chore: Bump version to 2.3.0, update release metadata

- plugin.json: 2.2.1 -> 2.3.0
- README.md: Add v2.3.0 release notes (orchestrator-dispatch pattern,
  skill preloading, model: sonnet for expert dispatch)
- docs/PLAN.md: Agent count 22 -> 23 (git-agent added)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-mods",
-  "version": "2.2.1",
+  "version": "2.3.0",
   "description": "Custom commands, skills, and agents for Claude Code - session continuity, 23 expert agents, 64 skills, 3 commands, 5 rules, 3 hooks, 4 output styles, modern CLI tools",
   "author": "0xDarkMatter",
   "repository": "https://github.com/0xDarkMatter/claude-mods",

README.md

@@ -22,6 +22,14 @@ From Python async patterns to Rust ownership models, from AWS Fargate deployment
 
 ## Recent Updates
 
+**v2.3.0** (March 2026)
+- 🎯 **Orchestrator-dispatch pattern** - Three skills upgraded from static reference dumps to active orchestrators that classify intent, dispatch to agents, and manage safety tiers:
+  - **`git-ops`** + **`git-agent`** - First skill+agent pair. Orchestrator routes T1 reads inline, dispatches T2 writes and T3 destructive ops to a dedicated Sonnet background agent with preflight confirmation. Replaces `git-workflow`.
+  - **`perf-ops`** - Routes profiling to language experts (python-expert for py-spy, go-expert for pprof, etc.). Parallel CPU+memory profiling, before/after benchmarking protocol.
+  - **`security-ops`** - 3 parallel audit agents (dependency scan, SAST patterns, auth/config review) consolidate into OWASP-mapped severity report. Modelled on techdebt's parallel scanner architecture.
+- 📚 **Skill preloading** - Dispatching skills now instruct agents to read relevant skill references before starting work. Review and testgen agents load security-ops + testing-ops context. Perf-ops agents load profiling references. Git-agent loads CI/CD context for releases.
+- 🔧 **`model: sonnet`** specified for all expert dispatch - Cheaper, faster analysis without sacrificing quality for read-only review, test generation, and profiling tasks.
+
 **v2.2.0** (March 2026)
 - 🔍 **`/introspect` enhanced** - Now generates Session Insights after every analysis: workflow improvements, skill suggestions, and ready-to-paste permission configs to reduce interruptions. Scales recommendations to session size.
 - 🔧 **`/setperms` expanded** - Default template now includes 74 tool permissions (was 51): docker, cargo, go, pytest, npx, pnpm, yarn, bun, make, archive tools, data utilities.

docs/PLAN.md

@@ -12,7 +12,7 @@
 
 | Component | Count | Notes |
 |-----------|-------|-------|
-| Agents | 22 | Domain experts (Python, Go, Rust, React, etc.) |
+| Agents | 23 | Domain experts + git-agent background worker |
 | Skills | 64 | Operational skills, CLI tools, workflows, dev tasks |
 | Commands | 3 | Session management (sync, save) + experimental (canvas) |
 | Rules | 5 | CLI tools, thinking, commit style, naming, skill-agent-updates |