Sieve — Security skill for Claude Code
A fully local LLM-traffic security proxy for crypto-native developers — redacts secrets outbound, blocks dangerous tool calls inbound (fail-closed).
How to install Sieve
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open SieveAI-dev/sieve and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Sieve does
A fully local LLM-traffic security proxy for crypto-native developers — redacts secrets outbound, blocks dangerous tool calls inbound (fail-closed).
Alternatives in Security
- Mcp-scan (Invariant Labs) — MCP security scanner with proxy mode for real-time scanning without infrastructure changes 1.9k ★
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
- Agentseal — Security toolkit for AI agents 344 ★
README
Sieve
English | [中文](./README.zh-CN.md)
[](./LICENSE) [](#installation-phase-1-macos-only) [](#project-status)
**A fully local LLM-traffic security proxy — the last gate before irreversible actions.**
Sieve is a fully local LLM-traffic security proxy (a single Rust binary) that sits between your AI coding agent (Claude Code / OpenClaw / Hermes / Codex CLI) and the upstream model API (Anthropic / OpenAI / relays). It inspects traffic in both directions — redacting secrets on the way out, and blocking dangerous tool calls on the way in (fail-closed) — to force a moment of cognitive friction before irreversible actions (signing, transfers, deploys). Built for crypto-native developers.
All detection reasoning runs 100% on your machine. Sieve never uploads your prompts, responses, or API keys.
How it works
Your agent points its base URL at a loopback listener (`127.0.0.1`). Sieve forwards traffic to the real upstream over end-to-end TLS — it does **not** install a local CA or MITM your connection. On the way out it matches outbound rules and redacts secrets in place; on the way in it intercepts Critical tool calls and holds them for human confirmation (HIPS — Host Intrusion Prevention System).
flowchart LR
A["AI agent
Claude Code / OpenClaw / Hermes / Codex CLI"]
S["Sieve
(local · 127.0.0.1)"]
U["Upstream
Anthropic / OpenAI / relay"]
A -- "request" --> S
S -- "outbound: redact secrets
(auto, no popup)" --> U
U -- "response" --> S
S -- "inbound: block Critical tool calls
fail-closed + HIPS confirmation" --> A
S -.-> D["100% local detection
no cloud verifier"]
The only outbound traffic Sieve itself makes is to fetch signed rule updates — see [Privacy
Related Skills
Reviewgate
Fail-closed independent review loop for Claude Code and Codex. Native hooks, six reviewer paths (Codex, Gemini
Agent Advisor
Hub for selective AI-agent routing across Codex, Claude Code & Antigravity: auditable solo/delegate/audit/full
Game Localization
Engine-agnostic game localization pipeline for AI agents: detect engine -> extract text -> translate with cont
Audit Risk
Find new risk surfaces (dependencies, auth, payments, destructive data ops, outbound calls, secrets) since the
LaptopAI Agent
Fully local, privacy-first autonomous AI agent for laptop management — LangGraph reasoning loop, Ollama local
KeyValet
Give your AI agents a valet key, not your master key. Local credential broker for AI agents (MCP) on macOS: To
Related Agents
Security Officer
OWASP + STRIDE pass over a change or surface. Fails closed — unresolved risk blocks ship. Spawn for anything t
Sf Integration Engineer
Implements outbound and inbound Salesforce integration metadata and integration Apex - Named and External Cred
Project Automation Auditor
Audits a project's automation and verification posture: test runner, formatter/linter PostToolUse hooks, PreTo