drift — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited drift (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.
Surface the gap between Shane's stated intentions and actual behavior — where he's drifting from his own goals and values, with vault evidence for each.
Don't: use this for topic pattern analysis — that's /emerge. Don't soften drift findings — this is accountability analysis, not cheerleading.
task: "Vault access (bash only, no MCP tools): obsidian search query='TERM' limit=10, obsidian read file='Note Name' (no .md), obsidian read file='Context/accountability', obsidian read file='Context/patterns'. Analyze the gap between Shane's stated intentions and actual behavior patterns in the vault around '[argument]' (or broadly). Where is he drifting from his own stated values or goals?"skill: "drift"If Qwen is unavailable:
obsidian search query='want to' limit=10, obsidian search query='goal' limit=10, obsidian search query='intend' limit=10, obsidian search query='commit' limit=10, obsidian search query='value' limit=10Context/accountability.md and Context/patterns.md by running obsidian read file='Context/accountability' and obsidian read file='Context/patterns' via bash[argument] is provided, scope the search to that domain; otherwise cast broadly~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.