GPT Pro Audit — Security skill for Claude Code
Agent skill that audits code and plans with connected GitHub context and a strong ChatGPT model using Effort Pro through Chrome.
How to install GPT Pro Audit
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open hubeiqiao/gpt-pro-audit and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What GPT Pro Audit does
Agent skill that audits code and plans with connected GitHub context and a strong ChatGPT model using Effort Pro through Chrome.
Alternatives in Security
- Data Viz Audit — Audit a data visualization for chart type selection, accessible color palette, annotations, and anti-patterns 309 ★
- Migration Agent — Plans a token migration (format, tool, naming or tier): chains token-audit and naming-audit, builds the transf 194 ★
- Sail Skill — SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments, secur 122 ★
README
gpt-pro-audit
[](https://skills.sh/hubeiqiao/gpt-pro-audit/gpt-pro-audit)
About
A reusable Codex/Claude skill that automatically packages codebase context and sends plans, diffs, documents, and implementation proposals to a strong ChatGPT model running with `Effort Pro` through the user's authenticated Chrome session for an external audit.
This skill sends selected content to ChatGPT/OpenAI through the user's authenticated account; do not use it for secrets or unredacted sensitive data.
Invoking the skill authorizes the selected artifact and its minimum necessary audit context. It does not require a separate "go" confirmation, but it does not authorize a broader payload or override browser and platform confirmation requirements.
ChatGPT does not know your codebase, local files, current branch, or project constraints. This skill is designed to gather and provide that context automatically so the audit is grounded instead of generic.

The skill focuses on:
- packaging enough context for a useful external review
- attaching
@GitHuband the full audit context in one message, with the exact repo, commit, and PR - starting automatically after invocation for the selected artifact
- automatically giving ChatGPT the repo/project context it cannot see
- verifying that the visible reasoning setting is exactly
Effort Pro - running up to 5 review rounds until GPT Pro accepts the revised plan
- actively revising the artifact between rounds instead of just relaying feedback
- resuming smoothly after browser slowdowns or context compaction with a local audit state file
- disclosing whether the audit will create a normal ChatGPT history record before submission
- avoiding repeated upload retries and using targeted follow-up prompts for later rounds
- using the Chrome plugin workflow safely
- avoiding secret/privat
Related Skills
Uabc
Universal AI Browser Controller — let any AI agent (Claude Code, Codex, ChatGPT, Claude) safely use your own C
Moatkit
Security toolkit for LLM apps and AI agents: blocks prompt injection, stops API keys and personal data leaking
Audit Cloudflare DNS
Audit every Cloudflare DNS zone the project owns through the signed-in Chrome browser — records missing, stale
Gtd Audit
A Claude skill that audits task lists against GTD (Getting Things Done) principles — Capture, Clarify, Organiz
Skill Detail
Shared model-rubric detail + plan-doc update pattern for gate-a~e, audit, doc-cleanup. Load on demand (not aut
Tools Comparison Table
A 107-topic deep dive into ChatGPT, Claude & Gemini—covering AI architecture, multimodality, prompting, contex
Related Agents
GPT 5.6 Sol
General-purpose agent that runs on GPT-5.6-Sol (routed through the shunt gateway to the ChatGPT/Codex subscrip
GPT 6 Luna
General-purpose agent that runs on GPT-6-Luna (routed through the shunt gateway to the ChatGPT/Codex subscript
GPT Pro
Surf GPT Pro advisory runner through the external-job provider bridge