Redstamp — Security skill for Claude Code
own your agent security — a deterministic, offline firewall for AI agent tool calls.
How to install Redstamp
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open askalf/redstamp and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Redstamp does
own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prompt injection and destructive commands before they run; same call, same verdict, no model in the decision path. 100% recall / 100% precision on a 298-sample corpus, scored in CI against live rivals. Claude Code hook or MCP proxy.
Alternatives in Security
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
- Unifly Audit — Security audit of UniFi configuration 248 ★
- Preloop — The open-source AI agent control plane: MCP firewall, model gateway with budgets, human approvals, runtime obs 54 ★
README
redstamp
**A deterministic, offline firewall for AI agent tool calls.**
Same call → same verdict, every time. No model in the decision path. Zero runtime dependencies.
[](https://github.com/askalf/redstamp/releases/latest) [](https://github.com/askalf/redstamp/actions/workflows/ci.yml) [](https://github.com/askalf/redstamp/actions/workflows/codeql.yml) [](https://scorecard.dev/viewer/?uri=github.com/askalf/redstamp) [](LICENSE) [](package.json) [](https://github.com/askalf/redstamp/releases/latest) [](SECURITY.md)
[Quick start](#quick-start) · [Scoreboard](#the-scoreboard) · [How it decides](#how-it-decides) · [Surfaces](#every-surface-an-agent-uses) · [Integrating](INTEGRATING.md) · [Threat model](SECURITY.md)
import { check, AuditLog } from '@askalf/redstamRelated Skills
Agent Overwatch
A deterministic guard for AI coding agents — checks each tool call before it runs (allow/ask/deny) and blocks
Arbitus
Open-source security gateway for MCP tool calls — blocks secret leaks, enforces agent policies, and requires h
Agent Security Stack
The open-source agent-security stack — redstamp + truecopy + strongroom — composed into one layered defense. V
Audit Risk
Find new risk surfaces (dependencies, auth, payments, destructive data ops, outbound calls, secrets) since the
Skilldoctor
A linter + security scanner for AI-agent skill files — validate Claude Code SKILL.md / AGENTS.md / subagent fr
Sieve
A fully local LLM-traffic security proxy for crypto-native developers — redacts secrets outbound, blocks dange
Related Agents
LLM Sec Review
LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode
Security Audit Agent
자바 코드 보안 취약점 검증 전문. Refactor 작업 직후 또는 git commit 직전 호출. OWASP Top 10 + Secret Scan (trufflehog/ggshield) + Pro
Worker High
pstack's general-purpose subagent at high effort. pstack skills spawn it wherever a step calls for an agent-mo
