Sensei
Sensei transforms engineering standards documentation into an active development mentor by intelligently injecting relevant portions of a comprehensive 57-section rulebook based on file types, operations, and context. Built with FastMCP, it analyzes code patterns across 50+ file types to determine which engineering principles are most relevant, maintains session memory of architectural decisions and constraints, and provides validation tools against established standards. The implementation coordinates 64 specialized AI personas across 12 categories, offers tools for recording and validating agreed-upon patterns, and supports session collaboration through Architecture Decision Records (ADRs), making it valuable for maintaining code quality standards, ensuring architectural consistency across teams, and providing contextual engineering guidance during development.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- file-system
- Source
- PulseMCP
- Repository
- github.com/amarodeabreu/sensei-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Sensei from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.