A read-only pre-submission code review tool for AKG projects. It checks formatting, security-related issues, rebase conflicts, dangerous functions, and compliance with SPEC.md.

Use it before committing or when requesting a code review to run tools such as ruff and bandit, inspect the target branch, apply project-specific checks, and generate a report.

It catches common problems before submission and records the findings in a review report without changing the code.

akg-review — Skill for Claude Code and OpenCode by mindspore-ai

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 mindspore-ai/akg --skill akg-review

Clone the repo

git clone --depth 1 https://github.com/mindspore-ai/akg

Made for: Claude Code, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mindspore-ai/akg/akg-review/github.svg)](https://agentmods.dev/skills/mindspore-ai/akg/akg-review)

Your own site

<a href="https://agentmods.dev/skills/mindspore-ai/akg/akg-review"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/akg-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mindspore-ai/akg/akg-review"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/akg-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,836 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.03836
Opus 5	$0.00034	$0.01918
Sonnet 5	$0.00013	$0.00767
Haiku 4.5	$0.00007	$0.00384

Measured 11d ago against content hash 7fce94a811bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

akg-review scanned grade C with 1 finding 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_code_style.py, scripts/check_rebase.py, scripts/check_spec_compliance.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$REVIEW_TMP_DIR"

akg_agents/.opencode/skills/akg-review/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AKG Review - 提交前代码自审

⛔ 核心规则

所有产物写入 $AKG_AGENTS_DIR/.tmp/review/。
优先使用现成工具：ruff（代码规范）、git（rebase 检查）。
自定义检查仅覆盖项目特定规则（危险函数、包名、SPEC.md）。
不执行任何修改，只检查和报告。

依赖检查（自动）：

ruff - 如未安装，自动执行 pip install ruff
git - 系统自带

流程

Step 0: 依赖检查（自动安装）

for tool in ruff bandit; do
  if ! command -v $tool &> /dev/null; then
    echo "$tool 未安装，正在安装..."
    pip install $tool -q
  fi
done

MYPY_AVAILABLE=$(command -v mypy &> /dev/null && echo "yes" || echo "no")
VULTURE_AVAILABLE=$(command -v vulture &> /dev/null && echo "yes" || echo "no")

REVIEW_TMP_DIR=$(mktemp -d "${TMPDIR:-/tmp}/akg_review_XXXXXX")

Step 1: 确定目标分支（需用户确认）

缓存文件：$AKG_AGENTS_DIR/.tmp/review_last.txt，记录上次确认过的参数。

CURRENT_BRANCH=$(git rev-parse --abbrev-ref HEAD)
TARGET_BRANCH=${ARGUMENTS:-}
REVIEW_CACHE="$AKG_AGENTS_DIR/.tmp/review_last.txt"

确定 TARGET_BRANCH 的优先级（依次尝试，取第一个有效值）：

用户本次指定的参数（$ARGUMENTS）
缓存文件中记录的上次值（$REVIEW_CACHE）
自动探测远程分支

# 如果用户未指定，尝试读缓存
if [ -z "$TARGET_BRANCH" ] && [ -f "$REVIEW_CACHE" ]; then
  CACHED_TARGET=$(grep '^target_branch=' "$REVIEW_CACHE" | cut -d= -f2)
  if [ -n "$CACHED_TARGET" ] && git rev-parse --verify "$CACHED_TARGET" &>/dev/null; then
    TARGET_BRANCH="$CACHED_TARGET"
  fi
fi

# 如果仍为空，自动探测
if [ -z "$TARGET_BRANCH" ]; then
  for candidate in origin/br_agents $(git branch -r | grep '/br_agents$' | head -1 | tr -d ' '); do
    if git rev-parse --verify "$candidate" &>/dev/null; then
      TARGET_BRANCH="$candidate"
      break
    fi
  done
fi

必须向用户展示以下信息并等待确认后才能继续：

📋 审查参数确认

当前分支: $CURRENT_BRANCH

目标分支: $TARGET_BRANCH （来源：用户指定 / 上次缓存 / 自动探测）

变更文件数: git diff $TARGET_BRANCH...HEAD --name-only --relative | wc -l

变更 .py 文件数: git diff $TARGET_BRANCH...HEAD --name-only --diff-filter=ACMR --relative | grep '\.py$' | wc -l

确认以上信息正确？(y/n)，或指定其他目标分支。

Read the full file on GitHub · 422 lines

Files

What ships with it

4 files 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.

11d ago First seen · 422 lines · 67 tokens per session scan C 7fce94a811bf

Subscribe to this mod's changes

akg-review is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 67 tokens to every session and 3,836 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Security

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

full-repo-review

Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.

notque/vexjoy-agent · 22 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens

akg-review