oh-my-customcode 0.62.5 → 0.63.1

package/README.md

@@ -21,17 +21,17 @@ npm install -g oh-my-customcode && cd your-project && omcustom init
 
 ---
 
-## What's New in v0.46.0
+## What's New in v0.62.5
 
 | Feature | Description |
 |---------|-------------|
-| **Rate Limit Monitoring** | Statusline now displays 5-hour rate limit usage with color-coded warnings (CC v2.1.80+) |
-| **Skill Effort Override** | Skills can set `effort` frontmatter to override model effort level at invocation time |
-| **Multi-project Web UI** | `omcustom serve` supports multi-project management with sidebar project selector |
-| **Batch Update UI** | Web dashboard supports visual project update status and batch updates |
-| **CC v2.1.72~v2.1.81 Compatibility** | Rate limits statusline, skill effort frontmatter, settings-based plugin source; `--bare` flag (harness disabled in bare mode), `--channels` permission relay (no changes required) |
-| **SDD Workflow** | Spec-Driven Development with `sdd/` folder hierarchy and planning-first gates |
-| **Ambiguity Gate** | Pre-routing clarity scoring and clarification questions |
+| **D3 Dependency Graph** | Interactive force-directed graph visualization at `/graph` — zoom, pan, drag, search, type filters |
+| **Playwright E2E Tests** | 11 accessibility tests with axe-core audit, `.pw.ts` extension for test isolation |
+| **Graph Accessibility** | WCAG keyboard navigation, aria-live announcements, skip link, focus-visible, reduced-motion support |
+| **CI Lockfile-Sync Gate** | New CI job validates bun.lockb consistency before lint/test |
+| **Token Optimization** | HTML comment technique reduces CLAUDE.md from 550→286 lines (48% reduction) |
+| **Workflow Engine** | YAML-defined workflow pipelines with `auto-dev` 7-step release batch |
+| **CC v2.1.83–v2.1.85 Compat** | Conditional hook `if` field, CwdChanged/FileChanged events, managed-settings.d |
 
 ---
 
@@ -131,7 +131,7 @@ Agent(arch-documenter):haiku      ┘
 |----------|-------|--------|
 | Languages | 6 | lang-golang, lang-python, lang-rust, lang-kotlin, lang-typescript, lang-java21 |
 | Backend | 6 | be-fastapi, be-springboot, be-go-backend, be-express, be-nestjs, be-django |
-| Frontend | 4 | fe-vercel, fe-vuejs, fe-svelte, fe-flutter |
+| Frontend | 5 | fe-vercel, fe-vuejs, fe-svelte, fe-flutter, fe-design |
 | Data Engineering | 6 | de-airflow, de-dbt, de-spark, de-kafka, de-snowflake, de-pipeline |
 | Database | 4 | db-supabase, db-postgres, db-redis, db-alembic |
 | Tooling | 3 | tool-npm, tool-optimizer, tool-bun |

package/dist/cli/index.js

@@ -9325,7 +9325,7 @@ var init_package = __esm(() => {
     workspaces: [
       "packages/*"
     ],
-    version: "0.62.5",
+    version: "0.63.1",
     description: "Batteries-included agent harness for Claude Code",
     type: "module",
     bin: {

package/dist/index.js

@@ -1674,7 +1674,7 @@ var package_default = {
   workspaces: [
     "packages/*"
   ],
-  version: "0.62.5",
+  version: "0.63.1",
   description: "Batteries-included agent harness for Claude Code",
   type: "module",
   bin: {

package/package.json

@@ -3,7 +3,7 @@
   "workspaces": [
     "packages/*"
   ],
-  "version": "0.62.5",
+  "version": "0.63.1",
   "description": "Batteries-included agent harness for Claude Code",
   "type": "module",
   "bin": {

package/templates/.claude/agents/sec-codeql-expert.md

@@ -2,6 +2,7 @@
 name: sec-codeql-expert
 description: Expert security code analyst using CodeQL for vulnerability detection, call graph analysis, and SARIF output. Use for security audits, CVE triage, code pattern analysis, and vulnerability validation.
 model: sonnet
+effort: high
 domain: devops
 memory: project
 isolation: sandbox

package/templates/.claude/rules/SHOULD-ecomode.md

@@ -36,6 +36,35 @@ Ecomode: `[lang-golang-expert] ✓ src/main.go reviewed: 1 naming issue (handle_
 
 Disable with: "ecomode off", "verbose mode", or "show full details".
 
