@dzhechkov/harness-cli 0.3.60 → 0.3.62

package/README.md

@@ -85,7 +85,7 @@ dz benchmark packages/@dzhechkov/skills-devops --all   # batch all
 dz benchmark skill-a --compare skill-b          # A/B compare
 
 # Find skills to canonicalize from the ecosystem:
-dz scout                                        # scan 9 sources (GitHub, npm+plugins, HN, ...)
+dz scout                                        # scan 10 sources (GitHub, npm+plugins, HN, ...)
 dz scout --deep                                 # deep analysis with SKILL.md parsing
 dz auto-canonicalize --source github.com/user/repo --pack packages/@dzhechkov/skills-devops
 ```
@@ -259,7 +259,7 @@ dz scout --topics mcp-server,ai-agent # custom topics
 dz scout --since 2026-05-01           # only recent repos
 ```
 
-**Radar mode** (`dz scout`) scans **9 sources in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv):
+**Radar mode** (`dz scout`) scans **10 sources in parallel (GitHub + npm + HN + MCP Registry + Glama + OSSInsight + Smithery + Semantic Scholar + arXiv + ECC):
 1. **Detects skill format** — SKILL.md, plugin.json, .claude/skills/, .claude-plugin/, MCP manifests
 2. **Scores relevance** — format (40%) + stars (30%) + recency (20%) + novelty (10%)
 3. **Compares against our 30 packages** — finds skills we don't have
@@ -539,6 +539,40 @@ dz init --target codex --preset meta --enrich
 
 ---
 
+## Example: Understand & Develop an Existing Project
+
+```bash
+# 1. Analyze project → get recommendations
+dz pretrain                                     # detects stack, recommends presets
+dz recommend "work on this Node.js API"         # suggests skills + toolkits
+
+# 2. Install skills
+dz setup --target claude-code --preset meta     # 8 core skills + self-learning
+dz setup --target claude-code --preset qe-engineer  # 20 QE skills
+```
+
+Then in Claude Code:
+```
+# 3. Map the codebase (requires Understand-Anything plugin)
+/understand                                      # builds knowledge graph
+# → understand-anything-bridge feeds architecture context to all skills
+
+# 4. Develop with full context
+"Add a payment module"
+# → feature-adr runs with architecture awareness (layers, hot spots, dependencies)
+# → code generation informed by real dependency graph
+# → QE review targets tests at high-impact files
+# → agentshield-scan checks new configs for security
+
+# 5. Verify impact
+"What files are affected by my changes?"
+# → blast radius calculation → targeted test generation
+```
+
+Architecture-aware development: every skill knows the codebase structure.
+
+---
+
 ## Self-Learning: JSONL vs AgentDB
 
 DZ Harness supports two memory backends for self-learning:
@@ -804,7 +838,7 @@ npx @dzhechkov/p-replicator init
 
 ## Status
 
-`v0.3.58` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
+`v0.3.61` — published on npm. Also available as [Claude Plugin](#claude-plugin). Part of [DZ Harness Hub](https://github.com/djd1m/dz-harness-hub).
 
 ## Claude Plugin
 
@@ -819,7 +853,7 @@ claude plugin install dz-harness-hub@dz-harness-hub
 claude --plugin-dir /path/to/dz-harness-hub
 
 # Generate plugin manifest from current inventory:
-dz plugin --version 0.3.52
+dz plugin --version 0.3.61
 ```
 
 The `.claude-plugin/` directory contains `plugin.json` + `marketplace.json` compatible with [pi-claude-marketplace](https://npm.im/pi-claude-marketplace) and [skill-hub](https://npm.im/@jasonwen/skill-hub).

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@dzhechkov/harness-cli",
-  "version": "0.3.60",
+  "version": "0.3.62",
   "description": "The dz CLI — install AI skills for Claude Code, Codex, OpenCode, Hermes. 11 commands, 7 presets, 4 platform adapters.",
   "type": "module",
   "license": "MIT",