source-of-truth-preflight — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited source-of-truth-preflight (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Run this skill before editing code for non-trivial feature work, especially when the task touches domain models, state machines, runtime providers, repository contracts, schema migrations, or existing subsystem boundaries.
This is a short gate, not a design ceremony. Produce the report before coding. If the report cannot identify the canonical model or enforcement points, pause instead of implementing.
Use this skill when any of these are true:
State the requested unit in one sentence. Name explicit non-goals.
Search before designing. Prefer rg:
rg -n "export (interface|type|class|const) .*<Concept>|<Concept>Schema|type <Concept>|interface <Concept>" src apps .specs .adr docs
rg -n "from ['\"].*<concept>.*['\"]|<Concept>" src appsRecord:
Name the model the implementation will build on. If there are multiple live models, classify each as one of:
canonical: new work should build herelegacy-live: still used, but not the right extension pointadapter-only: used only to translate between systemscontrol-plane: metadata/registry state, not the domain object itselftest-fixture: fixture-only, not production semanticsIf the choice is not obvious, pause and ask for a decision.
List the states that should be impossible. Check whether current types make them impossible.
Look for:
status plus many nullable fieldsstring identifiers for different ID classessave* methods that bypass lifecycle transitionsdiscriminated union
For each illegal state, decide whether to:
For each acceptance criterion, name the enforcing artifact:
If an acceptance item maps only to prose or a broad test, mark it as weak.
Before adding a new service/type/schema, answer:
Why does the existing model/engine/repository not own this?Proceed only when the answer is concrete. Good answers include:
Weak answers include:
After two unexpected findings, stop and write:
Do not debug process/tooling or migrate workflow systems inside the feature session unless that is the explicit unit of work.
Produce this before code edits:
Source Of Truth Preflight
Unit:
Non-goals:
Canonical model:
Legacy/competing models:
Control-plane models:
Adapters needed:
Illegal states currently representable:
Acceptance-to-enforcement map:
New types/services proposed:
Reuse decision:
Surprises:
Proceed / pause:Use file references for every model claim.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.