agent-reliability plugins

qualixar/superlocalmemory

Plugin Claude Code

Local-first agent memory with auditable hybrid retrieval — the Codex build, with Codex-shaped rules, hooks and launcher.

trustabl/trustabl

Plugin Claude Code

Bundles 2 skills, 1 agent, 1 hook, 1 MCP server · 310 tokens together

Self-audit AI agent, tool, and MCP-server code for security and reliability misconfigurations with Trustabl, the agent reliability scanner for the OpenAI Agents SDK, Claude Agent SDK, Google ADK, and MCP. Ships two skills (trustabl-scan and trustabl-enrich) and a subagent (trustabl) that together form a scan → enrich…

zaxardery8011-design/soplint

Plugin Claude Code

Bundles 1 skill · 53 tokens together

Lint rules for your AI agent's discipline, not its code. Audits belief-revision logs, decision propagation into CLAUDE.md, memory frontmatter, and index health.

IgorGanapolsky/ThumbGate

Plugin Claude Code

Bundles 74 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins · 6,303 tokens together

One 👎 becomes a hard rule the agent cannot bypass. Captures thumbs-down feedback, distills it into PreToolUse Pre-Action Checks, enforced across every future Claude Code session.

trustabl/trustabl-cursor

Plugin Cursor

Bundles 1 MCP server

Bring Trustabl's AI-agent safety & reliability scanner into Cursor — scan your agents, tools, and MCP servers, get a production-readiness score with severity-ranked findings, and fix issues before they ship.

ByteStack-Labs/claude-plugins

Plugin Claude Code

Bundles 4 skills · 933 tokens together

Claude skills for AI agent and ML reliability: reproduce the eval-to-production gap, catch confidently-wrong outputs, and prove root cause with verified numbers. Start with production-autopsy.

fainir/flipback

Plugin Claude Code

Bundles 1 skill, 1 hook · 149 tokens together

Your agent stopped. It was not finished. flipback reads the conversation, works out whether the work you asked for actually got done, and puts the agent back on when it did not.