pm-seatbelt
Agent safety seatbelts: the pre-flight security checklists you run before an agent touches email, the browser, files, or goes autonomous — least-privilege reviews…
Plugin-Paket · von Mohit Aggarwal
Überblick
pm-seatbelt ist ein Plugin-Paket für KI-Coding-Tools von Mohit Aggarwal. Marktplätze, die wir lesen und die es listen: 1 (Community GitHub marketplaces). Die letzte erfasste Änderung war am 2026-11-07. Stand unseres Marktplatz-Durchlaufs vom 2026-11-07.
Agent safety seatbelts: the pre-flight security checklists you run before an agent touches email, the browser, files, or goes autonomous — least-privilege reviews, prompt-injection spotting, and the blast-radius drill
Was es abfragt
- Wird als Plugin-Paket installiert
Keiner der Marktplätze, die wir lesen, veröffentlicht seine Tools oder die abgefragten Einstellungen.
Was es deklariert, abfragt und ausführt, vollständig
Installieren Sie nur Plugins von Entwicklern, denen Sie vertrauen. Wir zeigen, was die Marktplätze veröffentlichen, und testen keine Plugins.
Funktioniert mit
- Claude Code
Nach den Marktplätzen, die ihn listen, und dem angegebenen MCP-Transport, wie jeder Client sie dokumentiert. Wir testen keine Plugins.
Verbinden
Befehle und Konfigurationen nur aus den Angaben der Marktplätze. Wir führen sie nicht für Sie aus und testen keine Plugins.
Als Claude-Code-Plugin
Erstellt aus den Angaben von Community GitHub marketplaces.
/plugin marketplace add mohitagw15856/pm-claude-skills
/plugin install pm-seatbelt@pm-claude-skillsWo es veröffentlicht ist
| Marktplatz | Status | Version | Zahlen | Verifiziert | Erstmals gesehen |
|---|---|---|---|---|---|
| Community-Marktplatz mohitagw15856/pm-claude-skills (Quelle auf GitHub öffnen) | Gelistet | 1.0.0 | Forks (GitHub): 269 Sterne (GitHub): 1 528 |
Nicht markiert |
Jede Zahl stammt vom jeweiligen Marktplatz und wird nie über Marktplätze hinweg addiert. Ein Marktplatz ohne veröffentlichte Zahl zeigt keine: keine Zahl ist nicht null.
In einem Community-Marktplatz gelistet
| Marktplatz | Repository | Sterne (GitHub) |
|---|---|---|
| pm-claude-skills | mohitagw15856/pm-claude-skills | 1 528 |
Wie sich die Zahlen entwickelt haben
- 2026-10-16258
- 2026-10-17259
- 2026-10-18260
- 2026-10-19259
- 2026-10-22258
- 2026-10-23260
- 2026-10-28263
- 2026-10-31264
- 2026-11-03266
- 2026-11-04267
- 2026-11-05268
- 2026-11-07269
- 2026-10-161,5 Tsd.
- 2026-10-171,5 Tsd.
- 2026-10-181,5 Tsd.
- 2026-10-191,5 Tsd.
- 2026-10-201,5 Tsd.
- 2026-10-221,5 Tsd.
- 2026-10-231,5 Tsd.
- 2026-10-281,5 Tsd.
- 2026-10-291,5 Tsd.
- 2026-10-311,5 Tsd.
- 2026-11-011,5 Tsd.
- 2026-11-031,5 Tsd.
- 2026-11-041,5 Tsd.
- 2026-11-051,5 Tsd.
- 2026-11-071,5 Tsd.
Jeder Punkt ist ein Tag, an dem wir eine andere Zahl gelesen haben; flache Abschnitte sind Tage ohne Veränderung. Zahlen verschiedener Marktplätze werden nie addiert.
Was das Paket enthält
So veröffentlicht auf Community GitHub marketplaces.
