From nuclear-grade
Sorts a code change into a Nuclear-grade mode (Quick, Standard, or human-reviewed) based on consequence, undo difficulty, and uncertainty. Produces a risk record with required proof and safety habit.
How this command is triggered — by the user, by Claude, or both
Slash command
/nuclear-grade:ng-classifyThe summary Claude sees in its command listing — used to decide when to auto-load this command
# ng-classify Portable command prompt generated from `skills/rating-change-risk/SKILL.md`. Edit the skill, then run `python tools/ng.py gen-commands`; do not edit this file by hand. > Picks Quick, Standard, or a stronger human-reviewed mode based on consequence, how easy it is to undo, and how much is unknown. Use when you start a change to code, docs, dependencies, AI power, releases, or public claims and the right level of care is unclear. Do not use for a tiny easy-to-undo edit with obvious proof, which is Quick by default. ## Use when - A change request is new, vague, or has grown. ...
Portable command prompt generated from skills/rating-change-risk/SKILL.md. Edit the skill, then run python tools/ng.py gen-commands; do not edit this file by hand.
Picks Quick, Standard, or a stronger human-reviewed mode based on consequence, how easy it is to undo, and how much is unknown. Use when you start a change to code, docs, dependencies, AI power, releases, or public claims and the right level of care is unclear. Do not use for a tiny easy-to-undo edit with obvious proof, which is Quick by default.
docs/02-operating-system/activation-thresholds.md.risk.md, if one exists.Sort this change into a Nuclear-grade mode.
Inputs:
- Request or diff: <paste/link>
- Affected files/assets: <list>
- Impact on users, security, dependencies, data, AI behavior, or release: <known facts>
Return:
- the decision question and the proof that must clear before work goes on
- the chosen mode: Quick, Standard, or a stronger mode that a human reviews
- how bad it is if wrong, how easy to undo, how exposed, how easy to catch, how uncertain
- the work mode and which safety habit (HPI) to use: none, context pack, handoff, self-check, an independent check, a record of lessons from real operation (OPEX), or a trust check
- the assumptions or facts that drove the mode choice
- the record files this mode needs
- the least proof required
- the conditions that should make you ask for help
- a limits note: do not claim formal verification and validation, compliance, certification, safety, security, or regulatory adequacy
risk.md names the mode, scope, consequence, how easy it is to undo, who is exposed, what is unknown, and the proof required.python tools/ng.py validate .nuclear/changes/<slug> after the required files are filled.For the overview, process, outputs, escalation, common rationalizations, red flags, and source lineage, see skills/rating-change-risk/SKILL.md. This command sets up evidence for engineering review; it does not create compliance, formal V&V, safety, security, certification, or regulatory adequacy (see DISCLAIMER.md).
npx claudepluginhub flyfission/nuclear-grade-context-engineering --plugin nuclear-grade/riskScores the defect risk of a commit or range as a 0–10 number with driver breakdown, using git diff shape and learned heuristics.
/hatch3r-quick-changeHandles small, untracked changes with adaptive ceremony, inline or sub-agent implementation, and batch support. Detects ambiguity and asks clarifying questions before proceeding.
/consensusRuns multi-agent consensus review on code changes, docs/specs, or launch decisions using git PR/diff context and parallel agents for fast pragmatic outcomes.
/what-would-breakAnalyzes blast radius of proposed code changes via dependency mapping, risk assessment, and mitigation strategies to teach impact analysis.
/reviewRuns a 12-angle code review with skeptical triage for P0/P1 findings, or renders a requirement-to-test traceability tree. Supports --deep for full triage and trace subcommand for impact analysis.
/code_reviewPerforms comprehensive code review on modified files, categorizing findings by severity (CRITICAL/HIGH/MEDIUM/LOW), scoring quality, and saving prioritized action plan to Markdown report.