preregister — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited preregister (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.
This skill supports "decide before observing" for confirmatory claims. Exploratory runs may still use seed_perturb / pin_metric, but any number intended as a main publication claim should have a matching prereg row first.
bt-tournament returns the top-2 hypotheses when the next run is explicitly confirmatory./preregister.| arg | meaning | example |
|---|---|---|
hypothesis_id | id from mem_nodes (kind=hypothesis) | hyp_a3f9... |
metric_name | exact claim text the engineer will pin later | "test accuracy" |
direction | higher_better or lower_better | higher_better |
threshold | number that separates met from missed | 0.85 |
seed_count | how many seeds the seed_perturb call must use | 5 |
alpha | nominal Type-I error rate | 0.05 |
mc_correction | bonferroni (default), none, or legacy alias bh | bonferroni |
heldout_dataset | optional dataset name to be queried via query_heldout | mnist-test |
mcp__verify__list_preregistrations(hypothesis_id=...). If a row exists with status open, do not fail the session. Ask whether to reuse that lock, withdraw it outside this tool, or create a separate confirmatory prereg for a genuinely different metric.mcp__verify__preregister(...) with the exact metric text and threshold.prereg_id in the cockpit Claims tab; the user must see it before the engineer starts implementing.prereg_id along the agent chain so engineer knows which lock applies.The engineer or verifier later calls mcp__verify__resolve_preregistration(prereg_id, observed_value, observed_p_value). The verdict is frozen at that point and:
bh value is accepted as a compatibility alias for existing workflows.prereg_resolved events fire into the cockpit.reviewer agent later treats confirmatory manuscript claims with status != met as blockers. Exploratory claims must be labelled as exploratory in the manuscript.update_preregistration. If the locking was wrong, file a new prereg and add a note in the manuscript explaining that the earlier run was exploratory or superseded.withdrawn is reserved for cases the user actively cancels a hypothesis; the verifier never withdraws on its own.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.