nuclear-grade

Record the version everyone agreed is correct — the baseline — after a review, merge, release, or change to public docs. This is a portable command prompt.

Build a work breakdown for a deliverable — a tree that splits the thing you are building into its parts. The tree must add up to the whole and nothing more (the 100% rule), have no overlap between parts, use outline numbering, and define every part in a short dictionary. Do this so the scope can be checked before any folders or work begin. This is a portable command prompt.

Sort a change into the lightest mode that is still honest. First name the decision the change must settle. Then pick the mode. Then name the proof needed before work goes on. This is a portable command prompt.

Bring an abandoned or half-filled change packet to an honest terminal state: complete it, close it with a recorded rationale, or delete it. This is a portable command prompt that pairs with `ng status` health tags.

Review a diff or a module for slipping standards — oversized files, needless layers of abstraction, feature logic leaking where it should not, and clever indirection — and give one honest verdict. This is a portable command prompt.

Five subagents map onto the **PROVE** beats, each with tool boundaries that *encode* the authority

PROVE Educate stage. Use after the verdict to lock in the approved baseline and turn operation into a lesson — record the baseline, OPEX/lessons, and any charter update into .nuclear/. Do not use to build product code, decide ship/block, or run the change.

PROVE Verdict stage. Use to make the ship / block / defer / ship-with-named-risk decision on the evidence alone — read-only and independent of the runner. Do not use to build, to gather new evidence, or to write code.

PROVE Observe stage. Use to verify and review the runner's output — run tests, gather evidence, read the diff — WITHOUT writing product code, so it cannot fix code to pass its own evidence. Do not use to build, plan, or decide ship/block.

PROVE Plan stage. Use to turn a request into an approved plan — question, discover, specify, plan — writing only to the change packet, never product code. Dispatch first, before any building. Do not use to edit code, run commands, or decide ship/block.

Splits scope into a product-first work breakdown that follows the 100% rule, keeps pieces from overlapping, uses outline numbers, and gives every piece a dictionary entry. Use when an epic, feature, or new subsystem needs a clean split into deliverables, or one source of truth before folders or work begin. Do not use for a one-file edit or a backlog item already broken down.

Prepares focused context for an AI agent, reviewer, verifier, or releaser, with a clear role, goal anchor, authority, evidence to produce, forbidden actions, and stop conditions. Use when handing off or resuming work that matters. Do not use for a tiny self-contained task that needs no handoff.

Reviews public text for license, warranty, compliance, safety, security, certification, and fitness claims that go too far, then rewrites them to stay inside the real limits. Use when shipping or editing public docs, READMEs, or rollout copy. Do not use for internal code comments, or for deciding actual legal fitness, which needs a qualified lawyer.

Records a ship, block, defer, or ship-with-risk decision that ties baseline, evidence status, residual risk, rollback, monitoring, and handoff together. Use when a packet, PR, release, dependency change, or agent-authority change approaches merge. Do not use early in development before evidence exists.

Checks that the way you cite source families, agencies, standards, or borrowed ideas is honest and does not claim too much. Use when public docs, templates, skills, change records, or rollout copy point to outside sources. Do not use for private notes, or for checking whether code actually works.