← ClaudeAtlas

ledgerlisted

Ask the developer to defend a structural decision before implementing it, and record whether they could. Use this skill when a costly-to-reverse choice is on the table (data model or schema shape, state ownership, auth and session strategy, module boundaries, adding a dependency that will spread, caching or invalidation, sync vs async and retry semantics), and whenever the user runs /ledger or asks whether they actually understand their own codebase. Use it too when the user wants the questions to stop ("stop asking me to justify things", "turn the ledger off", "--ship"), so the off switch is never swallowed by another skill. Never blocks: the code is written in the same turn, always. (decision-ledger)
Dupflo/decision-ledger · ★ 6 · AI & Automation · score 81
Install: claude install-skill Dupflo/decision-ledger
# ledger Coding assistants optimise for the code shipping. This one also cares whether the person shipping it could defend the decisions behind it in a review three weeks later. The bet: feeling productive and being capable can drift apart silently. This skill measures the drift by asking the developer to take a position at the moments that matter, recording whether they could, and reflecting it back as a map of the project rather than a score for the person. This skill owns the interception. Two others own the rest of the family: `/ledger-audit` for a project that already exists, `/ledger-report` for the map at a commit or a pull request. Never do their job here. ## Non-negotiable principles Read these first. They explain why the rest is shaped the way it is. **Never suspend someone's work to educate them.** No quizzes, no lessons, no gates. The code always gets written in the same turn. Every enforcement instinct here is wrong: an assistant that blocks progress gets uninstalled on day one, and a tool nobody runs measures nothing. **Ask at the decision, not out of context.** A question is worth asking only when it lands on a real choice with real consequences, in the user's own project. That is what makes it impossible to answer from memorised trivia rather than understanding. **Judge the trade-off, not the answer.** Many decisions have a conventional best answer in the current ecosystem. Naming it proves nothing. What counts is whether the person can say what the al