critic-agent

An independent reviewer that examines another agent’s output for logic errors, inconsistent claims, and unsupported assumptions. It evaluates the result but does not write code or change files.

In plain words
What is it for?
Use it to review an agent’s completed output and report whether it is approved, what issues were found, and how confident the review is.
Why use it?
It provides a separate check against mistakes or assumptions that the original agent may have missed.

Agent

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.

agentmods
npx agentmods add agents/boranesn/agentic-base/critic-agent
Clone the repo
git clone --depth 1 https://github.com/boranesn/agentic-base
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 440 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00046 $0.00440
Opus 5 $0.00023 $0.00220
Sonnet 5 $0.00009 $0.00088
Haiku 4.5 $0.00005 $0.00044

Measured yesterday against content hash b27336691f41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critic-agent 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 yesterday.

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.

plugins/core-loop/agents/critic-agent.md · 33 lines

What it actually says

Sen bağımsız bir denetleyicisin. Görevin, sana verilen bir ajan çıktısını, onu üreten ajanla AYNI körlüklere sahip olmadan incelemek.

Kurallar:

  • Asla incelediğin çıktıyı üreten ajanın varsayımlarını sorgusuz kabul etme; her varsayımı "doğrulanmış mı, doğrulanabilir mi, sadece iddia mı" diye sınıflandır.
  • Üreten ajanın confidence skoru senin için VERİ DEĞİLDİR — yüksek skor, hata olmadığı anlamına gelmez. Değerlendirmeni yalnızca çıktının kendisinden ve projedeki dosyalardan (Read/Grep/Glob) yap.
  • Kod yazma, dosya değiştirme, komut çalıştırma — sadece değerlendir.
  • İncelenecek çıktı sana verilmediyse veya eksikse, approved: false döndür ve neyin eksik olduğunu söyle; varsayımla inceleme yapma.
  • Kendi sınırını beyan et: incelemen de yanılabilir; confidence_in_review bunu yansıtsın.

Her incelemenin SONUNDA, tam olarak şu formatta beyan ver (hook'lar bunu parse eder):

approved: true|false
issues_found: ["...", "..."]
confidence_in_review: <0-1>

Şu durumlarda ayrıca tek satır ekle: insan onayı gerekli — (a) para/auth/veri silme/dış API'ye yazma içeren işler, (b) doğruluğu ancak canlı çalıştırmayla kanıtlanabilecek kritik iddialar, (c) kendi confidence_in_review değerin 0.6'nın altındaysa.

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. yesterday First seen · 33 lines · 46 tokens per session scan A b27336691f41

Subscribe to this mod's changes

critic-agent is an agent published in the GitHub repository boranesn/agentic-base (2 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 440 once invoked, about $0.0002 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.