedCaps (lowercase first)
+```
+
+### 3. Control Structures
+
+```yaml
+if_statements:
+  - Accept initialization statement
+  - Prefer: if err := file.Chmod(0664); err != nil
+  - Omit else when if ends with break/continue/return
+  - Avoid unnecessary else
+
+for_loops:
+  - Go's only loop construct
+  - for init; condition; post { } - like C for
+  - for condition { } - like C while
+  - for { } - infinite loop
+  - Use range for strings, slices, arrays, maps, channels
+
+switch:
+  - Cases don't fall through by default
+  - Use fallthrough keyword if needed
+  - Multiple cases: case '0', '1', '2'
+  - Type switch: switch v := x.(type)
+```
+
+### 4. Functions
+
+```yaml
+multiple_returns:
+  - Return multiple values for result + error
+  - func (file *File) Write(b []byte) (n int, err error)
+
+named_results:
+  - Document return values with names
+  - Can simplify code but use judiciously
+  - Unnamed returns OK for short functions
+
+defer:
+  - Executes when function returns
+  - LIFO order for multiple defers
+  - Use for cleanup: unlock mutexes, close files
+  - Arguments evaluated when defer executes, not when called
+```
+
+### 5. Data
+
+```yaml
+new_vs_make:
+  - new(T): allocates zeroed storage, returns *T
+  - make(T, args): creates slices, maps, channels only
+  - make returns initialized (not zeroed) value of type T
+
+slices:
+  - Backed by arrays, can grow
+  - append() to add elements
+  - copy() for safe duplication
+  - Slice of slice shares underlying array
+
+maps:
+  - Reference type, nil until initialized
+  - make(map[KeyType]ValueType)
+  - Comma ok idiom: val, ok := map[key]
+  - delete(map, key) to remove
+```
+
+### 6. Methods
+
+```yaml
+pointer_vs_value_receivers:
+  - Pointer receiver: can modify, no copy overhead
+  - Value receiver: safe from modification
+  - If any method needs pointer, all should use pointer
+  - Rule: values immutable, pointers mutable
+```
+
+### 7. Interfaces
+
+```yaml
+design:
+  - Interfaces define behavior, not data
+  - Small interfaces (1-3 methods) preferred
+  - Accept interfaces, return structs
+  - If type implements interface, it satisfies implicitly
+
+common_interfaces:
+  - io.Reader: Read(p []byte) (n int, err error)
+  - io.Writer: Write(p []byte) (n int, err error)
+  - fmt.Stringer: String() string
+  - error: Error() string
+```
+
+### 8. Concurrency
+
+```yaml
+goroutines:
+  - Lightweight, multiplexed onto OS threads
+  - go function() to start
+  - Don't communicate by sharing memory
+  - Share memory by communicating
+
+channels:
+  - Primary synchronization mechanism
+  - ch := make(chan int) - unbuffered
+  - ch := make(chan int, 100) - buffered
+  - Send: ch <- v
+  - Receive: v := <-ch
+  - Close: close(ch)
+
+patterns:
+  - Don't leak goroutines - ensure they exit
+  - Use context for cancellation
+  - select for multiple channel operations
+  - sync.WaitGroup for goroutine coordination
+```
+
+### 9. Error Handling
+
+```yaml
+principles:
+  - Errors are values, handle them explicitly
+  - Check errors immediately after call
+  - Return errors, don't panic
+  - Add context when propagating: fmt.Errorf("op failed: %w", err)
+
+panic_recover:
+  - Panic for unrecoverable errors only
+  - Library functions should return errors, not panic
+  - Recover only in deferred functions
+  - Convert internal panics to errors at package boundary
+```
+
+### 10. Project Structure
+
+```yaml
+packages:
+  - One package per directory
+  - Package name matches directory name
+  - main package for executables
+  - Avoid circular imports
+
+files:
+  - doc.go for package documentation
+  - _test.go suffix for test files
+  - Group related types and functions
+```
+
+## Application
+
+When writing or reviewing Go code:
+
+1. **Always** run `gofmt` or `goimports`
+2. **Always** handle returned errors
+3. **Prefer** composition over inheritance
+4. **Prefer** small interfaces
+5. **Prefer** channels for goroutine communication
+6. **Avoid** global state
+7. **Avoid** init() when possible
+8. **Document** exported identifiers

package/templates/.claude/skills/hada-scout/SKILL.md

@@ -0,0 +1,92 @@
+---
+name: hada-scout
+description: hada.io RSS feed monitoring for AI agent/harness articles with automated /scout analysis
+scope: package
+version: 1.0.0
+user-invocable: false
+---
+
+# hada-scout
+
+Automated pipeline that monitors hada.io (via feedburner RSS) for AI agent, harness, benchmark, and eval-related articles, then runs `/scout` analysis on each match.
