fleet-doctrine

Model routing strategy for multi-model AI fleet. Use when spawning sub-agents, choosing models for cron jobs, delegating coding tasks, or deciding which model should handle a task. Covers Opus, Codex, Sonnet, Gemini, and Grok routing rules.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "fleet-doctrine" with this command: npx skills add jarvis-drakon/fleet-doctrine

Fleet Doctrine — Model Routing

Aliases

  • opusanthropic/claude-opus-4-6
  • sonnetanthropic/claude-sonnet-4-6
  • codexopenai-codex/gpt-5.3-codex
  • Gemini: google/gemini-3-pro-preview
  • Grok: xai/grok-4

Routing Rules

Opus — Commander

When: Main session, orchestration, security decisions, financial tasks, reviewing other models' output, anything high-stakes or ambiguous. Never waste on: Routine crons, simple lookups, email summaries, templated tasks.

Codex — Chief Engineer

When: Big coding tasks (refactors, new features, full repo work), PR reviews, debugging complex issues, checking other models' code output. Spawn as: sessions_spawn(model: "codex", task: "...") or sub-agent with --model codex. Pairs with: Grok for parallel work or second opinions on code.

Sonnet — Workhorse

When: Cron jobs, email briefings, admissions reports, routine admin, quick lookups, drafts, form letters, anything repetitive or templated. Default for: All crons unless the task requires reasoning.

Gemini — Creative & Vision

When: Image generation, analysing long documents (1M context), visual tasks, when a different perspective helps. Best at: Processing massive context windows, multimodal input.

Grok — Fast Backup

When: Parallel work alongside Codex, speed-over-depth tasks, sanity-checking other models' output, when you need a quick second opinion. Good for: Lightweight code reviews, fast research, draft generation.

Decision Flow

  1. Is it security, finance, or high-stakes? → Opus
  2. Is it a big coding task or repo work? → Codex (with Grok as backup)
  3. Does it need image gen or 1M+ context? → Gemini
  4. Is it routine/scheduled/templated? → Sonnet
  5. Need a fast second opinion? → Grok
  6. Not sure? → Opus decides, then delegates.

Fallback Rule

If a model is unavailable on your instance, fall back to your default model (typically Sonnet). The doctrine describes intent — use the best model you have access to that matches the category. When in doubt, do the task with what you've got rather than failing.

Anti-Patterns

  • Don't use Opus for email summaries or cron jobs
  • Don't use Sonnet for complex multi-step reasoning
  • Don't use Codex for non-coding tasks
  • Don't spawn multiple models on the same task unless deliberately seeking a second opinion

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

V19 Trust Manifesto

Agent Community认知治理协议公开受信声明v1.2.93。核心协议工程化完成(V94联通/DLP状态机知识图谱钩子/治理锚点INITIAL_TRUST_ANCHOR=4.0/72h未交互Agent自动标记/kpc_feedback_deposit跨模块接口打通)。任务市场完整生命周期(发布→认领→提交...

Registry SourceRecently Updated
Automation

Databricks Labs

Databricks is a unified data and AI platform from Apache Spark founders, integrating data engineering, analytics, and machine learning workflows on a Lakehou...

Registry SourceRecently Updated
Automation

Find Agent

OceanBus-powered agent and service discovery via Yellow Pages. Use when users want to find someone, look for a service, reach out to an expert, discover anot...

Registry SourceRecently Updated
Automation

Appdynamics

AppDynamics is Cisco's APM platform offering full-stack application, infrastructure, and user experience monitoring with integrated AIOps for enterprise obse...

Registry SourceRecently Updated