llm-operator-principles — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited llm-operator-principles (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.
Consulted by every /flow:* command before any other skill.
CONVERGENCE = ZERO FINDINGS. NOT EXHAUSTED BUDGET.
Iteration ceilings (fixForwardMaxIterations, reviewCycleLimit, qualityCheckMaxIterations, closedLoop.maxDebugIterations) are safety nets against infinite loops, not planned stop points.
Iteration is cheap, you do not tire, work is measured in tool calls, not human-engineer time.
Never write, suggest, or imply estimates in calendar units (weeks, days, hours, sprints, ETAs, deadlines). Phrases like "multi-day effort" or "by Friday" must never appear in any output: PR bodies, journal entries, commit messages, AskUserQuestion bodies, escalations, follow-up issues. If size must be conveyed, use t-shirt sizing (S / M / L), only when the user asked; otherwise describe the work ("3 file edits + a test re-run").
Every finding (P1/P2/P3) from any review is fixed in this PR. The ONLY non-fix outcomes:
Everything else (P3 in untouched files, "out-of-scope" findings, findings "not required by acceptance criteria"): fix now (improve: commit if needed). Finding triage is NEVER a valid escalation trigger; if drafting a Situation/Tried/Options block about a finding, stop and fix it.
Default to ONE PR. Split only when the user asks, the work crosses a deployment boundary (migration before code), or findings need user product decisions between phases; never to reduce reviewer load or defer findings.
Defaults: fixForwardMaxIterations: 10, reviewCycleLimit: 10, closedLoop.maxDebugIterations: 5, qualityCheckMaxIterations: 3. Approaching a ceiling: re-read findings against the actual diff, check whether you misunderstood one or two are in tension, then continue. Escalate only when you cannot progress at all.
Two signals:
fixForwardMaxIterations (or reviewCycleLimit) with findings still open.Only when BOTH fire: halt (do not exceed the ceiling or push with unresolved P1/P2) and file a six-field escalation per references/escalation-format.md citing the trigger "genuinely ambiguous architecture decision" (NOT finding-triage). Situation names the finding(s) in tension; Options: accept one fix and waive the other, request clarification, or revert and approach differently. Otherwise keep iterating.
Valid (six-field escalation, references/escalation-format.md):
Invalid:
improve: commit)settings.json autonomous: true (or "autonomous mode"/"autonomous on" in-conversation): never use AskUserQuestion for decisions resolvable under these principles; reserve it for Tier 3 confirmations (merge, release) and the valid triggers above.
settings.json minimalScope: true (or "minimal scope"/"minimal scope on" in-conversation) restores deferral for cosmetic P3 in untouched files only: the "Create a follow-up issue?" AskUserQuestion is re-enabled for that case and Boy Scout expansion is limited to fixes the task self-evidently requires. Everything else still applies.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.