+## Input Context Pruning
+
+Active removal of irrelevant retrieved content from agent context. Complements output compression by managing the input side of token budget.
+
+> **Terminology**: "Input Context Pruning" (R013) manages retrieved chunks during a task. "Memory Pruning" (R011) manages behavioral memory across sessions. These are distinct concepts.
+
+### Pruning Triggers
+
+| Trigger | Condition | Action |
+|---------|-----------|--------|
+| Search overflow | Retrieved chunks > 10 | Retain top-K by relevance, prune rest |
+| Context pressure | Context usage > 50% | Summarize oldest/lowest-relevance chunks |
+| Multi-hop intermediate | Between retrieval hops | Replace previous hop raw results with summary |
+
+### Pruning Strategy
+
+| Strategy | When | Behavior |
+|----------|------|----------|
+| **Retain** | Directly relevant code/docs | Keep as-is |
+| **Summarize** | Background context, prior hop results | Replace with 1-2 line summary |
+| **Drop** | Search noise, duplicates, already-reflected info | Remove entirely |
+
+### Rules
+
+- Pruning is irreversible — generate summary BEFORE dropping original
+- Prune at document/chunk level, not mid-sentence
+- When in doubt, Summarize rather than Drop
+- Track pruning decisions: `[Pruned] {N} chunks → {M} retained, {K} summarized, {J} dropped`
+
 ## Context Budget Management
 
 Task-type-aware context thresholds that trigger ecomode earlier for context-heavy operations.

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

@@ -3,6 +3,7 @@ name: alembic-best-practices
 description: Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration
 scope: core
 version: 1.0.0
+user-invocable: false
 ---
 
 # Alembic Best Practices

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

@@ -3,6 +3,7 @@ name: omcustom:analysis
 description: Analyze project and auto-configure agents, skills, rules, and guides
 scope: harness
 argument-hint: "[--dry-run] [--verbose]"
+user-invocable: true
 ---
 
 # Project Analysis Skill

package/templates/.claude/skills/audit-agents/SKILL.md

@@ -3,6 +3,7 @@ name: omcustom:audit-agents
 description: Audit agent dependencies and references
 scope: harness
 argument-hint: "[agent-name] [--all] [--fix]"
+user-invocable: true
 ---
 
 # Audit Agents Skill

package/templates/.claude/skills/claude-code-bible/SKILL.md

@@ -3,6 +3,7 @@ name: claude-code-bible
 description: Fetch Claude Code official documentation. Use when updating local reference docs or checking official spec.
 scope: core
 disable-model-invocation: true
+user-invocable: false
 ---
 
 # Claude Code Bible

package/templates/.claude/skills/codex-exec/SKILL.md

@@ -3,6 +3,7 @@ name: codex-exec
 description: Execute OpenAI Codex CLI prompts and return results
 scope: core
 argument-hint: "<prompt> [--json] [--output <path>] [--model <name>] [--timeout <ms>] [--effort <level>]"
+user-invocable: true
 ---
 
 # Codex Exec Skill

package/templates/.claude/skills/create-agent/SKILL.md

@@ -4,6 +4,7 @@ description: Create a new agent with complete structure
 scope: harness
 argument-hint: "<name> --type <type>"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Create Agent Skill

package/templates/.claude/skills/dag-orchestration/SKILL.md

@@ -3,6 +3,7 @@ name: dag-orchestration
 description: YAML-based DAG workflow engine with topological execution and failure strategies
 scope: core
 context: fork
+user-invocable: false
 ---
 
 # DAG Orchestration Skill

package/templates/.claude/skills/dev-refactor/SKILL.md

@@ -3,6 +3,7 @@ name: dev-refactor
 description: Refactor code for better structure and patterns
 scope: core
 argument-hint: "<file-or-directory> [--lang <language>] [--spec]"
+user-invocable: true
 ---
 
 # Code Refactoring Skill

package/templates/.claude/skills/dev-review/SKILL.md

@@ -3,6 +3,7 @@ name: dev-review
 description: Review code against language-specific best practices
 scope: core
 argument-hint: "<file-or-directory> [--lang <language>]"
+user-invocable: true
 ---
 
 # Code Review Skill

package/templates/.claude/skills/fix-refs/SKILL.md

@@ -4,6 +4,7 @@ description: Fix broken agent references and symlinks
 scope: harness
 argument-hint: "[agent-name] [--all] [--dry-run]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Fix References Skill

