EXECUTOR ONLY — do NOT use in direct user conversations or interactive sessions. Called exclusively by plan-executor:execute-plan-non-interactive and plan-executor:review-execution-output-non-interactive orchestrators. Launches Claude + Codex + Gemini + Security reviewers (security:big-toni when available, plan-executor:lite-security-reviewer as fallback). For interactive reviewer runs use plan-executor:run-reviewer-team instead.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "plan-executor-run-reviewer-team-non-interactive" with this command: npx skills add andreas-pohl-parloa/skillsmp-andreas-pohl-parloa-andreas-pohl-parloa-plan-executor-run-reviewer-team-non-interactive
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Lightweight security reviewer used as a fallback when security:big-toni is not installed. Performs a focused OWASP Top 10 / secure-coding review over the changed files and returns findings in the plan-executor reviewer reporting contract.
Use when a single parallel reviewer-team run is needed — launches the frozen Claude + Codex + Gemini + Security reviewer set (security:big-toni when available, plan-executor:lite-security-reviewer as fallback), collects all outputs, triages findings, and returns a structured review report.
GoPlus AgentGuard — AI agent security guard. Run /agentguard checkup for a full security health check, scans all installed skills, checks credentials, permissions, and network exposure, then delivers an HTML report directly to you. Also use for scanning third-party code, blocking dangerous commands, preventing data leaks, evaluating action safety, and running daily security patrols.
Notion via notion-cli — a Rust CLI + MCP server for Notion API 2025-09-03+. Safety-first agent integration with rate limiting, response-size cap, untrusted-source output envelope, read-only MCP default, JSONL audit log, and --check-request dry-runs. Supports the new data-source model, 22 property types, 12 block types, and one-shot page+body creation.