Search
@digicroz/jwt
adarshhatkar
Production-grade JWT utilities with complete type safety, timing-safe verification, and error handling without throwing. Fully typed, tested, and optimized for modern TypeScript projects.
...morediff-sequences
simenb
Compare items in two sequences to find a longest common subsequence
3tears-agent-skills
pace
Procedural memory for LLM agents -- skill definitions + invocation history
agent-gate-sec
AgentGate Team
AgentGate - AI Agent 数据采集与安全分析中间层服务
django-adminrestrict-CDSP
Alexandre Chevallier (fork) Robert Romano (original author)
Django admin restriction
acrqa
AI-powered code review with RAG-grounded explanations, 10 static analysers, and ECDSA-signed provenance
Vps Setup Skill
AndyShaman
Beginner-safe Linux VPS hardening skill for Claude Code. SSH lockdown deferred until key login is verified — first-time lockout structurally impossible. macOS/Linux/Windows laptops, Debian/Ubuntu servers.
...moreaegis-langchain
Aegis ACP
LangChain governance middleware for Aegis ACP
io.github.JoeyBrar/agentseal
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.
@thi.ng/imago
thi.ng
JSON & API-based declarative and extensible image processing trees/pipelines
@blackunicorn/bonklm-mcp
schenlong
MCP SDK connector for BonkLM
@alcideio/iskan-viewer
alcidebuilder
<img src="https://github.com/alcideio/iskan/raw/master/iskan.png" alt="skan" width="160"/>
@rimenko-dev/aiguard
rimenko-dev
Protect your projects from AI-tool secret leaks — catches .claude/, .cursor/, and hidden credentials before npm publish or git push
...moreskillscan
dejimarquis
Trust verification layer for AI agent skill marketplaces - scan, score, and verify skills before installation
rate-limiter-flexible
animir
Node.js atomic and non-atomic counters, rate limiting tools, protection from DoS and brute-force attacks at scale
clayseal
MCP gateway and Python guardrail that authorizes agent tool calls against a session policy. Stops prompt injection and aggregate attacks that per-call checks miss.
...more@jieai/dsh-plugin-vet
jieai
Plugin trust pipeline for deepseek-harness (DSH): deterministic static scan, runtime guard (T1 sentinel + T2 hooks), audit protocol skill, GUI shield. Alarms by default; N7 confirm-block intercepts confirmed destructive fs ops (family 1/2) by throwing.
...more@resq-sw/http
resq-eng
Effect-based HTTP client with retry, timeout, and schema validation
yui-agent-guard
yui-stingray
Static repository guardrails for agent-touched codebases.
contextforge-apiconnect-fedapimgmt
IBM API Connect Federated API Management Plugin for ContextForge - automated MCP server and tool synchronization with centralized governance
...more