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

@@ -3,6 +3,7 @@ name: omcustom:help
 description: Show help information for commands and system
 scope: harness
 argument-hint: "[command] [--agents] [--rules]"
+user-invocable: true
 ---
 
 # Help Skill

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

@@ -3,6 +3,7 @@ name: omcustom:lists
 description: Show all available commands
 scope: harness
 argument-hint: "[--category <category>] [--verbose]"
+user-invocable: true
 ---
 
 # List Commands Skill

package/templates/.claude/skills/memory-recall/SKILL.md

@@ -3,6 +3,7 @@ name: memory-recall
 description: Search and recall memories from claude-mem
 scope: core
 argument-hint: "<query> [--recent] [--limit <n>]"
+user-invocable: true
 ---
 
 # Memory Recall Skill
@@ -58,6 +59,24 @@ avoid:
   - Special characters or complex syntax
 ```
 
+## Retrieval Strategy
+
+### Recall-Precision Tradeoff
+
+Default bias: **recall > precision** — it is easier to filter out irrelevant results (false positives) than to recover missed information (false negatives).
+
+| Task Type | Bias | Recommended --limit | Rationale |
+|-----------|------|--------------------:|-----------|
+| Debugging / Investigation | High recall (16:1) | 10-15 | Cast wide net, prune later |
+| Decision reference | Balanced | 5 (default) | Moderate breadth with manageable noise |
+| Specific fact lookup | High precision | 3 | Narrow, targeted retrieval |
+
+### Guidelines
+
+- **Over-retrieve, then filter**: When uncertain, request more results and discard irrelevant ones in post-processing
+- **Narrow progressively**: Start broad, refine query only if results are noisy — avoid starting too narrow
+- **Combine temporal + semantic**: Add date filters (`--date`) to semantic queries for better precision without sacrificing recall
+
 ## Output Format
 
 ### Basic Search

package/templates/.claude/skills/memory-save/SKILL.md

@@ -4,6 +4,7 @@ description: Save current session context to claude-mem
 scope: core
 argument-hint: "[--tags <tags>] [--include-code]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Memory Save Skill

package/templates/.claude/skills/model-escalation/SKILL.md

@@ -2,6 +2,7 @@
 name: model-escalation
 description: Advisory model escalation based on task outcome tracking
 scope: core
+user-invocable: false
 ---
 
 # Model Escalation Skill

package/templates/.claude/skills/monitoring-setup/SKILL.md

@@ -3,6 +3,7 @@ name: omcustom:monitoring-setup
 description: Enable/disable OpenTelemetry console monitoring for Claude Code usage tracking
 scope: package
 argument-hint: "[enable|disable|status]"
+user-invocable: true
 ---
 
 # Monitoring Setup Skill

package/templates/.claude/skills/npm-audit/SKILL.md

@@ -3,6 +3,7 @@ name: omcustom:npm-audit
 description: Audit npm dependencies for security and updates
 scope: package
 argument-hint: "[--fix] [--production]"
+user-invocable: true
 ---
 
 # NPM Audit Skill

package/templates/.claude/skills/npm-publish/SKILL.md

@@ -4,6 +4,7 @@ description: Publish package to npm registry with pre-checks
 scope: package
 argument-hint: "[--tag <tag>] [--dry-run]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # NPM Publish Skill

package/templates/.claude/skills/npm-version/SKILL.md

@@ -4,6 +4,7 @@ description: Manage semantic versions for npm packages
 scope: package
 argument-hint: "<major|minor|patch> [--no-tag] [--no-commit]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # NPM Version Management Skill
@@ -74,3 +75,30 @@ npm-version major
 # Update version without creating git tag
 npm-version patch --no-tag
 ```
+
+## Release Branch Integration
+
+When working with `auto-tag.yml` (automatic tag creation on release PR merge):
+
+1. `.npmrc` has `git-tag-version=false` — prevents local tag creation during `npm version`
+2. `auto-tag.yml` creates the tag on the **merge commit** when a `release/*` PR is merged to `develop`
+3. Do NOT manually push tags — let the CI workflow handle tag creation
+
+### Release Workflow
+
+```
+1. Create release branch: release/vX.Y.Z
+2. Run version bump (npm version / manual edit)  ← no local tag created
+3. Build dist, commit, push
+4. Create PR → merge to develop
+5. auto-tag.yml creates vX.Y.Z tag on merge commit  ← correct tag target
+6. release.yml triggers on tag → GitHub Release + npm publish
+```
+
+### Troubleshooting
+
+If a tag already exists on remote (from a previous failed attempt):
+```bash
+git push origin :refs/tags/vX.Y.Z   # delete remote tag
+# Then re-merge or let auto-tag.yml handle it
+```

package/templates/.claude/skills/optimize-analyze/SKILL.md

@@ -3,6 +3,7 @@ name: optimize-analyze
 description: Analyze bundle size and performance metrics
 scope: core
 argument-hint: "[target] [--verbose]"
+user-invocable: true
 ---
 
