Guard the deploy script against being pointed at production by accident. Use when the user asks to deploy, ship, or release, and when a deploy command is being drafted. Not for local builds or test runs, which no guard covers.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add tjdwls101010/Harness-Creator --skill deploy-guard --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Deploy Guard?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/tjdwls101010-deploy-guard)More formats (shields.io, HTML) on the badges page.
---
name: deploy-guard
description: Guard the deploy script against being pointed at production by accident. Use when the user asks to deploy, ship, or release, and when a deploy command is being drafted. Not for local builds or test runs, which no guard covers.
hooks:
PreToolUse:
- matcher: Bash
hooks:
- type: command
command: hooks/check-target.sh
- type: command
command: hooks/check-target.sh
once: true
"PostToolUse":
- matcher: Bash
hooks:
- type: command
command: "${CLAUDE_PROJECT_DIR}/.claude/hooks/shared-audit.sh"
args: []
---
# deploy-guard
The deploy script takes `--env` and refuses to run without it, so the ordinary
mistake is impossible. What remains is the one this hook covers: a `--env prod`
typed during a session that was only ever meant to touch staging.
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!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
