locus-feedback-d23e2e — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited locus-feedback-d23e2e (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.
Record quality feedback on the most recent Locus run. Annotates the run's metrics file with a user verdict so retrieval quality can be tracked over time.
Usage: /locus-feedback <quality> [note]
Arguments:
quality (required) — pass, partial, or fail (aliases: good/ok/bad)note (optional) — free-text explanation (quote if it contains spaces)Examples:
/locus-feedback pass
/locus-feedback partial "Got the right room but missed the port number"
/locus-feedback fail "Answered about the wrong service entirely"Map the first argument to a canonical value:
pass or good → "pass"partial or ok → "partial"fail or bad → "fail"If the argument is missing or unrecognized, stop and output:
Usage: /locus-feedback <pass|partial|fail> [note]Walk up from the current working directory looking for a directory that contains both INDEX.md and _metrics/. Stop at the filesystem root if not found.
If no palace root is found, output:
Error: no palace found (no _metrics/ directory above current path).
Run from inside a palace directory.List all .json files in <palace_root>/_metrics/ sorted by modification time (most recent first). Use the first result.
If _metrics/ is empty or missing:
Error: no metrics files found in <palace_root>/_metrics/.
Run a locus query first to generate a metrics file.Read the file. Parse as JSON. Check:
schema_version is "1" — if not, warn but continuefeedback field is null — if already set, output a warning: Warning: this run already has feedback (<existing quality>).
Overwrite? If yes, re-run with the same command. (Proceeding to overwrite.)Then overwrite.
Set the feedback field to:
{
"quality": "<resolved quality>",
"note": "<note or null>",
"recorded_at": "<current UTC timestamp in ISO 8601>"
}Write the updated JSON back to the same file (preserve all other fields, maintain 2-space indentation).
Output a single confirmation line:
Locus feedback recorded: <quality> → <relative path to metrics file>If a note was provided:
Locus feedback recorded: <quality> — "<note>" → <relative path to metrics file>Locus feedback recorded: pass — "Got the exact IP and port" → _metrics/2026-03-02T143012Z.jsonErrors use the prefix Error:, warnings use Warning:. No other output.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.