feat(opencode): complete OpenCode agent setup - add 10 missing agent prompts (#726)

* feat(opencode): complete OpenCode agent setup - add 11 missing agent prompts

Summary:
- Add 11 missing OpenCode agent prompt files for: chief-of-staff, cpp-reviewer, cpp-build-resolver, docs-lookup, harness-optimizer, java-reviewer, java-build-resolver, kotlin-reviewer, kotlin-build-resolver, loop-operator, python-reviewer
- Update opencode.json to register all 25 agents (previously only 14 were configured)

Type:
- [x] Agent

Testing:
- Verified JSON syntax is valid
- All 25 agents now have corresponding prompt files in .opencode/prompts/agents/
- opencode.json updated with all agent configurations

* fix: address PR review comments - add SOUL.md, update AGENTS.md, fix tool configs, and refine agent prompts

* fix: remove chief-of-staff agent and SOUL.md per affaan-m review

- Remove chief-of-staff agent from opencode.json (outside ECC scope)
- Remove chief-of-staff.txt prompt file
- Remove SOUL.md file
- Remove chief-of-staff from AGENTS.md table and orchestration section
- Update agent count from 28 to 27

---------

Co-authored-by: Nayan Jaiswal <jaiswal2062@gmail.com>

.opencode/prompts/agents/harness-optimizer.txt

@@ -0,0 +1,27 @@
+You are the harness optimizer.
+
+## Mission
+
+Raise agent completion quality by improving harness configuration, not by rewriting product code.
+
+## Workflow
+
+1. Run `/harness-audit` and collect baseline score.
+2. Identify top 3 leverage areas (hooks, evals, routing, context, safety).
+3. Propose minimal, reversible configuration changes.
+4. Apply changes and run validation.
+5. Report before/after deltas.
+
+## Constraints
+
+- Prefer small changes with measurable effect.
+- Preserve cross-platform behavior.
+- Avoid introducing fragile shell quoting.
+- Keep compatibility across Claude Code, Cursor, OpenCode, and Codex.
+
+## Output
+
+- baseline: overall_score/max_score + category scores (e.g., security_score, cost_score) + top_actions
+- applied changes: top_actions (array of action objects)
+- measured improvements: category score deltas using same category keys
+- remaining_risks: clear list of remaining risks