Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
Home › Compare › always-on-agent-safety vs superreview

always-on-agent-safety vs superreview

Two Engineering Claude Code skills, side by side. Pick the right skill for your workflow with a side-by-side look at metadata, sample code, and install commands.

Side-by-side

Namealways-on-agent-safetysuperreview
DescriptionSafety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of…Deep allure-server code review the MODEL or the USER can invoke: routes changed files to domain-expert agents, runs the mechanical gates, checks correctness + architecture + reuse + version pins + scope discipline…
CategoryEngineeringEngineering
Sub-categorydevopsarchitecture
Tagsai:agenttype:review
Authorcuriositechkochetkov-ma
License—Apache-2.0
Install/add-skill always-on-agent-safety/add-skill superreview

Tag overlap

Shared —

Only in always-on-agent-safety ai:agent

Only in superreview type:review

Sample code from each SKILL.md

always-on-agent-safety

┌─────────────────────────────────────────────────────────┐
│              Always-On Agent Risk Surface                │
├────────────┬───────────┬──────────┬──────────┬──────────┤
│  PRIVACY   │   COST    │  SCOPE   │  PSYCH   │ SECURITY │
│            │           │          │          │          │
│ What the   │ Runaway   │ Agent    │ Human    │ External │
│ agent      │ token     │ does too │ depends  │ actors   │
│ knows      │ spending  │ much or  │ on agent │ exploit  │
│ about you  │ and…

superreview

PLAN — allure-server superreview
INPUT:  <arguments verbatim, or "(empty)">
MODE:   <resolved MODE> — <which rule>; Depth <resolved DEPTH> — <which signal>
SCOPE:  <branch, commit range/folder, focus, file count>
DO:     <gates, intent pass, and — EXTENDED only — expert fan-out, scope passes, validation>
RESULT: <the merged report + chat summary>

When to choose each

always-on-agent-safety — Safety, privacy, cost management, and frank advice for building always-on AI agents with episodic memory. Covers data hygiene, privacy risk surfaces, runaway cost prevention, scope creep, psychological effects of…

superreview — Deep allure-server code review the MODEL or the USER can invoke: routes changed files to domain-expert agents, runs the mechanical gates, checks correctness + architecture + reuse + version pins + scope discipline…

Both are free to install. If you're unsure, install both — Claude Code skills are isolated by filename and only collide if their trigger phrases overlap (rare). The richest signal is the SKILL.md body itself — open both skill pages and read the first paragraph of each.

Open always-on-agent-safety → Open superreview →

Other comparisons in this category

See all Claude Code skill comparisons · Browse all Engineering skills · Top 100