claude

guardrails

Enforces safe agent behavior by blocking or limiting tool usage patterns that degrade session quality.

1 on GitHubby PoYen Chenv0.1.0updated 16 days ago
/

Plugin guardrails from marketplace agent-plugins in poyenc/agent-plugins. Commands read from the repo's manifest — 15 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Hooks (20)

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-sleep.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-timeout-ssh.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-srun.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/herdr-prompt-guard.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-herdr-wait.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-blind-find.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-blind-search.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-docker-on-login-node.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-tail-follow.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-long-foreground.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/bg-timeout-cap.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/cron-guard.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-memory-access.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-memory-access.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-memory-access.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/read-guard.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/no-named-agent.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/cron-track-create.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/cron-track-delete.sh"

  • SessionEnd

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/cron-session-end.sh"

View source on GitHub

More from poyenc/agent-plugins

All 5 plugins →

recall

claude

Automatic branch-aware recall system with layered overlays, conditional topic loading, and merge promotion.

14 skills · hooks

1

herdr-kit

claude

Herdr agent tools: checkpoint-and-relaunch a running claude/pi/codex agent in place (including self-rotation via a detached daemon), plus non-blocking async inter-agent messaging.

3 skills · 1 command · hooks

1

ntfy

claude

ntfy.sh push notifications when the agent asks a question. Off by default; toggle per-session with /ntfy-on and /ntfy-off.

3 skills · hooks

1

mnemosyne

claude

Mnemosyne working memory — injects bank/branch context and tool-use conventions at session start, consolidates memories at session end.

1 skill · hooks

1

Similar plugins

Security default for organizations: seated outermost, it keeps the organization's classic hooks, prompt content, settings, tool policy and pinned environment out of reach of the plugins a person installs, and adds no policy of its own; one managed option, allowManagedModsOnly, limits mods to the organization's.

anthropics/claude-code 155,476

Cache-aware /loop workers and CronCreate background automation

2 skills · 2 commands · 1 agent

ruvnet/ruflo 81,589

Convex

claude

Official Convex plugin for Claude Code with bundled Convex skills, the convex-expert subagent for code-writing, a runtime-error monitor, and MCP access for backend development, schema design, real-time features, auth, file storage, scheduled jobs, and AI agents.

16 skills · 1 command · 2 agents · 1 MCP server · hooks

anthropics/claude-plugins-official 47,076

API security hardening, authentication implementation, authorization patterns, rate limiting, and input validation

2 agents

wshobson/agents 42,461

Portfolio monitoring and analytics for private-capital LP teams using the Chronograph connector: cashflow forecasting, commitment pacing, look-through exposure scans and GP-meeting prep. Requires a Chronograph account and the Chronograph connector.

4 skills · 5 agents

anthropics/knowledge-work-plugins 35,601

Build, launch, grade, and schedule Claude Managed Agents (CMA) in your own Anthropic account — a plugin re-implementation of Anthropic's launch-your-agent reference skill (Apache-2.0; independent, not a fork). Every session starts with a goal (./my-agent/goal.json, opt-in SessionStart hook, driven by /cs-goal); loop_compiler.py compiles it into a bounded grade->iterate loop (max_iterations 1..20), a recurring cron scheduled-deployment loop, or a single-pass interview->stage->launch workflow. 6 skills: orchestrator (context: fork goal router) + interview + stage-launch + grade-iterate + run-without-you + wrap-up. 18 stdlib-only deterministic scaffolders (no network/API calls; live launches emitted as BYOK curl that never prints the key), 4 agents, 8 commands, hooks, 5 references, 4 assets. Validators enforce CMA limits. Distinct from engineering/agent-harness (generic domain loop) and write-a-skill (authors Claude Code skills, not CMAs).

6 skills · 8 commands · 4 agents · hooks

alirezarezvani/claude-skills 29,725

Maintain guardrails?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins5 plugins