← ClaudeAtlas

decision-rightslisted

Framing discipline for artifacts instructing a downstream reader — handoffs, plans, ADRs, subagent prompts. Separates evidence access from decision rights; marks which decisions evidence can reopen.
MrBinnacle/skills · ★ 0 · AI & Automation · score 62
Install: claude install-skill MrBinnacle/skills
# Downstream-Instruction Framing Discipline ## Problem LLMs default to authoritative downstream instructions: "Approved Decisions — Do Not Re-Litigate," "Execute the following steps," "These are final." This is usually wrong. The downstream reader often has evidence the author lacks: target-repo access, tests, and local rules. Command framing can make them silently follow a plan the code contradicts. Test that asymmetry **per decision**: who can access the evidence that bears on it? Downstream often knows the target code and tests better; upstream may know legal rules, security policy, product intent, or external facts unavailable in the worktree. Evidence and decision authority are separate. Better evidence licenses a revisit request, not the right to change scope, values decisions, or explicit user constraints. ## Context / Trigger Conditions Apply when writing handoffs, plans, dispatch prompts, workflow briefs, future-work ADRs, or instructions to a fresh session. Symptoms: blanket "Do Not Re-Litigate" / "These are final" headers; evidence-sensitive decisions without "Revisit if:"; no per-decision evidence test; or proposed work written as commands. ## Solution ### 1. Default framing: informed proposals from a less-informed reviewer Open with a framing block adapted to the actual evidence asymmetry. Template: ``` ## How to Treat This Document You are not being given orders. You are being given the prior session's best research output, written by a session that