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.
references/strategy-dual-loop.md
View on GitHub# Strategy: dual-loop (supervisor / worker)
Splits work between a strategic Outer Loop (Supervisor) and an execution-focused Inner Loop (tactical coding sub-agent).
## Constraints
- **Inner loop isolation**: Inner Loop agents are strictly forbidden from running `git` commands.
- **Background execution**: Always redirect standard input (`< /dev/null`) to avoid `SIGTTIN` hangs.
- **Verification gate**: Outer Loop must mechanically verify tests and diffs before merging.
- **Single commit rule**: Commits and merges are executed exclusively by the Outer Loop.
## Quick start
Dispatch the inner loop through the `cli-agent` skill (cli-agents plugin), run from that skill's root:
```bash
python3 scripts/run_agent.py handoffs/task_packet_001.md <target_file> handoffs/result.md \
"Execute strategy packet exactly." --cli <cli> --model "<model>" < /dev/null
```
## Workflow
1. **Decomposition**: Break work into atomic, testable Work Packages.
2. **Model Selection**: Select companion backend (`agy`, `claude`, `copilot`, `codex`, `llama`) via [cheapest_models.json](cheapest_models.json).
3. **Strategy Packet**: Author `handoffs/task_packet_NNN.md` in isolated worktree specifying scope and "NO GIT" rule.
4. **Supervised Review**: Outer Loop audits `git diff` for authorized paths and zero stub placeholders.
5. **Retrospective**: Conduct post-run assessment using [post_run_survey.md](post_run_survey.md); escalate repeat friction to the agent-agentic-os skill lab (os-lab).
## Verification
```bash
# Verify delta and ensure zero stub placeholders
git -C <WORKTREE_PATH> diff --stat
# Run automated tests against worktree output
pytest <TEST_TARGET>
```
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 |