Skip to content

richfrem/agent-plugins-skills / plugins/agent-orchestration/.apm/skills/orchestrating-agent-work

orchestrating-agent-work

Verified

Interactive 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.

FileKindSize
SKILL.mdskill md6.8 KB
assets/templates/dual-loop-meta-tasks.mdmarkdown1.6 KB
assets/templates/loop_retrospective_template.mdmarkdown1.5 KB
assets/templates/red_team_briefing_template.mdmarkdown747 B
assets/templates/scratchpad-template.mdmarkdown991 B
assets/templates/strategy-packet-template.mdmarkdown1.2 KB
assets/templates/workflow-retrospective-template.mdmarkdown1.3 KB
evals/evals.jsonconfig7.0 KB
references/PATTERN_GUIDE.mdmarkdown6.2 KB
references/acceptance-criteria.mdmarkdown6.8 KB
references/agentic-os-reuse-map.mdmarkdown2.5 KB
references/bot-delegation-patterns.mdmarkdown5.2 KB
references/cheapest_models.jsonconfig845 B
references/cheapest_models.mdmarkdown1.1 KB
references/cli-agent-executor.mdmarkdown3.5 KB
references/delegated-dag-refactoring-playbook.mdmarkdown5.5 KB
references/diagrams/agent_swarm.mmdother1.8 KB
references/diagrams/dual_loop_architecture.mmdother1.4 KB
references/diagrams/graph-planner-flow.mmdother540 B
references/diagrams/graph_execution_state_machine.mmdother823 B
references/diagrams/orchestrating_agent_work_architecture.mmdother4.5 KB
references/dispatch-preflight.mdmarkdown2.1 KB
references/fallback-tree.mdmarkdown9.7 KB
references/graph-execution.mdmarkdown4.1 KB
references/graph-manifest-schema.jsonconfig7.0 KB
references/graph-planning.mdmarkdown3.0 KB
references/learning-loop.mdmarkdown4.9 KB
references/patterns.jsonconfig2.0 KB
references/post_run_survey.mdmarkdown1.4 KB
references/routing-and-closure.mdmarkdown2.4 KB
references/strategy-agent-swarm.mdmarkdown2.1 KB
references/strategy-dual-loop.mdmarkdown1.6 KB
references/strategy-red-team-review.mdmarkdown2.0 KB
references/strategy-selection.mdmarkdown4.0 KB
references/topology-rules.mdmarkdown6.0 KB
scripts/agent_orchestrator.pyscript7.6 KB
scripts/dispatch_guard.pyscript1.1 KB
scripts/graph_runner.pyexecutablescript36.3 KB
scripts/select_strategy.pyscript13.1 KB
scripts/swarm_run.pyscript28.0 KB
scripts/validate_manifest.pyexecutablescript19.8 KB
scripts/work_loop.pyscript28.0 KB
tests/_loop_fixtures.pyscript2.5 KB
tests/test_graph_fixes.pyscript12.6 KB
tests/test_graph_runner.pyscript30.0 KB
tests/test_isolation.pyscript3.5 KB
tests/test_loop_strategies.pyscript7.7 KB
tests/test_select_strategy.pyscript7.8 KB
tests/test_swarm_run.pyscript9.4 KB
tests/test_swarm_run_models.pyscript3.1 KB
tests/test_validate_manifest.pyscript18.1 KB
tests/test_work_loop_e2e.pyscript3.8 KB
tests/test_work_loop_hardening.pyscript27.3 KB

references/cli-agent-executor.md

View on GitHub
---
name: cli-agent-executor
description: >
  CLI Sub-Agent System (Claude, Gemini, Copilot) for persona-based analysis. Use when piping
  large contexts to LLM CLI models for security audits, architecture reviews,
  QA analysis, or any specialized analysis requiring a fresh model context.
---

## Ecosystem Role: Inner Loop Specialist

This reference describes specialized **Inner Loop Execution** patterns for the `dual-loop` skill.

- **Orchestrated by**: the `orchestrating-agent-work` skill (routing step)
- **Use Case**: When "generic coding" is insufficient and specialized expertise (Security, QA, Architecture) is required.
- **Why**: The CLI context is naturally isolated (no git, no tools), making it the perfect "Safe Inner Loop".

## Identity: The Sub-Agent Dispatcher 🎭

You, the Antigravity agent, dispatch specialized analysis tasks to the CLI sub-agents natively supported by this ecosystem (claude-cli, agy-cli, copilot-cli).

## 🛠️ Core Pattern
```bash
# Recommended: Run via run_agent.py multi-LLM router
python scripts/run_agent.py <PERSONA_PROMPT> <INPUT> <OUTPUT> "<INSTRUCTION>" --cli agy

# Direct execution (using file-ref system prompt and stdin redirection):
agy --dangerously-skip-permissions -p "$(cat <PERSONA_PROMPT>)" < <INPUT> > <OUTPUT>
```

## ⚠️ CLI Best Practices

### 1. Token Efficiency — PIPE, Don't Load
**Bad** — loads file into agent memory just to pass it:
```python
content = read_file("large.log")
run_command(f"<cli_engine> -p 'Analyze: {content}'")
```
**Good** — direct shell piping:
```bash
<cli_engine> -p "Analyze this log" < large.log > analysis.md
```

### 2. Self-Contained Prompts
The CLI runs in a **separate context** — no access to agent tools or memory.
- **Add**: "Do NOT use tools. Do NOT search filesystem."
- Ensure prompt + piped input contain 100% of necessary context

### 3. Output to File
Always redirect output to a file (`> output.md`), then review with `view_file`.

## 🎭 Specialization via System Prompts

Specialized behavior is achieved by passing a system prompt file to the CLI agent. The source
of that system prompt is up to you — user-supplied, from an installed persona plugin
(e.g., `agent-personas`), or inline in the command.

```bash
# With a system prompt file (running via run_agent.py router):
python scripts/run_agent.py system_prompt.md pr.md review.md "Review this PR" --cli claude

# Without a system prompt (general-purpose direct execution):
claude -p "Analyze this code for security issues" < input.md > analysis.md

# Antigravity (agy) equivalent:
python scripts/run_agent.py system_prompt.md bundle.md audit.md "Audit this architecture" --cli agy
```

## 🔄 Recommended Audit Loop

When asked to perform a comprehensive "Audit Loop", construct a sequence of CLI dispatches
passing the SAME `bundle.md` or context block to consecutive specialist prompts.

1. **Security Review**
   `python scripts/run_agent.py security_prompt.md bundle.md audit_01_security.md "ACT AS SECURITY AUDITOR. Focus on vulnerabilities." --cli agy`

2. **Architecture Review**
   `python scripts/run_agent.py architect_prompt.md bundle.md audit_02_architecture.md "ACT AS ARCHITECT REVIEWER. Focus on patterns and complexity." --cli agy`

3. **QA Review**
   `python scripts/run_agent.py qa_prompt.md bundle.md audit_03_qa.md "ACT AS QA EXPERT. Focus on testability and edge cases." --cli agy`

Always run the Architect **AFTER** the Security review to catch any security-driven side effects
that may have artificially inflated the system's complexity.
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: 469kUpdated Claude CodeCodexVerifiedInstall
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: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 321kUpdated Claude CodeCodexVerifiedInstall