← ClaudeAtlas

agent-reviewlisted

Audits a candidate agent (.agent.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence) plus Gate 6 (tool allowlist minimality). Use when reviewing a new agent draft before commit, evaluating a Mall agent or store agent for adoption, or re-auditing existing agents on a periodic cadence.
fabioc-aloha/Alex_ACT_Edition · ★ 0 · AI & Automation · score 73
Install: claude install-skill fabioc-aloha/Alex_ACT_Edition
<!-- intentional divergence from Supervisor: Edition expands the five-gate names inline (heirs don't ship ADR-007) and strips Supervisor-only ADR/script refs. Same gates, same criteria. Audited 2026-05-31. --> # Agent Review Audit a candidate agent against the five-gate contract plus mandatory Gate 6 (Tool Allowlist Minimality). Agents are sub-process roles with their own tool capabilities — each tool granted is an attack/error surface, so the allowlist gate is mandatory for this type. ## When to Use Three fire contexts: 1. **Author self-audit** — dogfood your own draft before committing. Invoked from [agent-creator](../agent-creator/SKILL.md) Phase 7. 2. **External candidate adoption** — gate before pulling a Mall agent or store agent into this brain. 3. **Periodic re-audit** — re-check existing agents on a cadence (e.g., quarterly retraining). The shared gate model lives in [skill-review/SKILL.md § The Five Gates](../skill-review/SKILL.md). This file documents the **agent-specific criteria** for each gate plus the mandatory **Gate 6 — Tool Allowlist Minimality**. A mechanical validator (e.g., a brain-qa script that ships with the heir) typically checks Gate 1 frontmatter compliance and the mechanical subset of Gate 5. Gates 2–6 are judgment-only. ## The Five Gates + Gate 6 A candidate must pass **all six** to ship. Failure on any gate = decline or revise. ### Gate 1 — Spec Compliance | Check | Pass criterion | |---|---| | Frontmatter present | `name` + `descripti