skilld
All skills
oaustegard avatar

/agent-routing

@576f2c8
by Oskar Austegardoaustegard/claude-skills150 stars
6

Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when spawning subagents via the Agent or Workflow tools, when choosing how to escalate a failed attempt, when fanning out more than a handful of agents, or when asked which model or effort a task should get. Grounded in measured calibration (references/calibration-2026-07-15.md), a 2026-08 coding-cost study, and a 2026-09 agentic-repair battery that measured the cascade rungs directly; Managed Agents API specifics are operational, not calibrated.

Ask your Agent

Use this Skill: https://skilld.dev/gh/oaustegard/claude-skills/agent-routing

This session only. Nothing lands on disk.

README.md

≈200 tokens on demand. Your agent reads this file only when SKILL.md points to it.

agent-routing

Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when spawning subagents via the Agent or Workflow tools, when fanning out more than a handful of agents, or when asked which model or effort a task should get. Grounded in measured calibration (references/calibration-2026-07-15.md) plus a 2026-08 coding-cost study; Managed Agents API specifics are operational, not calibrated.

Source: SKILL.md on GitHub

Third-party checks

No alerts12d3 checks · Risk SAFE
  • Gen Agent Trust Hub12d

    The skill provides technical guidelines for routing tasks between different AI models and managing subagent orchestration. It is generally safe; however, it encourages a workflow where untrusted data, such as file scan outputs, is passed directly into subagent prompts, which creates a surface for indirect prompt injection.

  • Socket12d

    No alerts

  • Snyk12d

    Risk: LOW · No issues

Provenance

Signed by skilld at 576f2c8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 3 days ago

Capability

metadata
{
  "author": "Oskar Austegard and Claude",
  "version": "2.3.0"
}
Other metadata
compatibility
Designed for Claude Code / Claude Code on the Web — assumes an orchestrator with Agent/Workflow subagent tools. Only the Workflow tool sets a subagent's effort; the Agent tool sets its model. Not applicable to claude.ai chat use.

README badge

README badge for oaustegard/claude-skills/agent-routing