agentmods.dev

code-review-line

code-review-line is a skill for Claude Code from jtprogru/bear-skills. It costs 109 tokens per session (843 once invoked), scanned A, original, MIT.

A code-review format that reports one finding per source-code line, with a severity level and a concrete action. A diff is the set of changes between two versions of code, and a PR is a proposed change for review.

In plain words
What is it for?
Use it to review diffs and pull requests for correctness, edge cases, error handling, concurrency, security, readability, and related risks.
Why use it?
It makes review findings quick to scan and focuses attention on problems instead of praise or a summary of the changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

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

not rated 1repo 21d ago A scan 109 tokens original MIT

Good fit Use it to review diffs and pull requests for correctness, edge cases, error handling, concurrency, security, readability, and related risks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jtprogru/bear-skills/code-review-line
View source ↗ jtprogru/bear-skills
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.

Any agent
npx skills add jtprogru/bear-skills --skill code-review-line
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 code-review-line

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jtprogru/bear-skills/code-review-line"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/code-review-line.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 843 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 $0.00109 $0.00843
Opus 5 $0.00055 $0.00421
Sonnet 5 $0.00022 $0.00169
Haiku 4.5 $0.00011 $0.00084

Measured 8d ago against content hash 438bde0bf071, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-review-line 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 8d 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.

domains/code/skills/code-review-line/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-review-line — Построчное ревью

Формат подобран так, чтобы находку можно было прочитать за секунду и сразу понять, что делать.

Формат

Одна находка — одна строка:

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

путь:строка: <эмодзи> <уровень>: <проблема>. <действие>.

Уровни:

уровень значение
🔴 bug сломается или уже сломано
🟡 risk работает сейчас, развалится при изменении условий
🔵 nit стиль, именование, читаемость
❓ q непонятно намерение, нужен ответ автора

Последней строкой итог: totals: 1 bug, 2 risk, 3 nit, 1 q.

Нет находок — ответ No issues. целиком. Пустое ревью лучше выдуманного.

Что смотреть и в каком порядке

Порядок отражает цену ошибки:

  1. Корректность — делает ли код то, что заявлено
  2. Границы — пустые данные, нули, переполнения, отсутствующие ключи
  3. Ошибки — что происходит на неуспешной ветке, не проглатывается ли исключение
  4. Конкурентность — гонки, дедлоки, общее состояние
  5. Безопасность — данные из недоверенного источника, секреты, права
  6. Читаемость — имена, длина функций, комментарии

Отдельно ищи то, чего в diff не видно: сломанные инварианты, места, где новый код противоречит соседнему, обработчики, которые надо было обновить вместе с этим.

Где формат разворачивается

Правило ~/.claude/rules/agentops-auto-clarity.md применимо и здесь. Однострочный формат выключается, когда находка касается:

  • безопасности — уязвимость объясняется целиком, с вектором и последствиями
  • архитектурного спора — если проблема в подходе, а не в строке, одной строкой её не сформулировать
  • онбординга — когда автор новичок и ему нужна не пометка, а объяснение

В этих случаях после однострочной находки идёт развёрнутый абзац. Формат — инструмент экономии, а не самоцель.

Чего не делать

  • Не хвали. «Хорошая декомпозиция» не меняет ни строки кода.
  • Не пересказывай изменения. Автор их написал.
  • Не помечай bug то, в чём не уверен: есть risk и q.
  • Не предлагай переписать всё иначе — для этого отдельный разговор, а не комментарий к строке.
  • Не собирай находки ради непустого списка.
  • Не ставь nit там, где в проекте нет соответствующего соглашения: это твой вкус, а не правило.

Read the full file on GitHub · 69 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 69 lines · 109 tokens per session scan A 438bde0bf071

Subscribe to this mod's changes

code-review-line is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 21d ago), licensed MIT. It adds 109 tokens to every session and 843 once invoked, about $0.0005 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.

Claude CodeCode reviewagentopsagentsai-agentsclaude-code-plugin
Related

Other skills, from other repositories

gemini

Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…

nowork-studio/notfair-plugin · 184 tokens

ocr

AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.

spencermarx/open-code-review · 44 tokens

OCR Review-to-Approval Loop

Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…

spencermarx/open-code-review · 178 tokens

receiving-code-review

Use when receiving code review feedback, before implementing suggestions - requires technical verification rather than performative agreement or blind implementation.

andreymudri/claude-teammates · 28 tokens

code-review

A code-review skill that examines changes for requirement fit, correctness, security, maintainability, and performance. It reports findings with risk levels.

ryanzhao1011/workframe · 40 tokens

code-to-doc

A code-reading tool that turns a module's implementation into four current-state documents: architecture, API surface, data model, and code map. A monorepo is a repository containing multiple related projects, and the tool can account for that structure as well as other supported project layouts.

ryanzhao1011/workframe · 111 tokens