ledger — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited ledger (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.
Single source of truth shared between claude-ops (Mac) and Perplexity (off-Mac). Stored at ~/.claude-ops/ledger.jsonl and mirrored to Notion DB "Ops Ledger".
# Default: human digest of last 24h
/ops:ledger
# What needs owner's attention right now?
/ops:ledger awaiting
# What did Perplexity do while I was at the gym?
/ops:ledger query --source perplexity --since -PT4H
# What's been touched on this Gmail thread?
/ops:ledger query --claim-key gmail:thread:19e690a55d213f52Wraps ~/.claude-ops/bin/ledger (the CLI from this skill). Always reports:
Before doing real work, run:
~/.claude-ops/bin/ledger query --claim-key "$CLAIM_KEY" --since -PT24HIf result has any entry with status in (in_progress, done, drafted, awaiting_sam), SKIP — the other system already handled it. Don't duplicate.
After doing work:
~/.claude-ops/bin/ledger claim --claim-key "$CLAIM_KEY" --kind <kind> --brand <brand> \
--title "<title>" --source claude-ops
# ... do work ...
~/.claude-ops/bin/ledger resolve <id> --status done|drafted|awaiting_sam~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.