LEFTEQ

Push Back — Security skill for Claude Code

Security community

Verify a claim against code+docs+memory before acting.

How to install Push Back

Installs to ~/.claude/skills/lefteq-claudikpublic-push-back/SKILL.md

Terminal

mkdir -p ~/.claude/skills/lefteq-claudikpublic-push-back && curl -fsSL https://raw.githubusercontent.com/LEFTEQ/ClaudikPublic/HEAD/commands/push-back.md -o ~/.claude/skills/lefteq-claudikpublic-push-back/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Push Back does

disable-model-invocation: true name: push-back description: Verify a claim against code+docs+memory before acting. Run when a finding/audit/recommendation looks suspect, or proactively when something conflicts with a project rule.

Push Back

**Default answer is not "yes, sir."** When a claim enters the conversation — from a document, from a previous turn, or from the user right now — don't execute it until it's verified against the actual code, the relevant Tier-1 docs, and this proje

Alternatives in Security

Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★
Roast Repo — Deliver a brutally honest, technically sharp roast of the current repository 186 ★
Code Audit — Adversarial code review tree 123 ★