Skill of Skills
🔌 pluginActiveCuratedmedium

context-mode

by mksglu

Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.

Stars

17.1k

Skill Type

📖 Library & API Reference

Quality Score

130/200

License

NOASSERTION

Forks

1.2k

Last Updated

Jun 11, 2026

Discovered

Mar 26, 2026

Validation

Passed

github.com/mksglu/context-mode

Quality Breakdown

130/ 200

Content Signals

â—‹Gotchas/Edge Cases+40
✓Progressive Disclosure+30
â—‹Trigger Description+20
✓Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
â—‹Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains persistent configuration modification files (.claude/, .claude-plugin/, .openclaw-plugin/) that could alter AI tool behavior
  • Multiple hook files (hooks/auto-injection.mjs, hooks/*/sessionstart.mjs, hooks/*/stop.mjs) suggest injection and lifecycle manipulation capabilities
  • MCP (Model Context Protocol) integration with tool access virtualization layer indicates potential for tool capability escalation
  • Configuration files for multiple AI platforms (Claude, Cursor, Gemini, JetBrains, VSCode) suggest broad tool integration and context injection
  • Auto-injection mechanism (hooks/auto-injection.mjs) indicates automated modification of AI tool behavior without explicit per-request approval
  • Bundle and CI/CD workflows suggest runtime code generation and dynamic plugin loading