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/cheapest_models.md
View on GitHub# CLI Cheapest Models Reference
This is the single source of truth for current model costs per CLI engine.
Update here only — do not hardcode model names or cost claims in SKILL.md or agent files.
| CLI Engine | Model | Cost Tier | Notes |
|---|---|---|---|
| `llama` | `gemma-4-12b` | **Free** (self-hosted) | Local `llama-server` on port 8089. Only truly zero-cost option. |
| `copilot` | `gpt-5.6-luna` | Paid (AI Credits) | 20 cr/1M input, 120 cr/1M output. MAI-Code-1.1-Flash: 25/200; cache read 2.5, cache write 0. |
| `agy` | `gemini-3.8-flash` | Paid (Per-token / Pro quotas) | Antigravity CLI — replacement for deprecated `gemini` CLI; select Low effort separately for cost-sensitive calls. |
| `claude` | `claude-haiku-4-5` | Paid (Per-token) | $1/MTok input, $5/MTok output. |
| `codex` | `gpt-5.6-luna` | Paid (Per-token) | $0.20/1M input, $1.20/1M output; current cost-sensitive OpenAI model. |
> [!WARNING]
> Only `llama` (self-hosted Gemma 4) is free. Copilot, Gemini/Agy, and Claude all bill per token as of June 2026.
> The standalone `gemini` CLI (Google) was deprecated and shut down June 18, 2026 — use `agy` instead.
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 |