Skills: 6
blast-radius-drillbrowser-agent-preflightemail-agent-preflightfile-access-preflightinjection-spottertool-permission-review
Was sich geändert hat
- Auf einem neuen Marktplatz erschienen: Community GitHub marketplaces
- Community GitHub marketplaces: wieder gelistet
- Nicht mehr auf Community GitHub marketplaces gelistet
- Community GitHub marketplaces: entfernt
- Wird seitdem als Produkt geführt
- Community GitHub marketplaces: erschienen
Ähnliche Plugins
Produkte, deren eigene Namen, Beschreibungen, Werkzeuge und Skills diesem der Bedeutung nach am nächsten sind, auf allen Marktplätzen, die wir lesen. Die Nähe ist nur innerhalb dieser Liste geordnet.
-
Reco SaaS & AI security — query app risks, shadow IT, AI agents, user posture, and access events directly from Claude Code
-
agentic-bundle-aas-privacy-compliance-engineering
Install the "AAS Privacy & Compliance Engineering" editorial skill bundle for Claude Code.
-
Core safety skills for AI-assisted development: Four Laws, Three Strikes, production-first, scope validation, and environment separation. 11 skills enforce guardrails on every…
-
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
-
Agent Tooling — Building the skills, hooks, commands, and plugins that agents run on.
-
Zero-trust military-grade AI co-founder OS with progressive FULL/PARTIAL/BASIC security, Fortress Bible audit trail, and native hooks
-
AI agent security guard. Blocks dangerous commands, prevents data leaks, protects secrets.
-
capability-admission-check-adrian-lerer
Screens AI Skills, MCP servers, plugins, and agent tools before installation or activation using provenance, static inspection, least privilege, version pinning, and…
-
Use Claude Code without fear of data leakage. Unbound enforces command policies, DLP and jailbreak guardrails, and streams session analytics to your security dashboard — all with…
Ähnliche Plugins nach Marktplatz
Dieselbe Frage an jeden Marktplatz einzeln: Gibt es dort ein Gegenstück zu diesem Plugin?
Gelistet auf Claude Code: claude-plugins-community (5)
-
Reco SaaS & AI security — query app risks, shadow IT, AI agents, user posture, and access events directly from Claude Code
-
Core safety skills for AI-assisted development: Four Laws, Three Strikes, production-first, scope validation, and environment separation. 11 skills enforce guardrails on every…
-
Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks…
-
Zero-trust military-grade AI co-founder OS with progressive FULL/PARTIAL/BASIC security, Fortress Bible audit trail, and native hooks
-
Use Claude Code without fear of data leakage. Unbound enforces command policies, DLP and jailbreak guardrails, and streams session analytics to your security dashboard — all with…
Gelistet auf Claude Code: claude-plugins-official (5)
-
Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or from explicit instructions. Define rules via simple markdown files.
-
Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
Gelistet auf Claude: knowledge-work-plugins (5)
-
The Vanta plugin connects Claude Code to Vanta's security and compliance platform through the Vanta MCP server. It combines Vanta's test-specific remediation intelligence with…
-
Triage tickets, draft responses, escalate issues, and build your knowledge base. Research customer context and turn resolved issues into self-service content.
-
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF…
-
Connects Claude Code to the Synthflow AI voice-agent platform through its hosted MCP server, with skills for reviewing calls and auditing agent prompts, plus a docs-search…
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
Gelistet auf Codex: openai-curated (openai/plugins) (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Codex Security workflows for security scans, analysis, and investigation.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
Gelistet auf Community GitHub marketplaces (5)
-
agentic-bundle-aas-privacy-compliance-engineering
Install the "AAS Privacy & Compliance Engineering" editorial skill bundle for Claude Code.
-
Agent Tooling — Building the skills, hooks, commands, and plugins that agents run on.
-
AI agent security guard. Blocks dangerous commands, prevents data leaks, protects secrets.
-
capability-admission-check-adrian-lerer
Screens AI Skills, MCP servers, plugins, and agent tools before installation or activation using provenance, static inspection, least privilege, version pinning, and…
-
Autonomous security agent that remediates Orca alerts with validation, impact analysis, and notifications
Gelistet auf Copilot CLI: github/awesome-copilot (5)
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Comprehensive collection for building declarative agents with Model Context Protocol integration for Microsoft 365 Copilot
-
crowdstrike-charlotte-ai-agentworks
CrowdStrike Charlotte AI AgentWorks skills for creating, managing, and invoking AI agents via external Falcon API Gateway endpoints. Includes agent lifecycle management…
-
CrowdStrike Falcon Fusion skills for authoring, deploying, and executing Fusion workflows. Includes live action discovery, YAML authoring with schema validation, workflow import…
-
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
Gelistet auf Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
workiq
Query Microsoft 365 data with natural language — emails, meetings, documents, Teams messages, and more.
