recording-a-known-good-version
Skill33 starsChanged 16 days agoMITView on GitHub
Records the version everyone agreed is correct, the evidence behind it, and what would make that record out of date. Use when a standard change ships, when prompts, models, tools, dependencies, docs, or release items are accepted, or when a lesson forces a re-record. Do not use for a tiny local edit with nothing to release or trust, or while the work is still under review.
In this repository34 other files it gives its agents.
- AGENTS.mdAGENTS.md
- challenge/AGENTS.mdAGENTS.md
- challenge/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- breaking-down-the-workSkill
- briefing-an-agentSkill
- checking-factsSkill
- checking-legal-and-safety-wordingSkill
- checking-release-readinessSkill
- checking-source-claimsSkill
- checking-what-a-change-affectsSkill
- choosing-what-to-controlSkill
- closing-stale-packetsSkill
- creating-change-recordsSkill
- deciding-who-decidesSkill
- declaring-intentSkill
- double-checking-before-actingSkill
- handing-off-workSkill
- learning-from-experienceSkill
- organizing-project-foldersSkill
- proving-claimsSkill
- questioning-attitudeSkill
- rating-change-riskSkill
- recording-what-an-agent-didSkill
- reporting-shared-defectsSkill
- responding-to-incidentsSkill
- reviewing-code-qualitySkill
- running-a-review-panelSkill
- staying-on-missionSkill
- stress-testing-agent-changesSkill
- tracking-deficienciesSkill
- using-nuclear-gradeSkill
- verifying-final-artifactsSkill
- vetting-outside-code-and-modelsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Write down what is included and what is left out.
- Distinctive: line 61
Stop if the record claims a version is accepted but the evidence is missing.
- Distinctive: line 78
Create or update the Nuclear-grade baseline record for this change.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Recording a Known-Good Version
Overview
A baseline is simply the version everyone agreed is correct and wants to protect. This skill writes down that version, the evidence that backs it, and the things that would make it out of date.
Decision contract
- Claim checked: the accepted version can be rebuilt exactly from its named commit/PR/release, everything under control is either included or deliberately left out, the accepted residual risks have owners, and the triggers that force a new known-good version are recorded.
- Artifact observed:
controlled-items.md,change-impact.md,verification.md, theship.mddecision, and the identifying commit/PR/release -> abaseline.mdwith included/excluded scope, accepted gaps, and re-record triggers. - Decision affected: warn -- the accepted baseline the ship decision produced, and the triggers that invalidate it.
- Failure class: unrebuildable-baseline (a version recorded as accepted with missing evidence or silently dropped scope).
- Next action: record the missing link or excluded scope as a named gap; escalate when the version affects customers, regulated work, or outside trust.
When to Use
- A standard change ships, or the public-facing state of the workflow changes.
- Controlled prompts, models, tools, dependencies, docs, templates, skills, commands, checkers, or release items are accepted.
- A lesson from operation or a piece of review feedback means you need to re-record the known-good version.
- A near miss or operating lesson changes the accepted state or the trigger for re-checking it.
When Not to Use
- The change is a tiny local edit with nothing to release and no trust on the line.
- The work is still under review and the evidence is not ready.
Inputs
- The records for what is under control, the ripple effects, the verification, and the ship decision (
controlled-items.md,change-impact.md,verification.md, andship.md). - The pull request, commit, or release that identifies the exact version.
- The gaps you accepted and the triggers for re-checking.
Process
- Name the known-good version and the decision it came from.
- Write down what is included and what is left out.
- Link the basis, ripple effects, run record, verification, ship decision, and any operating lessons.
- Name the leftover risks you accepted and what would trigger a re-check.
- Record what would force you to write a new known-good version.
Outputs
- A
baseline.mdfile, or a known-good section insideship.md. - The triggers that would force a new known-good version.
- The accepted gaps, each with an owner.
- A link to the lesson, if a lesson is what changed the version.
Verification
- The version can be rebuilt exactly from the commit, pull request, release, or artifact.
- Everything under control is either included or clearly left out on purpose.
- The re-check triggers are easy to find.
Escalation
- Stop if the record claims a version is accepted but the evidence is missing.
- Escalate when the version affects customers, regulated work, safety, security, procurement, or any outside-trust claim.
Common Rationalizations
- "The merge commit is the baseline." The commit names the version; the record explains why it was accepted and what would change it.
- "We'll record the version later." Waiting lets things drift at the exact moment that matters.
- "Only release teams need this." Agent prompts, skills, and public claims drift too.
Red Flags
- The record has no links to evidence.
- Things were quietly left out.
- There are no re-check triggers for dependencies, models, prompts, tools, or public claims.
Prompt
Create or update the Nuclear-grade baseline record for this change.
Inputs:
- packet:
- baseline identity:
- included controlled items:
- excluded items/claims:
- verification evidence:
- OPEX / near-miss links:
- accepted gaps:
Return a baseline record. Include the version that is saved, the items it covers, the items it leaves out, links to the evidence, the gaps you have accepted, and what should trigger a re-check or a new baseline. Do not imply formal assurance or compliance.
Source-lineage note
This skill is an original known-good-version workflow influenced by public configuration-management, lifecycle, release-readiness, and operating-lesson sources mapped in docs/00-standards-foundation/source-map.md. It does not create formal assurance or compliance.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

