Tooluck logoTooluck
SKILL.md

skill-native-escalation-routing

Agent skill fromnyldn/claude-octopus

Use when choosing native or multi-LLM handling for init, review, or security requests

How to install skill-native-escalation-routing

install skill-native-escalation-routing
# install the claude-octopus pack with the skills CLI
npx skills add nyldn/claude-octopus

# or add only this skill to Claude Code: copy the folder

skills/skill-native-escalation-routing/

# into

~/.claude/skills/skill-native-escalation-routing/ (all projects)

.claude/skills/skill-native-escalation-routing/ (one project)

skills/skill-native-escalation-routing/SKILL.md

MITFull file
1> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.
2> Cross-reference commands use installed skill names in Codex rather than `/octo:*` slash commands.
3> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.
4> For host tool equivalents, see `skills/blocks/codex-host-adapter.md`.
5
6
7# Native-First Escalation Routing
8
9Use this skill when the user asks for repository initialization, code review, or security review and it is not yet clear whether Claude-native behavior is sufficient or whether Octopus escalation is warranted.
10
11## Core Policy
12
13Claude-native first:
14
15- `/init`
16- `/review`
17- `/security-review`
18
19Octopus for escalation:
20
21- `/octo:review`
22- `/octo:security`
23- `/octo:debate`
24- `/octo:multi`
25
26## Route to Claude-Native First
27
28Prefer Claude-native behavior when all of the following are true:
29
30- the request maps directly to init, review, or security review
31- the user did not ask for multiple model opinions
32- the user did not ask for Codex, Antigravity, or another provider explicitly
33- the task does not require adversarial debate, consensus scoring, or external-provider specialization
34
35Examples:
36
37- "initialize this repo"
38- "review my staged changes"
39- "security review this auth module"
40
41## Escalate to Octopus
42
43Escalate when the user asks for or clearly benefits from:
44
45- multiple model opinions
46- adversarial review
47- debate between providers
48…

Excerpt shown under the repository's MIT license.

More skills in claude-octopus

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates