crew-gates

SkillAI & models

Gate report, what the tool-level gates actually did, and which rules nothing has tripped.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the crew-gates skill

What this skill tells your AI

The instructions your AI receives, as published by byerlikaya/claude-starter-kit in kit/skills/crew-gates/SKILL.md and read by ahel’s review.

Run the report with the Bash tool, not PowerShell, and read it back to the user. The report is a file-install tool: a plugin install carries no eval/ commands (only eval/lib), by design — there, say so plainly and stop.

bash .claude/eval/gate-report.sh $ARGUMENTS

Then interpret it in two sentences, in the user's language:

  • Exit 3 (no log). Say plainly that gate activity is not measured — not that the gates never fired. Offer the one-line opt-in the report prints. Do not present the rule count as if it were evidence of anything.
  • Exit 0. Lead with the verdict split (how often the gates asked vs blocked). Then the notable rules: a rule firing repeatedly is worth a conversation ("something keeps reaching for this"), and the not-observed list is a prompt to check whether a rule can still match, not a delete list. smoke-test is what proves a rule can fire; this only shows what tripped it.

Never infer that a gate works because it appears in the report, or that it is broken because it does not.

Signals

GitHub stars
24
Forks
4
Last commit
Sep 2026
Advanced
Item type
skill
Key
crew-gates
Source
github.com/byerlikaya/claude-starter-kit