Start the explicit manual-root fallback after switching the current Codex thread to the configured executor model.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add TerenceLiu98/prewalk --skill pw-resume --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Pw Resume?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/terenceliu98-pw-resume-prewalk)More formats (shields.io, HTML) on the badges page.
---
name: pw-resume
description: Start the explicit manual-root fallback after switching the current Codex thread to the configured executor model.
---
# $prewalk:pw-resume - continue after a manual model switch
Run this only after `pw-go` requested the manual fallback and the user completed
`/model <executor>`:
```bash
python3 hooks/_pw.py resume "${CODEX_THREAD_ID:-${CODEX_SESSION_ID:-}}"
```
The helper reloads and prints the durable Handoff Packet. Continue the remaining
todos in the current thread, strictly in order; do not reconstruct context,
restart exploration, or repeat task 1. Verify every item before completing it.
Record the explicit manual fallback result with:
```bash
python3 hooks/_pw.py complete "${CODEX_THREAD_ID:-${CODEX_SESSION_ID:-}}"
python3 hooks/_pw.py incomplete "${CODEX_THREAD_ID:-${CODEX_SESSION_ID:-}}" "<reason>"
```
These commands reject native agent routes; native completion remains owned by
the bound agent's `SubagentStop` hook.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.