+
+## Purpose
+
+Complement geeknews-scout with harness/eval-focused coverage from hada.io. While geeknews-scout casts a broad net over AI agent news, hada-scout narrows to benchmark/evaluation framework content — the domain most relevant to oh-my-customcodex's harness and agent-eval subsystems.
+
+## Architecture: 2-Layer Hybrid
+
+### Layer 1 — check-feed.sh (feed → issues)
+
+1. Fetch hada.io feedburner RSS
+2. Filter entries by keyword regex (case-insensitive)
+3. Dedup against existing `hada-scout` issues
+4. Create GitHub issue per match with labels `hada-scout` + `pending-scout`
+
+### Layer 2 — scout-runner.sh (issues → /scout)
+
+1. Find open issues with `pending-scout` label
+2. Extract source URL from issue body
+3. Run `claude -p "/scout {url}"` (max 5 executions per run)
+4. Parse verdict from /scout output
+5. Apply verdict label, remove `pending-scout`
+
+## Keyword Strategy
+
+hada-scout uses harness/benchmark/eval focused keywords, distinct from geeknews-scout's broader AI agent coverage:
+
+```
+harness|benchmark|eval|evaluation framework|agent framework|코드 리뷰 자동화|하네스|벤치마크|평가
+```
+
+Geeknews-scout handles: `Claude|Anthropic|MCP|AI agent|에이전트|agentic|multi-agent|...`
+
+## Label Scheme
+
+| Label | Purpose |
+|-------|---------|
+| `hada-scout` | Source identification — all hada-scout created issues |
+| `pending-scout` | Awaiting /scout analysis (set by Layer 1, cleared by Layer 2) |
+| `scout:internalize` | /scout verdict: adopt into project |
+| `scout:integrate` | /scout verdict: use as external dependency |
+| `scout:skip` | /scout verdict: not relevant |
+
+## Cost Controls
+
+- Layer 2 runs at most **5 /scout executions per cron invocation**
+- Each /scout call costs ~$0.5–1.5 (sonnet)
+- Remaining `pending-scout` issues are processed in the next scheduled run
+
+## Deployment
+
+- Pattern: same K8s CronJob structure as `infra/geeknews-scout/`
+- Host: `ubuntu-ext` cluster
+- Infrastructure files: `infra/hada-scout/`
+  - `check-feed.sh` — Layer 1 feed poller
+  - `scout-runner.sh` — Layer 2 /scout executor
+  - `Dockerfile`
+  - `cronjob.template.yaml`
+  - `deploy.sh`
+  - `.env.example`
+
+## Environment Variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `GH_TOKEN` | (required) | GitHub PAT for issue creation |
+| `REPO` | `baekenough/oh-my-customcodex` | Target repo |
+| `FEED_URL` | `http://feeds.feedburner.com/geeknews-feed` | hada.io RSS feed |
+| `KEYWORDS` | (see above) | Pipe-separated keyword regex |
+| `MAX_SCOUT_PER_RUN` | `5` | Max /scout executions per Layer 2 run |
+
+## Integration
+
+| Rule | How |
+|------|-----|
+| R009 | Layer 1 and Layer 2 run as independent CronJobs |
+| R010 | Skill defines the architecture; implementation delegated to infra-docker-expert for K8s manifests |
+| scout skill | Layer 2 invokes `/scout` via `claude -p` subprocess |
+
+## Tracking Issue
+
+GitHub Issue #841

package/templates/.claude/skills/harness-eval/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: harness-eval
+description: Structured SE task evaluation using 15 benchmark definitions from claude-code-harness research
+scope: harness
+user-invocable: true
+argument-hint: "[--preset all|quick] [--task task-name]"
+effort: high
+version: 1.0.0
+---
+
+# Harness Eval — Structured SE Task Benchmark
+
+## Purpose
+
+Evaluate agent quality using 15 structured software engineering task definitions with quantitative scoring. Based on research from [revfactory/claude-code-harness](https://github.com/revfactory/claude-code-harness) which demonstrated 60% improvement (49.5 → 79.3 points) through structured pre-configuration.
