Creating change records
Skill FlyFission/nuclear-grade-context-engineering/skills/creating-change-records
AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assisted software engineering.
npx -y skills add FlyFission/nuclear-grade-context-engineering --skill creating-change-recordsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Creates or updates Quick or Standard change records, adds the required files, and refreshes what each claim must prove for an evidence-backed pull request. Use when starting or revising a change record. Do not use for a one-off throwaway script, or for work that belongs in an existing record rather than a new one.
SKILL.md
5.7 KB, as published. Nobody here has run it
Creating Change Records
Overview
A change record keeps the whole story in Git, together: the scope, what the change must do, the plan, the trace from claim to evidence, the proof, and the release decision. Use the smallest record that still lets a doubting reviewer decide.
Decision contract
- Claim checked: the record carries every file its mode requires, with the required links, exit criteria, source-lineage notes, and plain status labels (
pass,fail,gap,deferred,not applicable,planned) present and the internal links resolving. - Artifact observed: the mode from
risk.mdand thetemplates/quick/ortemplates/standard/templates -> a Quick record (risk.md,proof.md) or Standard record (risk.md,basis.md,plan.md,trace.md,verification.md,ship.md) plus the validator result. - Decision affected: block -- whether the packet is structurally complete and valid (
python tools/ng.py validatepass/fail). - Failure class: incomplete-record (a missing file, broken internal link, or proof command absent).
- Next action: add the missing file or link and rerun the validator; raise Quick to Standard or human review when proof cannot answer the reviewer.
When to Use
- You are starting a real AI-assisted change.
- You are updating a record after the scope, proof, risk, or release posture changed.
- You are preparing a pull request that needs evidence beyond the usual review notes.
- A preview, a self-check, a handoff, a lesson from operation (OPEX), or a supplier trust check is in play and needs a record.
When Not to Use
- The work leaves no lasting artifact and no need for review.
- The request is only to browse or explain existing docs.
- You only need to pick the mode / grade the change's risk, not author the record yet -- use
rating-change-riskinstead.
Inputs
- The chosen mode from
risk.mdor from the risk-rating skill. - A questioning-attitude screen, when uncertainty, AI power, dependency trust, or release stakes are real.
- Templates under
templates/quick/ortemplates/standard/. - The files the change affects and the proof commands.
- An existing record, if there is one.
Process
- Run
python tools/ng.py new <slug> --mode quick|standard. - Say, in your reply, which required files the chosen mode needs, by name -- not only in the files themselves, so a reader without tool access still sees the list. Name only the set for the mode in play: Quick needs
risk.mdandproof.md; Standard needsrisk.md,basis.md,plan.md,trace.md,verification.md, andship.md. - Fill in only the parts of each file that help someone decide.
- Add habit records (self-check, handoff, and the like) only when they change a decision or an action.
- Link to the files affected, the tests, the reviews, the source-map rows, and the known gaps.
- Keep status labels plain:
pass,fail,gap,deferred,not applicable, orplanned. - Run
python tools/ng.py validate .nuclear/changes/<slug>.
Outputs
- Quick record:
risk.md,proof.md. - Standard record:
risk.md,basis.md,plan.md,trace.md,verification.md,ship.md. - Habit records such as
turnover.md,self-check.md,opex.md, orsupplier-trust.mdwhen the stakes call for them. - The checker result.
Verification
- The required files exist.
- The required links, exit criteria, and source-lineage notes are present.
- The proof or verification file states the evidence status.
- The links inside the record resolve.
Escalation
- Move from Quick to Standard when Quick proof cannot answer the reviewer's question.
- Move to human review when a stronger written mode is in play.
- Stop if the record turns into a long story with no links from claim to evidence.
Common Rationalizations
- "We will fill it in after the pull request." The evidence should shape the work, not dress it up afterward.
- "Everything is obvious." If it matters to a future review, save the assumption and the path to the evidence.
- "One big record is easier." One change per record keeps the review small enough to do well.
Red Flags
- A missing proof command or evidence link.
- Claims that reach past what the tests or the review evidence cover.
- Record files that repeat each other instead of linking.
Prompt
Create or update a Nuclear-grade change record.
Inputs:
- slug: <slug>
- mode: <quick|standard>
- scope: <summary>
- affected files/assets: <list>
- questioned assumptions: <list>
- what the change must prove: <command/review/evidence>
- safety-habit (HPI) records started: <turnover/self-check/opex/supplier-trust/none>
Use the repo templates. Keep the record short. Lean on links, and point at evidence. Include the required links, the conditions for being done, and a note on where the ideas come from. Do not imply formal assurance or compliance.
Return:
- the required files for the chosen mode, named -- Quick: risk.md, proof.md; OR Standard: risk.md, basis.md, plan.md, trace.md, verification.md, ship.md (name only the set for the mode in play)
- the filled-in content for those files
Source-lineage note
This change-record skill is an original Git-native workflow. It draws on public configuration, lifecycle, assurance, secure-development, and release-readiness sources mapped in docs/00-standards-foundation/source-map.md. It does not create a certified quality assurance program.