gut-check — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited gut-check (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.
Don't lock in a decision or assert a fact from a thin basis: memory, the handoff, the first framing, an unexamined pick. Ground it first, then proceed.
Violating the letter of this is violating the spirit of it. "I'm confident, so I can skip the check" is the exact failure this skill exists to catch.
You are about to do one of these AND the basis is thin (not verified this session):
Skip it for trivial, reversible steps, and for claims already backed by output you produced this turn. When unsure whether it's trivial, it isn't, engage.
Name the thin basis in one line: "I'm about to [decide X / claim Y] based on [memory / the handoff / first framing / my own pick]." Naming it is what flips you from asserting to grounding.
Then pick the mode: grounding a decision → DECIDE. Grounding a fact → VERIFY.
decisions. The answer is often already settled there, don't reason in a vacuum.
and durability (long-run). Not a blurry summary.
thinking; don't offload the thinking, and don't seize the deciding.
Memory and the handoff do not count.
/ "Partial: X yes, Y no." Show the receipt.
Hard rule, the pre-existing dismissal: never call a failure pre-existing, unrelated, or flaky without reproducing it on a clean base this session (run on main, git stash + test, or git blame the lines). This is the highest-value case: such dismissals close off investigation and almost always go unchecked. "It's probably pre-existing" is a trigger thought, not a conclusion.
If grounding flips your answer, say so plainly. Reversing your own earlier pick after checking is the skill working, not a failure.
If you catch yourself thinking any of these, you're rationalizing:
All of these mean: ground first. For the full set of excuses and their counters, read references/rationalizations.md. For worked DECIDE/VERIFY examples, read references/examples.md.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.