+
+## Usage
+
+```
+/omcodex:harness-eval                    # Run all 15 benchmarks
+/omcodex:harness-eval --preset quick     # Run top 5 high-impact benchmarks
+/omcodex:harness-eval --task api-design  # Run specific task benchmark
+```
+
+## Quality Dimensions
+
+| Dimension | Weight | Description |
+|-----------|--------|-------------|
+| Test Coverage | 30% | Unit test count, edge case coverage, assertion quality |
+| Architecture Design | 25% | Separation of concerns, dependency management, scalability |
+| Error Handling | 25% | Input validation, error propagation, recovery strategies |
+| Extensibility | 20% | Plugin points, configuration flexibility, API surface |
+
+## 15 SE Task Benchmark Suite
+
+| # | Task | Category | Key Evaluation Criteria |
+|---|------|----------|------------------------|
+| 1 | API Design | Architecture | RESTful conventions, versioning, error responses |
+| 2 | Data Modeling | Architecture | Schema normalization, relationships, indexing |
+| 3 | Authentication Flow | Security | Token management, session handling, OWASP compliance |
+| 4 | Test Suite Creation | Quality | Coverage breadth, assertion quality, edge cases |
+| 5 | Error Handler | Reliability | Error classification, recovery, user feedback |
+| 6 | Logging System | Observability | Structured logging, levels, correlation IDs |
+| 7 | Configuration Manager | Operations | Env-based config, validation, secrets handling |
+| 8 | CLI Tool | UX | Argument parsing, help text, exit codes |
+| 9 | Database Migration | Data | Reversibility, data preservation, zero-downtime |
+| 10 | Cache Layer | Performance | Invalidation strategy, TTL, cache-aside pattern |
+| 11 | Queue Consumer | Reliability | Idempotency, retry logic, dead letter handling |
+| 12 | Middleware Chain | Architecture | Composability, ordering, short-circuiting |
+| 13 | File Processor | I/O | Streaming, error recovery, format validation |
+| 14 | Webhook Handler | Integration | Signature verification, retry tolerance, idempotency |
+| 15 | Rate Limiter | Security | Algorithm choice, distributed state, fairness |
+
+## Scoring Rubric
+
+Each task is scored 0-100 across the 4 quality dimensions:
+
+```
+Score = (test_coverage × 0.30) + (architecture × 0.25) + (error_handling × 0.25) + (extensibility × 0.20)
+```
+
+### Score Thresholds
+
+| Score Range | Grade | Interpretation |
+|-------------|-------|----------------|
+| 80-100 | A | Production-ready, well-structured |
+| 60-79 | B | Functional with minor gaps |
+| 40-59 | C | Works but needs improvement |
+| 0-39 | D | Significant structural issues |
+
+## Presets
+
+### `all` (default)
+Run all 15 tasks. Full evaluation ~45 minutes.
+
+### `quick`
+Run top 5 high-impact tasks (1, 3, 4, 5, 12). Quick evaluation ~15 minutes.
+
+## Integration with evaluator-optimizer
+
+This skill provides preset rubrics for the evaluator-optimizer pipeline:
+
+```
+/omcodex:harness-eval → loads rubric → evaluator-optimizer executes → scoring → report
+```
+
+The evaluator-optimizer skill's `pre_negotiation` phase accepts harness-eval rubric dimensions as sprint contract criteria.
+
+## Output
+
+Results saved to `.codex/outputs/sessions/{YYYY-MM-DD}/harness-eval-{HHmmss}.md` with per-task scores and aggregate grade.
+
+## Attribution
+
+Evaluation framework based on research by [revfactory/claude-code-harness](https://github.com/revfactory/claude-code-harness). Adapted for oh-my-customcodex's evaluator-optimizer pipeline with permission.