 # Bundle Analysis Skill

package/templates/.claude/skills/optimize-bundle/SKILL.md

@@ -4,6 +4,7 @@ description: Apply bundle size optimizations
 scope: core
 argument-hint: "[--dry-run] [--safe]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Bundle Optimization Skill

package/templates/.claude/skills/optimize-report/SKILL.md

@@ -3,6 +3,7 @@ name: optimize-report
 description: Generate comprehensive optimization report
 scope: core
 argument-hint: "[--baseline <file>] [--format <format>]"
+user-invocable: true
 ---
 
 # Optimization Report Skill

package/templates/.claude/skills/pipeline-guards/SKILL.md

@@ -3,6 +3,7 @@ name: pipeline-guards
 description: Safety constraints and quality gates for pipeline and workflow execution
 scope: core
 context: fork
+user-invocable: false
 ---
 
 # Pipeline Guards Skill

package/templates/.claude/skills/pr-auto-improve/SKILL.md

@@ -2,6 +2,7 @@
 name: pr-auto-improve
 description: Opt-in post-PR analysis and improvement suggestions for code quality enhancement
 scope: core
+user-invocable: false
 ---
 
 # PR Auto-Improvement Skill

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

@@ -228,6 +228,33 @@ Convergence expected by round 3. Hard stop at round 30.
 | Ecomode | Auto-activate for team result aggregation (R013) |
 | Intent display | Show research plan before execution (R015) |
 
+## Retrieval-Reasoning Separation
+
+Retrieval and reasoning are distinct cognitive operations that benefit from explicit role separation. Mixing them in a single agent degrades both: retrieval becomes biased by premature conclusions, and reasoning gets polluted by search noise.
+
+### Principle
+
+| Role | Phase | Model | Responsibility |
+|------|-------|-------|----------------|
+| Retriever | Phase 1 | sonnet (fast, broad) | Gather, catalog, enumerate — no judgment |
+| Reasoner | Phase 2-3 | opus (deep, precise) | Verify, synthesize, judge — no new retrieval |
+
+### Why Separate
+
+- **Retrieval bias**: A reasoning agent searching for evidence tends to confirm existing hypotheses (confirmation bias)
+- **Context pollution**: Raw search results mixed with analysis obscure both
+- **Cost efficiency**: Retrieval needs speed and breadth (cheaper model); reasoning needs depth (capable model)
+- **Debuggability**: When results are wrong, separated roles make it clear whether the problem was bad retrieval or bad reasoning
+
+### Application in Research Workflow
+
+| Phase | Role | Separation Rule |
+|-------|------|-----------------|
+| Phase 1 (10 teams) | Retriever | Teams gather and catalog only. No ADOPT/AVOID judgments. |
+| Phase 2 (Verification) | Reasoner | Verifiers challenge claims using Phase 1 data. No new searches. |
+| Phase 3 (Synthesis) | Reasoner | Synthesizer produces taxonomy from verified findings only. |
+| Phase 4 (Output) | Reporter | Formats and persists. No new analysis. |
+
 ## Model Selection
 
 | Phase | Model | Rationale |

package/templates/.claude/skills/sauron-watch/SKILL.md

@@ -3,6 +3,7 @@ name: omcustom:sauron-watch
 description: Full R017 verification (5+3 rounds) before commit
 scope: harness
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Sauron Watch Skill

package/templates/.claude/skills/skills-sh-search/SKILL.md

@@ -3,6 +3,7 @@ name: skills-sh-search
 description: Search and install skills from skills.sh marketplace when internal skills are insufficient
 scope: core
 argument-hint: "<query> [--install] [--global]"
+user-invocable: true
 ---
 
 # Skills.sh Search Skill

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

@@ -3,6 +3,7 @@ name: omcustom:status
 description: Show system status and health checks
 scope: harness
 argument-hint: "[--verbose] [--health]"
+user-invocable: true
 ---
 
