Security guardrails for Claude Code. Blocks dangerous bash commands and sensitive file access. Enable/disable via plugin settings.
Plugin ajbm-security from marketplace ajbm in ajbmachon/ajbm-skills. Commands read from the repo's manifest — 1 month 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.
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/smart-guard.py"
Skills and agents for software development, analytical thinking, and meta-skill authoring. Tuned for Opus 4.7. Includes 5-mode thinking, Verbalized Sampling creativity, PAI skill transfer methodology, and the full dev toolkit (debugging, TDD, linting, prompt-craft).
15 skills · 2 agents
Skills for business and marketing: offer creation (Hormozi methodology), pricing, copywriting, and Twitter/X content.
2 skills
Structured AI-to-AI alignment protocol for multi-agent delegation. Three graduated levels (Inline, Quick, Full) with constraint inheritance chains.
1 skill
Skills for negotiation, persuasion, and human communication. Includes tactical-empathy (Chris Voss methodology with situation analysis and roleplay sparring).
1 skill
Structured elicitation and spec crystallization through rigorous challenge, assumption surfacing, and constraint enforcement. Workflows: DevSpec, BusinessIdea, DocumentDraft, DesignReview, Ideation, DevilsAdvocate, QuickClarify.
1 skill
Skills for social media: Twitter/X bookmark management, search, timeline reading, posting, and content workflows.
1 skill
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
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, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Cross-installation agent federation with zero-trust security, PII-gated data flow, and compliance-grade audit trails
3 skills · 1 command · 1 agent
Install the "AAS Secure App Builder" editorial skill bundle for Claude Code.
12 skills
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture
24 skills · 2 agents
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
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.