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Advanced Security plugin for GitHub Copilot.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
Gelistet auf Cursor: cursor/plugins (5)
-
Query and remediate compliance tests, controls, frameworks, risks, and vulnerabilities in Vanta.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Scaffold and validate new agent plugins.
-
Search company knowledge and draft verified answers.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
Gelistet auf Docker MCP Catalog (5)
-
Manage Zscaler Zero Trust Exchange via 400+ tools — ZPA, ZIA, ZDX, ZCC, ZTW, ZMS, EASM, and more.
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Connects with the Beagle Security backend using a user token to manage applications, run automated security tests, track vulnerabilities across environments, and gain intelligence…
-
Give your AI agents trusted access to the full Postman platform.
-
A unified MCP proxy that aggregates multiple MCP servers into one interface, enabling seamless tool discovery and management across all your AI interactions. Manage all your MCP…
Gelistet auf Official MCP Registry (5)
-
Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
-
Agent asks a person go/stop/wait before Slack, CRM or risky steps. $49 for 30 days.
-
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
-
QualeQuest — AI Agent Governance Platform
Multi-agent governance: task orchestration, compliance, decision validation, and ML predictions.
-
Every KnowBe4 KMSAT reporting feature plus a local SQLite store that answers the cross-client
Gelistet auf PyPI (MCP servers) (5)
-
rootly com.mcparmory/rootly
Manage incident alerts, events, and workflows with custom automations
-
saferagenticai-mcp io.github.NellInc/saferagenticai-mcp
Read-only tools over the Safer Agentic AI framework: 239 patterns + 15 heuristics.
-
air-blackbox-mcp io.github.airblackbox/air-blackbox-mcp
EU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.
-
mcp-safeguard com.cognivators/mcp-safeguard
MCP server security scanner: detects prompt injection, credential leaks, SSRF, tool poisoning.
-
agent-harnesses io.github.RyanAlberts/agent-harnesses
Agent-harness picks, decision guides, setup templates, and skills; live GitHub/HN discovery.
Gelistet auf npm registry (MCP servers) (5)
-
Ask Vulnify before an AI agent acts. Check, record, and read policy decisions.
-
A firewall for AI agents. Detects and blocks prompt injection in email, web pages, documents and MCP tool results before they reach your model.
-
Context Assurance for AI agents: context engineering, AI cost optimization, verification.
-
agentic-flow (external: maintained in ruvnet/agentic-flow, pinned to commit d19737b, plugin 3.4.0): the agentic-flow MCP server pinned to agentic-flow@3.4.0 (ReasoningBank…
-
shield-kya io.github.The-Pixel-Boys/shield-kya
Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.
Nach Bedeutung gefunden, nicht über gemeinsamen Code oder ein gemeinsames Repository: Ähnliche Plugins bleiben getrennte Produkte, und dies ist weder eine Bewertung noch eine Empfehlung.
Möchten Sie dieses Zeichen für Ihr Plugin in unserem Katalog?
Belegen Sie mit einer Datei im Repository, einer Datei auf Ihrer Domain oder einem DNS-Eintrag, dass Sie es pflegen, und Sie können dieses Zeichen auf der Karte zeigen, dazu Live-Banner für Ihre Website und Ihr README. So funktioniert die Verifizierung
Außerdem erhalten Sie Hinweise, wenn ein Marktplatz es aufnimmt, entfernt, sein Verified-Zeichen oder seine Anforderungen ändert, und sein Remote-Endpunkt wird wie ein Webdienst überwacht.
Daten von Community GitHub marketplaces. Die Zahlen stammen aus unseren eigenen regelmäßigen Durchläufen über die Marktplätze, zuletzt abgerufen am . Kontaktdaten von Plugin-Herausgebern veröffentlichen wir nicht.