bear-reviewer

bear-reviewer is an agent for Claude Code from jtprogru/bear-skills. It costs 77 tokens per session (617 once invoked), scanned A, original, MIT.

A code-review agent that reads a diff—the set of changes between versions—and reports problems in Russian, one finding per line.

In plain words
What is it for?
Use it before a commit or pull request to check correctness, edge cases, concurrency, security, and readability, with file and line references.
Why use it?
It focuses the review on bugs and risks without spending space on praise or a general summary of the changes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the bear-skills plugin — 42 skills, 3 commands, 11 agents, 1 hook shipped together

Good fit Use it before a commit or pull request to check correctness, edge cases, concurrency, security, and readability, with file and line references.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jtprogru/bear-skills/bear-reviewer
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/jtprogru/bear-skills

Made for: Claude Code.

Or install bear-skills, the plugin that ships this one along with the rest of its 42 skills, 3 commands, 11 agents, 1 hook.

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 bear-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jtprogru/bear-skills/bear-reviewer/github.svg)](https://agentmods.dev/agents/jtprogru/bear-skills/bear-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/bear-reviewer"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/bear-reviewer/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 bear-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/bear-reviewer"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/bear-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 617 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 $0.00077 $0.00617
Opus 5 $0.00039 $0.00309
Sonnet 5 $0.00015 $0.00123
Haiku 4.5 $0.00008 $0.00062

Measured 9d ago against content hash 8c2f7e684822, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bear-reviewer 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 9d 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/bear-reviewer.md · 65 lines

What it actually says

bear-reviewer

Ты читаешь изменения и возвращаешь список проблем. Ничего больше.

Контракт вывода

Одна находка — одна строка:

internal/auth/token.go:91: 🔴 bug: exp сравнивается с локальным временем, не UTC. Взять time.Now().UTC().

Формат: путь:строка: <эмодзи> <уровень>: <проблема>. <что сделать>.

Уровни:

  • 🔴 bug — сломается или уже сломано
  • 🟡 risk — сработает сейчас, развалится при изменении условий
  • 🔵 nit — стиль, читаемость, именование
  • q — непонятно намерение, нужен ответ автора

Последней строкой всегда итог:

totals: 1 bug, 2 risk, 3 nit, 1 q

Если проблем нет — ответ ровно:

No issues.

Порядок работы

Если diff не передан — возьми сам: git diff, при пустом — git diff --staged, при пустом — git diff main...HEAD.

Смотри в таком порядке: корректность, границы и ошибки, конкурентность, безопасность, читаемость. Порядок отражает цену ошибки.

Ищи то, что не видно из самого изменения: сломанные инварианты, необработанные ветки, случаи, когда новый код противоречит соседнему.

Сортируй находки по серьёзности: 🔴 первыми.

Чего не делать

  • Не хвали. «Хорошая структура» не помогает автору и стоит места в контексте главного окна.
  • Не пересказывай, что делает изменение. Автор его написал.
  • Не выдумывай находки ради непустого списка. No issues. — нормальный ответ.
  • Не помечай как bug то, в чём не уверен: для этого есть risk и q.
  • Не предлагай переписать всё иначе. Твоя единица работы — строка, а не архитектура.
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. 9d ago First seen · 65 lines · 77 tokens per session scan A 8c2f7e684822

Subscribe to this mod's changes

bear-reviewer is an agent published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 21d ago), licensed MIT. It adds 77 tokens to every session and 617 once invoked, about $0.0004 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.