richfrem/agent-plugins-skills / plugins/agent-orchestration/.apm/skills/orchestrating-agent-work
orchestrating-agent-work
VerifiedInteractive orchestrator for complex engineering work. Analyzes the task, conducts a diagnostic interview to select the appropriate execution strategy (Directed Acyclic Graph versus Loop, and which Loop type), plans the artifact, and supervises execution and verification. Use for "how should I orchestrate this", "plan this workflow", "should this be a DAG or a loop", "run these jobs in parallel", "delegate this to a worker agent", or "run/resume this graph manifest". Not for single trivial edits or skill self-improvement.
assets/templates/dual-loop-meta-tasks.md
View on GitHub# Dual-Loop Meta-Tasks
<!-- To be included in Session Task List for any Dual-Loop Execution -->
## Phase A: Strategy (Outer Loop)
- [ ] **Verify planning artifacts**: Confirm spec, plan, and task documents exist
- [ ] **Query User**: Select the LLM CLI backend (e.g., `agy`, `claude`) and specific model to use
- [ ] **Create worktree**: Create an isolated workspace for the Inner Loop (or use branch-direct mode)
- [ ] **Generate Strategy Packet**: Create a targeted markdown packet holding context and acceptance criteria for the inner loop
## Phase B: Hand-off & Execution
- [ ] **Hand off to Inner Loop**: Launch the inner agent with the strategy packet using `run_agent.py` with redirected stdin (e.g., `python scripts/run_agent.py handoffs/task_packet_NNN.md <target_file> handoffs/result_packet.md "Execute strategy packet" --cli <selected_cli> --model "<selected_model>" < /dev/null`)
- [ ] **Inner Loop completes**: All acceptance criteria met, no git commands used
## Phase C: Verification (Outer Loop)
- [ ] **Verify result**: Run tests, check deltas, and validate output against the strategy packet
- [ ] **Verify clean state**: Ensure no git rules were violated and the inner loop workspace is clean
- [ ] **On PASS**: Commit in worktree, update task lane to `done`
- [ ] **On FAIL**: Hand off `correction_packet_NNN.md`, repeat Phase B
## Phase D: Closure
- [ ] **Seal**: Validate changes and record current state
- [ ] **Persist**: Sync session traces to long term memory
- [ ] **Retrospective**: Analyze session performance
- [ ] **End**: Push to remote and close domain
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |