Jinbe — Security agent for Claude Code
Final Superloopy gate reviewer that integrates implementation, QA, review, and audit evidence into an APPROVE/REJECT.
How to install Jinbe
Installs to ~/.claude/agents/beefiker-superloopy-jinbe.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/beefiker/superloopy/HEAD/agents/jinbe.md -o ~/.claude/agents/beefiker-superloopy-jinbe.md Restart Claude Code, or start a new session, for it to be picked up.
What Jinbe does
name: jinbe description: Final Superloopy gate reviewer that integrates implementation, QA, review, and audit evidence into an APPROVE/REJECT. Use as the last check before the parent finishes the loop. model: opus
You are jinbe, the final evidence integrator for a Superloopy task. Reason at maximal rigor.
Do not edit product files or Superloopy plan state. Read the original brief, current Superloopy guide/check/report output, code-review report, QA report, audit verdicts when present,
Alternatives in Security
- Omd Orchestrator — Coordinates multi-agent design workflows across writing, five-locale adaptation, humanization, UI slop audit 465 ★
- Mathodology Submission Packager — Use for final contest package assembly, file checks, reproducibility README, AI-use statement, and submission 137 ★
- Rails Auditor — Final gatekeeper for code quality, security, and performance 46 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Squad Code Review
Operate as the squad's final implementation-quality gate after behavioral QA — review correctness, security, c
Sf Review Agent
Final Salesforce quality gate — validate Apex, LWC, Flow against architect plan; audit security, governor limi
Verification Auditor
Verification auditor that checks every agent's claims against the actual codebase. Runs twice — once after imp
Coder Check
Validates implementation matches plan requirements. Security gate and compliance checker. Receives SESSION_ID
Zoro
Independent code reviewer for a bounded Superloopy change. Use to review a diff for correctness, tests, securi
Team Finisher
Final cleanup specialist. Removes all console.log statements (including audit diagnostic logs) and enforces co
Related Skills
Agentic AI Human Approve Or Reject Agent
Agentic AI agent with Human-in-the-Loop approval using LangGraph and Claude. The agent pauses for human approv
Figure Bake
Drive one figure from design brief to manuscript-ready PDF + outline PNG. Three-agent loop (@figure-descriptor
Pbi Review
Run the read-only quality gate (pbi-reviewer) on the open project: model rules, DAX hygiene, RLS evidence, PBI