Skip to content

Instantly share code, notes, and snippets.

View stevesolun's full-sized avatar

Steve Solun stevesolun

View GitHub Profile
@stevesolun
stevesolun / README.md
Last active July 9, 2026 05:59
Unknowns-First Coding Codex skill

Unknowns-First Coding Skill

unknowns-first-coding is a Codex skill for risky coding tasks where a wrong assumption would be expensive.

The main idea: before implementing, Codex should separate what is known from what is guessed. It should inspect the repo first, surface important unknowns, ask only questions that materially change the implementation, and proceed on low-risk reversible choices with assumptions clearly logged.

This is not a planning ceremony for every edit. Tiny deterministic changes should stay lightweight: inspect, edit, validate, summarize. The full workflow is for ambiguity with real reversal cost: architecture, public APIs, schemas, migrations, production data, security/privacy/auth/payments/compliance, large refactors, or risky UX semantics.

What It Teaches Codex

@stevesolun
stevesolun / README.md
Last active July 2, 2026 13:29
Goal Contract Loop: Codex skill for verified autonomous coding goals

Goal Contract Loop

Codex skill for turning loose coding intent into a verified work loop:

intent -> contract -> SPEC/Plan/tracker/prompt -> execution evidence

It captures the outcome, evidence, edit boundaries, tools, iteration policy, budgets, pause conditions, and task acceptance criteria before the agent starts work.

Install