package/templates/.claude/skills/harness-synthesizer/SKILL.md

@@ -0,0 +1,145 @@
+---
+name: harness-synthesizer
+description: Synthesize code harnesses for agent action validation — AutoHarness-inspired verifier/filter/policy generation
+scope: core
+version: 1.0.0
+user-invocable: true
+argument-hint: "[--mode verifier|filter|policy] [--agent <name>] [--dry-run]"
+effort: high
+---
+
+# Harness Synthesizer Skill
+
+## Purpose
+
+Synthesize executable validation harnesses for agent tool calls, inspired by AutoHarness (Google DeepMind, arxiv 2603.03329). Generates code-level verifiers that check action validity before or after execution, reducing agent errors through structured constraint enforcement.
+
+Default mode is advisory (verifier). Hard enforcement requires explicit `--hard-enforce` opt-in per R021.
+
+## Three Modes
+
+| Mode | Flag | Behavior | Enforcement |
+|------|------|----------|-------------|
+| `verifier` | default | Post-hoc check: validates tool call results after execution | Advisory only |
+| `filter` | `--mode filter` | Pre-execution check: blocks invalid tool calls | Opt-in, requires `--hard-enforce` |
+| `policy` | `--mode policy` | Suggests the best valid action from available options | Advisory only |
+
+### Verifier Mode (Default)
+
+Generates a YAML harness that describes post-execution checks for each tool the agent uses. Checks are emitted as advisory warnings — they do not block execution.
+
+```yaml
+# Example verifier harness output
+harness:
+  agent: lang-golang-expert
+  mode: verifier
+  rules:
+    - tool: Write
+      checks:
+        - field: file_path
+          pattern: ".*\\.go$"
+          on_fail: warn  # advisory
+        - field: content
+          must_not_contain: "TODO:"
+          on_fail: warn
+    - tool: Bash
+      checks:
+        - command_pattern: "^(go build|go test|go fmt|go vet)"
+          on_fail: warn
+```
+
+### Filter Mode (Opt-in)
+
+Generates pre-execution filter rules. Requires `--hard-enforce` flag. Used when advisory warnings are insufficient and the risk of invalid actions is high.
+
+```yaml
+# Example filter harness output (--hard-enforce)
+harness:
+  agent: mgr-gitnerd
+  mode: filter
+  enforcement: hard
+  rules:
+    - tool: Bash
+      blocks:
+        - pattern: "git push --force"
+          reason: "Force push to protected branch"
+        - pattern: "git reset --hard"
+          reason: "Destructive reset without confirmation"
+```
+
+### Policy Mode
+
+Generates a policy function that ranks valid actions and suggests the best one. Useful for agents with multiple valid paths to the same goal.
+
+```yaml
+# Example policy harness output
+harness:
+  agent: qa-engineer
+  mode: policy
+  policies:
+    - scenario: "test file modification"
+      preferred_sequence:
+        - tool: Read
+          reason: "Read before modifying"
+        - tool: Edit
+          reason: "Edit is safer than Write for existing files"
+      avoid:
+        - tool: Write
+          on_existing_file: true
+          reason: "Overwrites without diff"
+```
+
+## Workflow
+
+1. **Read target agent frontmatter** — extract `tools`, `domain`, `limitations` fields
+2. **Analyze recent tool call patterns** — check `.codex/outputs/` for prior session logs (if available)
+3. **Synthesize validation harness** — generate YAML harness matching agent's declared capabilities
+4. **Refine via evaluator-optimizer loop** — iterate harness against edge cases (3 rounds max)
+5. **Save output** — write to `.codex/outputs/harnesses/{agent-name}-{mode}.yaml`
+6. **Report** — print harness summary and integration instructions
+
+## Integration
+
+| System | How |
+|--------|-----|
+| `action-validator` | Harness output feeds into action-validator's code-verified mode |
+| `adaptive-harness --learn` | Auto-triggers harness-synthesizer for project-specific patterns |
+| `evaluator-optimizer` | Provides iterative refinement loop (gradient-free optimization) |
+| `pipeline-guards` | Harness checks usable as pipeline quality gates |
+
+## Usage Examples
+
+```bash
+# Generate advisory verifier for lang-golang-expert
+/harness-synthesizer --agent lang-golang-expert --mode verifier
+
+# Dry-run: preview harness without saving
+/harness-synthesizer --agent mgr-gitnerd --mode filter --dry-run
+
+# Generate hard-enforce filter (explicit opt-in)
+/harness-synthesizer --agent mgr-gitnerd --mode filter --hard-enforce
+
+# Generate policy harness
+/harness-synthesizer --agent qa-engineer --mode policy
+```
+
+## R021 Compliance
+
+- Default `verifier` mode: advisory only — never blocks tool execution
+- `filter` mode without `--hard-enforce`: advisory only — emits warnings
+- `filter --hard-enforce`: opt-in hard enforcement — requires explicit user flag
+- All harness output is saved to `.codex/outputs/harnesses/` (git-untracked)
+
+## Output Format
+
+Harnesses are saved as YAML at `.codex/outputs/harnesses/{agent-name}-{mode}.yaml`. Each harness includes:
+
+```yaml
+harness:
+  agent: {agent-name}
+  mode: verifier | filter | policy
+  version: 1.0.0
+  generated: {ISO-8601 timestamp}
+  enforcement: advisory | hard  # hard only with --hard-enforce
+  rules: [...]
