Audit Strict — Security skill for Claude Code
Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings.
How to install Audit Strict
Installs to ~/.claude/skills/omermaksutii-rugproof-audit-strict/SKILL.md
mkdir -p ~/.claude/skills/omermaksutii-rugproof-audit-strict && curl -fsSL https://raw.githubusercontent.com/omermaksutii/RugProof/HEAD/commands/audit-strict.md -o ~/.claude/skills/omermaksutii-rugproof-audit-strict/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Strict does
description: Multi-pass consensus audit — runs the audit twice with different prompts, only reports consensus findings. Aggressively cuts false positives. argument-hint: "[file-or-dir]" allowed-tools: Read, Bash, Agent, Skill
/audit-strict — consensus-based audit
Same surface as `/audit`, but each finding must be *independently produced* by two passes to be reported.
Procedure
Step 1 — Pass A: bottom-up
Read the code function by function. For each function:
- Apply the vuln
Alternatives in Security
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
- Goal Prompt Builder — Build audit-friendly /goal prompts for OpenAI Codex 225 ★
- Senior Engineering Partner — A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/A 148 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Fp Review
Triage security scanner findings as true or false positives. Generates precise Semgrep rule tuning for FPs and
App Security Skills
Claude Code skill: security + code review in one pass. Evidence-gated findings, invariant-based hunting, deep
Vuln Scan
Multi-agent security vulnerability sweep — fans out region-scoped hunters, verifies findings, and reports
Breachguard
Methodology-driven Claude skill for security and code-quality audits, with threat modeling, false-positive ver
Kai Review Project
Audit a project's AI system against brigade conventions and project-structure rules. Reports PASS/FAIL per che
Feedback To Closure
Turn raw feedback (reports, Sentry, reviews, QA/audit findings) into deduplicated durable tickets and drive ea
Related Agents
Review Arbiter
Authoritative LLM-as-a-Judge meta-agent that adjudicates multi-agent plan and code reviews whenever two or mor
Ddw Sec Auditor
Security auditor. Spawn it in CODE when a SAST scan reports findings, to triage them before anyone starts fixi
Daw Sec Auditor
Security auditor. Spawn it in CODE when a SAST scan reports findings, to triage them before anyone starts fixi