using-instincts — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited using-instincts (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.
superpowers is the base process: brainstorm, spec, plan, TDD, verify. instincts is one level finer — a set of working reflexes that keep that process honest rather than just followed. This skill is the map to them.
Load an instinct with the Skill tool the first time it applies in a session — before you act on it, then follow the skill you loaded. If several instincts hit the same move, load them all in one response.
Once loaded, a skill stays active for the rest of the session: apply it without re-invoking. One exception — after a context compact, if you can no longer see the skill's full text, it's gone; reload it before relying on it.
Acting on an instinct that was never loaded this session is working from memory, and it doesn't count: you lose the current text and the checklist, and nothing shows the reflex ran — exactly how corners get cut. Nothing runs until you call the Skill tool. The load is once per skill per session; the cost argument is spent.
| Rationalization | Reality |
|---|---|
| "I applied it internally — same result" | If it was never loaded this session, you worked from memory, not the current text. No checklist, no trace. |
| "The map line below tells me enough" | The map routes, it doesn't teach. The method lives in the skill. |
| "Loading it won't change what I'm about to type" | Then it costs seconds and confirms you. When it would have changed something — that's the whole point. |
| "No time for ceremony right now" | One load per skill per session, seconds each. You'll spend longer justifying the skip. |
| "I loaded it earlier" — said after a compact | If you can't see its full text anymore, it's gone. Reload before relying on it. |
| "superpowers already forces skills, so these are covered" | Not covered — each instinct still gets its own first load. |
| You named an instinct in your reasoning without ever loading it | Naming it is not running it. Load the skill, then proceed. |
User instructions — CLAUDE.md, AGENTS.md, direct requests — take precedence over any instinct here, and instincts take precedence over default behavior. Never cite an instinct against what the user explicitly asked for; skip a skill only when they told you to.
Load the one that matches the move you're about to make.
Verify against the world, not your memory:
Build for the failure you won't be there to see:
Look wider than the line in front of you:
Design for real conditions, not the happy path:
Finish honestly:
These sit on top of superpowers, the base process, installed separately (/plugin marketplace add obra/superpowers, then /plugin install superpowers). Without it, instincts works standalone — the reflexes just have less process around them.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.