+```

package/templates/.claude/skills/help/SKILL.md

@@ -0,0 +1,127 @@
+---
+name: omcodex:help
+description: Show help information for commands and system
+scope: harness
+argument-hint: "[command] [--agents] [--rules]"
+user-invocable: true
+---
+
+# Help Skill
+
+Show help information for commands, agents, and system rules.
+
+## Options
+
+```
+--agents, -a     List all available agents
+--commands, -c   List all commands (same as 'lists')
+--rules, -r      List all rules
+```
+
+## Output Format
+
+### Default Help
+```
+AI Agent System - Help
+
+Usage: {command} [arguments] [options]
+
+Quick Start:
+  lists              Show all available commands
+  status             Show system status
+  help <command>     Get help for a specific command
+
+Common Commands:
+  /update-docs       Sync documentation with project
+  /update-external   Update external agents
+  /audit-agents      Check agent dependencies
+  /create-agent      Create a new agent
+
+Use "lists" to see all available commands.
+Use "help <command>" for detailed help.
+```
+
+### Command Help
+```
+help /update-docs
+
+Command: /update-docs
+
+Description:
+  Sync documentation with project structure. Ensures all
+  documentation accurately reflects the current project state.
+
+Usage:
+  /update-docs
+  /update-docs --check
+  /update-docs --target <path>
+
+Options:
+  --check, -c      Check only, don't modify
+  --verbose, -v    Show detailed changes
+  --target, -t     Specific target to update
+
+Examples:
+  /update-docs                 # Update all documentation
+  /update-docs --check         # Check for issues
+  /update-docs --target agents # Update agents only
+```
+
+### Agent List
+```
+help --agents
+
+Available Agents:
+
+Orchestrator:
+  secretary        Manages manager agents
+
+Manager:
+  mgr-creator          Creates new agents
+  mgr-updater          Updates external sources and docs
+  mgr-supplier         Validates dependencies
+
+SW Engineer:
+  lang-golang-expert       Go development (Effective Go)
+  lang-python-expert       Python development (PEP 8)
+  lang-rust-expert         Rust development (API Guidelines)
+  lang-kotlin-expert       Kotlin development (JetBrains)
+  lang-typescript-expert   TypeScript development (Google)
+  fe-vercel-agent  React/Next.js (Vercel)
+
+Backend Engineer:
+  be-fastapi-expert      FastAPI (Python async)
+  be-springboot-expert   Spring Boot (Java)
+  be-go-backend-expert   Go backend (Uber style)
+
+Infra Engineer:
+  infra-docker-expert       Docker containerization
+  infra-aws-expert          AWS architecture
+
+Total: 15 agents
+```
+
+### Rules List
+```
+help --rules
+
+Global Rules:
+
+MUST (Never violate):
+  R000  Language Policy      Korean I/O, English files
+  R001  Safety Rules         Prohibited actions
+  R002  Permission Rules     Tool tiers, file access
+  R006  Agent Design         Structure, separation
+
+SHOULD (Strongly recommended):
+  R003  Interaction Rules    Response format
+  R004  Error Handling       Error levels, recovery
+  R007  Agent Identification Display agent in responses
+  R008  Tool Identification  Display agent when using tools
+
+MAY (Optional):
+  R005  Optimization         Efficiency guidelines
+  R009  Parallel Execution   Max 4 parallel instances
+
+Total: 10 rules
+```