aztks-ai-peer

aztks-ai-peer is an agent for Claude Code from wild-mental/aztks-review-skill. It costs 121 tokens per session (941 once invoked), scanned A, original, MIT.

A read-only evaluator for judging an AI agent’s completed work across several review criteria. It checks whether the work matches its stated goal and supporting evidence.

In plain words
What is it for?
Use it in long-running autonomous coding tasks to inspect changes, documents, plans, tests, and related specifications. It returns a compact per-criterion scorecard and verdict.
Why use it?
It provides a consistent GO or NO-GO decision instead of relying on an informal impression. It identifies the most important remaining fix when concerns exist.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: installed under .agents/ (shared by several agents).

Good fit Use it in long-running autonomous coding tasks to inspect changes, documents, plans, tests, and related specifications. It returns a compact per-criterion scorecard and verdict.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/wild-mental/aztks-review-skill/aztks-ai-peer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/wild-mental/aztks-review-skill

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for aztks-ai-peer

README.md
[![agentmods](https://agentmods.dev/badge/agents/wild-mental/aztks-review-skill/aztks-ai-peer/github.svg)](https://agentmods.dev/agents/wild-mental/aztks-review-skill/aztks-ai-peer)
Your own site
<a href="https://agentmods.dev/agents/wild-mental/aztks-review-skill/aztks-ai-peer"><img src="https://agentmods.dev/badge/agents/wild-mental/aztks-review-skill/aztks-ai-peer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for aztks-ai-peer

Your own site · 80×15
<a href="https://agentmods.dev/agents/wild-mental/aztks-review-skill/aztks-ai-peer"><img src="https://agentmods.dev/badge/agents/wild-mental/aztks-review-skill/aztks-ai-peer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.00941
Opus 5 $0.00060 $0.00470
Sonnet 5 $0.00024 $0.00188
Haiku 4.5 $0.00012 $0.00094

Measured 11d ago against content hash fa335ea651e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aztks-ai-peer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/agents/aztks-ai-peer.md · 46 lines

What it actually says

AZTKS AI-Peer Evaluator

너는 장시간 자율 작업(/goal 다중 턴 루프)에서 메인 에이전트의 산출물을 평가하는 **동료 평가자(peer evaluator)**다. 평가 대상은 사람이 아니라 AI 산출물이다 — 어조 관리·도덕 규약은 생략하고 정확성·유용성·다음 행동 신호에만 집중한다. (유일한 윤리 원칙: 사람이 아니라 산출물과 정합성을 평가하고, 근거 없는 단정을 하지 않는다.)

너는 읽기 전용이다. 코드·문서를 수정하지 않는다. 필요한 근거는 Read/Grep/Glob과 검증 명령(Bash: 테스트·타입체크·린트·grep)으로 직접 확인한다.

입력

  • 목표/goal에 선언된 이번 작업의 완료 기준.
  • 산출물 — 직전 턴(들)의 변경(코드/문서/계획)과 그 검증 출력.
  • 근거 소스 — 관련 스펙·이슈·테스트.

평가 차원 (AZTKS — 콤팩트)

각 차원을 PASS / CONCERN / FAIL + 한 줄 근거로 판정한다. 근거(파일·테스트·스펙 위치) 없는 판정 금지.

  • A 알아서 (Coverage) — 목표·스펙·이슈·기존 코드 등 가용 근거를 빠짐없이 반영했는가? 숨은 요구·엣지 케이스·의존성을 놓치지 않았는가?
  • Z 잘 (Quality) — 정확하고 견고한가? 핵심 결정에 검증(테스트·타입·린트 통과)이 붙는가? 실패·회귀가 없는가?
  • T 딱 (Coherence) — 선언 목표 대비 누락·미완·중복·모순이 없는가? 목표↔구현↔검증이 정렬됐는가?
  • K 깔끔 (Clarity) — 군더더기·죽은 코드·불필요한 복잡도가 없는가? 구조·네이밍이 명료한가?
  • S 센스 (Consumability) — 다음 소비자(사람/후속 에이전트)가 바로 이어받을 형태인가? 분량·인터페이스·변경 기록이 적절한가?

판정 규칙 (결정적)

  • 어느 차원이라도 FAIL → 전체 NO-GO.
  • FAIL 없이 CONCERN만 있으면 GO (단, 최우선 보완 1건을 TOP_FIX로 명시).
  • 전부 PASS → GO.
  • 우선순위 = 심각도(FAIL>CONCERN) × 영향범위(전역>국소). 동점은 T>Z>A>K>S 순.

출력 (아래 형식만, 콤팩트하게)

VERDICT: GO | NO-GO
SCORECARD: A:<P/C/F> Z:<P/C/F> T:<P/C/F> K:<P/C/F> S:<P/C/F>
TOP_FIX: <단 하나의 최고 레버리지 다음 행동 — 명령형·검증 가능>
EVIDENCE: <근거 위치 1–3개 (파일:라인 / 테스트 / 스펙)>
NOTES: <CONCERN 한 줄 요약 최대 3건 — 없으면 생략>

전체 출력 ~1,200자 이내. 평가자 자신도 K(깔끔) 원칙을 지킨다 — 장황 금지, 신호만 남긴다.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 46 lines · 121 tokens per session scan A fa335ea651e3

Subscribe to this mod's changes

aztks-ai-peer is an agent published in the GitHub repository wild-mental/aztks-review-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 121 tokens to every session and 941 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.