SPECTRE is an agentic Coding Workflow - /Scope, /Plan, /Execute, /Clean, /Test, /Rebase, /Evaluate - that uses simply step by step product development workflow to generate high quality results from your AI Coding Agents. - Codename-Inc/spectre
Hey everyone! I’ve been iterating on the SPECTRE workflow almost daily for the last year with the goal of getting repeatable and consistent high quality results from Claude Code.
SPECTRE has made it possible to do more, faster, and with higher quality and I really don’t see an end to this workflow continuing to improve and find/eliminate each bottleneck in agentic coding process.
🎯 Core SPECTRE Principles
* Great Inputs → Great Outputs
* Ambiguity is Death
* One Workflow, Every Feature, Any Size, Any Codebase
* Obvious > Clever
We use SPECTRE at our startup Codename to build Subspace (open beta) and New June (closed alpha). Neither of those products would exist without it.
I hope this works as well for you all as it does for us.
Congrats on the launch @joenandez! The systematic workflow approach is smart for AI coding consistency. How are you planning to onboard developers to adopt this process?
hey @joenandez congrats on launch , is it a fork of claude code, that you have enhanced?
Agentic coding has completely changed how I ship. Built a 118k-line SwiftUI Mac app solo using Claude Code — the key insight was that it's not just autocomplete, it's having something that actually understands the full codebase. What's your approach to context management across longer sessions? That's where I've found the biggest gains.
Hey Joe, that principle of ambiguity is death says a lot. Was there a specific feature or task where Claude Code went completely off the rails because the input wasn’t clear enough?
