probity
01Plugin Claude Code
Plugin marketplace listing 1 plugin: probity.
38 tagged guardrails, measured the same way as everything else here.
Browse within: hooks 8AI Safety 7
Plugin Claude Code
Plugin marketplace listing 1 plugin: probity.
Plugin Claude Code
TDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.
Plugin Claude Code
Plugin marketplace listing 1 plugin: makoto.
Plugin Claude Code
Holds Claude Code to its word — every claim checked against the agent's own logged record; faked checks blocked, not warned (four narrow advisory self-checks excepted). Two-tier catalog (15 pre-checks, 19 Stop gates), each shipped at measured zero false positives.
Plugin Claude Code
AI Harness + Ouroboros: Specification-first development with structural guardrails.
Plugin Claude Code
Specification-first AI harness: 11 structural gates, 11 Ouroboros commands, 11 agent personas, and 3-tier architecture enforcement. v2.1: Pair Mode (Navigator-Driver + independent test design + /review command).
Plugin Claude Code
A secure runtime for Claude Code. Intercepts every tool call with policy-based allow/block/ask decisions, evasion detection, path fencing, file snapshots, and audit logging.
Plugin Claude Code
Plugin marketplace listing 1 plugin: sentinel-ai.
Plugin Claude Code
Real-time safety scanning for LLM interactions. Detects prompt injection, PII leaks, harmful content, toxicity, obfuscation, secrets, and dangerous tool calls — 600-case benchmark at 100% accuracy with sub-millisecond latency.
Plugin Claude Code
Plugin marketplace listing 1 plugin: sparda-gate.
Plugin Claude Code
The behavior gate for AI edits — proves each edit lost no auth guard, dropped no route, and grew no blast radius. Deterministic, <2s, offline, zero API key.
Plugin Claude Code
Vibe coding is how you start; engineering is what keeps it alive. Auto-activating Claude Code plugin that silently installs production engineering guardrails — architecture awareness, TDD, quality gates, security-first development, and 25+ skills so vibe coders build real systems without thinking about process.
Plugin Claude Code
Production engineering guardrails for vibe coders — architecture awareness, TDD, quality gates, security, and 25+ skills that turn prototypes into production systems. Auto-activates on session start.
Plugin Claude Code
Caushell integrations for pre-execution semantic analysis of Harness shell actions.
Plugin Claude Code
Session-aware shell guardrails for Claude Code backed by the Caushell runtime.
Plugin Claude Code
codoop-flow: in-session orchestration for an AI-coding ticket pipeline (build/verify/review/ship) with a deterministic guardrail CLI.
Plugin Claude Code
In-session orchestration for the codoop-flow Agent-Centric ticket pipeline: pick -> build -> verify -> review -> ship, driven by a skill plus a deterministic guardrail CLI.
Plugin Claude Code
A one-file door-guard for coding agents. Name's not on the list.
Plugin Claude Code
A one-file PreToolUse door-guard that bounces destructive Bash commands (rm -rf, DROP TABLE, curl|sh, force-push, device wipes) before they run. Blocks 45/45 known footguns, 0 false positives.
Plugin Claude Code
Production safety guardrails for Claude Code.
Plugin Claude Code
Production safety guardrails that block write/mutating operations on cloud, database, IaC, and deployment CLIs.
Plugin Claude Code
Plugin marketplace listing 1 plugin: agentlint.
Plugin Claude Code
Claude Code marketplace wrapper for AgentLint's AI-agent guardrail engine. 77 rules across 8 packs, hybrid AgentChute security feeds, circuit-breaker visibility, inline-ignore reasons.
Plugin Claude Code
Risk guardrails for AI trading agents: a pre-trade risk check and the Agent Skill that gates execution on it.