ScobleClaw monorepo
d74bb3852a
Final architecture spec for scobleclaw#7, covering: - Actor-Judge separation principle (separate model instances, divergent optimization goals) - Risk classification matrix (4 tiers: no-judge, lightweight-approval, full-judge-review, human-only) - Judge protocol spec (proposal/verdict JSON formats, retry/override logic with clarify cycles, confidence scoring) - Integration via MCP Tool Proxy Middleware (zero agent changes, single enforcement point) - Kubernetes sidecar pattern for kubeclaw operator - Implementation priority: exec/Forgejo (P0) -> web/Discord (P1-P2) - Metrics framework (approval rate, latency, clarify cycles, escalation) - 4-phase rollout plan with shadow mode before enforcement Closes scobleclaw#7 |
||
|---|---|---|
| docs | ||
| coach-pattern-analysis.md | ||
| README.md | ||
ScobleClaw
Agentic engineering framework by Scott Scoble — tools, workflows, and skills for building with AI agents.
What Is ScobleClaw?
ScobleClaw is a monorepo for agentic engineering patterns used across Scott Scoble's open-source projects. It provides:
- Subagent dispatch patterns for structured AI agent workflows
- Skill-based development with reusable, composable AI context modules
- Provenance tracking for auditable agent outputs and decisions
- Cross-repo tooling shared across Speckl, brand-site, beyond-the-prompt, and more
Projects
| Project | Description | Author |
|---|---|---|
| Speckl | Spec language compiler with embedded provenance | Scott Scoble |
| Brand Site | Professional speaker website | Scott Scoble |
| Beyond the Prompt | Workshop: Lessons from building with Claude Code | Scott Scoble |
Author
Created and maintained by Scott Scoble — builder, speaker, and AI agentics engineer.
- Website: scott.scoble.me
- LinkedIn: scottscoble
- GitHub: sscoble
License
MIT © Scott Scoble / Greybeard Holdings, LLC