Forge with Rigor: specs are canonical, gate every stage, nothing certifies its own work — 53 findings at 13% token cost
colinmcnamara · x · 2026-10-06
Jake Cukjati's 'Forge with Rigor' methodology for coding agents: specs are canonical, every stage is gated, nothing certifies its own work, and skills should get CLIs. Replace prompt→code with spec→plan→implement.
Key points:
- Tests need a harness, and the harness is the asset; failing tests must cite spec clauses.
- Review the whole diff against spec clauses covering intent, code quality, and architecture.
- Real numbers: 53 findings, 56 fixes, 13% of tokens; docs only count if two live sites use them.
- Forge CTL is moving to dynamic workflows on the Agent SDK.
A copyable assembly-line design for multi-agent digital labor.
More from coding & agent
- What a Jumping Spider With 600,000 Neurons Teaches Us About AI Agent Orchestration — uxmag · 2026-10-06
- AI Estimates 5-8 Weeks of Engineering; Developer Has Sub-Agents Finish It in Two Days — Dan_Jeffries1 · 2026-10-06
- AI formal verification hits reality: the halting problem blocks existing codebases — danbri · 2026-10-06
- Developer Builds SEO/AEO Feedback Loop with Grok Bot and Claude Code — doooyle · 2026-10-06
- Next experiment: running most daily todos entirely through voice-driven Grok Bot — FinanceYF5 · 2026-10-06
- Voice-controlled Grok Bot handles Notion, Slack, email and even payments — FinanceYF5 · 2026-10-06