Commit 8ea8b8

2026-03-16 04:04:58 Claude (MCP): [mcp] Document implementation workflow with Sonnet subagent pipeline
/dev/null .. Design/Implementation_Workflow.md
@@ 0,0 1,94 @@
+ ---
+ category: reference
+ tags: [process, agents, workflow]
+ last_updated: 2026-03-16
+ confidence: high
+ ---
+
+ # Implementation Workflow
+
+ How Claude Code orchestrates implementation tasks on robot.wtf using Sonnet subagents.
+
+ ## Principles
+
+ - **Opus orchestrates, Sonnet implements.** No Opus manager layer. The orchestrator (main Claude Code session) dispatches Sonnet agents directly.
+ - **Background everything.** Subagents, deploys, and tool calls run in background (`run_in_background: true`) so the orchestrator and user can keep talking.
+ - **Task list tracks the pipeline.** Each implementation task gets 5-6 task list items with dependencies. The orchestrator dispatches agents as blockers clear.
+ - **Rule of Two.** No subagent output is merged without independent verification by a second agent.
+ - **No VPS mutations outside Ansible.** Read-only SSH diagnostics only. All changes go through Ansible playbooks.
+
+ ## Pipeline per task
+
+ When the user and orchestrator agree on an implementation task:
+
+ ### 1. Plan (Sonnet Plan agent)
+ - Reads relevant code
+ - Produces implementation plan with specific file changes
+ - Orchestrator reviews plan with user if non-trivial
+ - **Dispatch:** immediately
+
+ ### 2. Implement (Sonnet agent, worktree isolation)
+ - Gets the plan output + file paths
+ - Writes code, writes tests, commits to feature branch
+ - **Dispatch:** when Plan completes
+ - **Always use `isolation: "worktree"`**
+
+ ### 3. Chico review (Sonnet agent)
+ - Code quality, correctness, edge cases
+ - Rates issues: critical / important / minor
+ - **Dispatch:** when Implement completes (parallel with Zeppo)
+
+ ### 4. Zeppo review (Sonnet agent)
+ - Security, infrastructure, deployment concerns
+ - Same rating scale
+ - **Dispatch:** when Implement completes (parallel with Chico)
+
+ ### 5. Fix (Sonnet agent, same worktree)
+ - Gets review output + code
+ - Fixes critical and important issues
+ - Recommits to same branch
+ - **Dispatch:** when both reviews complete
+ - **Skip if:** no critical or important issues found
+
+ ### 6. Verify (Sonnet agent)
+ - Reads the diff
+ - Runs tests if they exist
+ - Confirms changes match the spec
+ - Reports pass/fail
+ - **Dispatch:** when Fix completes (or after Implement if no Fix needed)
+
+ ### 7. Report
+ - Orchestrator summarizes results and any concerns to the user
+ - User approves
+ - Orchestrator merges and deploys via Ansible
+
+ ## Task list structure
+
+ For a task "Foo", create these items:
+
+ ```
+ - [ ] Foo: Plan
+ - [ ] Foo: Implement (blocked by Plan)
+ - [ ] Foo: Chico review (blocked by Implement)
+ - [ ] Foo: Zeppo review (blocked by Implement)
+ - [ ] Foo: Fix (blocked by Chico + Zeppo)
+ - [ ] Foo: Verify (blocked by Fix)
+ ```
+
+ Mark each `in_progress` when the agent launches, `completed` when it returns.
+
+ ## Agent prompts
+
+ Keep prompts short and specific:
+ - "Read X, change Y, commit to branch Z"
+ - Include the Plan output for implementers
+ - Include the diff for reviewers
+ - Include review findings for fixers
+ - All agents: "Do NOT use git add -A. ALWAYS commit before reporting back. Do NOT push or merge."
+
+ ## What NOT to do
+
+ - Don't launch Opus managers that delegate to Sonnet workers (they do the work themselves at Opus cost)
+ - Don't merge without verification
+ - Don't debug VPS issues via SSH mutations
+ - Don't ask the user if they're done
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9