Deep mode, up to 10 lookups per turn and read-only subagents, but no edits. Use for "/shipright:deep", "go deeper", or "deep mode".
2 stars
0 votes
0 copies
0 views
Added November 7, 2026
developmentpythongo
Security analysis
A100/100
Scanned November 7, 2026
$npx -y skills add agoopintsai/shipright --skill deep --agent claude-code
Installs into .claude/skills of the current project.
Are you the author of Deep?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/agoopintsai-deep)
---
name: deep
description: Deep mode, up to 10 lookups per turn and read-only subagents, but no edits. Use for "/shipright:deep", "go deeper", or "deep mode".
---
# /shipright:deep
1. Run `python3 "${CLAUDE_PLUGIN_ROOT}/scripts/shipright_hooks.py" set deep`.
2. Relay the one-line output, including the reminder to switch the model menu to your strongest model.
## Rules while active
- Up to 10 lookups per turn, Agent included.
- Subagents must be read-only: `shipright:scout`, `scout`, `Explore`, `Plan` or `claude-code-guide`. Anything else, and Workflow, is denied.
- No edits (Edit, Write, NotebookEdit are denied). To build, switch with `/shipright:delegate`.
- Reply length and format are unrestricted. Subagent anomalies are reported (see `/shipright:mode`).
- End every reply with the marker `[deep]`.