 # System Status Skill

package/templates/.claude/skills/stuck-recovery/SKILL.md

@@ -2,6 +2,7 @@
 name: stuck-recovery
 description: Detect stuck loops and advise recovery strategies
 scope: core
+user-invocable: false
 ---
 
 # Stuck Recovery Skill

package/templates/.claude/skills/task-decomposition/SKILL.md

@@ -3,6 +3,7 @@ name: task-decomposition
 description: Auto-decompose large tasks into DAG-compatible parallel subtasks
 scope: core
 context: fork
+user-invocable: false
 ---
 
 # Task Decomposition Skill

package/templates/.claude/skills/update-docs/SKILL.md

@@ -4,6 +4,7 @@ description: Sync documentation with project structure
 scope: harness
 argument-hint: "[--check] [--target <path>]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Update Documentation Skill

package/templates/.claude/skills/update-external/SKILL.md

@@ -4,6 +4,7 @@ description: Update agents from external sources (GitHub, docs, etc.)
 scope: harness
 argument-hint: "[agent-name] [--check] [--force]"
 disable-model-invocation: true
+user-invocable: true
 ---
 
 # Update External Sources Skill

package/templates/.claude/skills/vercel-deploy/SKILL.md

@@ -2,6 +2,7 @@
 name: vercel-deploy
 description: Deploy applications to Vercel with auto-detection and preview URLs
 scope: core
+user-invocable: true
 ---
 
 ## When to Use

package/templates/.claude/skills/worker-reviewer-pipeline/SKILL.md

@@ -3,6 +3,7 @@ name: worker-reviewer-pipeline
 description: Worker-Reviewer iterative pipeline for quality-critical code with review cycles
 scope: core
 context: fork
+user-invocable: false
 ---
 
 # Worker-Reviewer Pipeline Skill

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

@@ -19,13 +19,32 @@ argument-hint: "<workflow-name> | (no args to list available)"
 
 ## Behavior
 
-### List Mode (no arguments)
+### List Mode (no arguments or --list flag)
 
-Scan `workflows/*.yaml` and display:
-```
-Available workflows:
-  auto-dev — verify-done issues release batch: triage → plan → implement → verify → PR
-```
+Execute these steps to display available workflows:
+
+1. **Scan built-in workflows**: Use `Glob("workflows/*.yaml")` (NOT templates/) to find all workflow definitions
+2. **Extract metadata**: For each YAML file found, use `Bash` to extract name and description:
+   ```bash
+   for f in workflows/*.yaml; do
+     name=$(grep -m1 '^name:' "$f" | sed 's/^name: *//' | tr -d '"')
+     desc=$(grep -m1 '^description:' "$f" | sed 's/^description: *//' | tr -d '"')
+     echo "  $name — $desc"
+   done
+   ```
+3. **Scan template workflows**: Use `Glob("templates/workflows/*.yaml")` for template examples
+4. **Extract template metadata**: Same extraction as step 2 for `templates/workflows/*.yaml`
+5. **Display formatted output**:
+   ```
+   Available workflows:
+     {name} — {description}
+     {name} — {description}
+
+   Template workflows (in templates/workflows/):
+     {name} — {description}
+   ```
+6. If no workflows found, display: "No workflows found in workflows/ directory."
+7. If YAML parsing fails for a file, skip it and show: `  {filename} — (parse error, skipped)`
 
 ### Run Mode (with workflow name)
 

package/templates/.claude/skills/workflow-resume/SKILL.md

@@ -1,17 +1,17 @@
 ---
-name: workflow-resume
+name: omcustom:workflow:resume
 description: Resume a halted workflow from its last failure point
 scope: harness
 user-invocable: true
 effort: medium
 ---
 
-# /workflow:resume — Resume Halted Workflow
+# /omcustom:workflow:resume — Resume Halted Workflow
 
 ## Usage
 
 ```
-/workflow:resume            # Find and resume the most recent halted workflow
+/omcustom:workflow:resume            # Find and resume the most recent halted workflow
 ```
 
 ## Behavior

package/templates/.claude/skills/writing-clearly-and-concisely/SKILL.md

@@ -2,6 +2,7 @@
 name: writing-clearly-and-concisely
 description: Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.
 scope: core
+user-invocable: false
 ---
 
 # Writing Clearly and Concisely

package/templates/manifest.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.62.5",
+  "version": "0.63.1",
   "lastUpdated": "2026-03-24T00:00:00.000Z",
   "components": [
     {