issue-review

issue-review is a skill for Claude Code from ArcBlock/agent-skills. It costs 78 tokens per session (24,246 once invoked), scanned A, original, MIT.

A process for reviewing one GitHub issue, which is a tracked task, question, proposal, or investigation. It reads the issue and related repository material, checks the result against the actual code, and posts evidence-backed findings.

In plain words
What is it for?
Reviewing documentation, auditing existing documents, performing system audits, researching integrations, and assessing internal ideas.
Why use it?
It keeps reviews grounded in the implemented project instead of leaving conclusions only in a private conversation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Part of the agentloop plugin — 20 skills shipped together

Good fit Reviewing documentation, auditing existing documents, performing system audits, researching integrations, and assessing…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arcblock/agent-skills/issue-review
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 ArcBlock/agent-skills --skill issue-review
Clone the repo
git clone --depth 1 https://github.com/ArcBlock/agent-skills

Made for: Claude Code.

Or install agentloop, the plugin that ships this one along with the rest of its 20 skills.

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 issue-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/arcblock/agent-skills/issue-review.svg)](https://agentmods.dev/skills/arcblock/agent-skills/issue-review)
Your own site
<a href="https://agentmods.dev/skills/arcblock/agent-skills/issue-review"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/issue-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 24,246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.24246
Opus 5 $0.00039 $0.12123
Sonnet 5 $0.00016 $0.04849
Haiku 4.5 $0.00008 $0.02425

Measured 6d ago against content hash f80d6c0e0c80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

issue-review scanned grade A 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

不许 `ALLOW_STALE_UPLOADER=1` 绕过;② 任何要内嵌进 comment 的图片 URL 必须**无凭据 curl 200**
plugins/agentloop/skills/issue-review/SKILL.md · 693 lines

How it starts

The opening of the file, as written. The whole thing — 693 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Review — AI Agent Review / Audit for Doc-from-Issue

Repo profile — read .claude/repo-profile.md first. This skill is repo-agnostic; arc is the reference implementation. Use the profile's repo_slug, verification_entry, kb_issue, plugin_root (where issue-graph's scripts live), and toolchain wherever this doc shows an arc default. Arc's own provenance for the lessons below is not inlined here (fuller case narratives, where they exist, are under .claude/case-law/).

把一篇 issue 处理到位:读 issue + 引用的 repo 文档/代码 + 已有 comments + 对照已落地的实现/代码/intent,产出带证据的发现,作为 comment 落回 issue(而不是埋在某次对话里)。覆盖五类:

  • Doc-review:人起源的新设计在 issue 里被讨论/评审(找漂移、独立发现、reframe)。轻量、讨论导向,产出 = 评审 comment + 拆分建议。
  • Doc-audit:repo 里的存量老文档被逐篇审计(对照代码重验、跑测试、给 5 类结论)。有界单元,按价值分档投入。
  • System-audit(comprehensive code audit):issue 要求对一个子系统 / 跨平台 parity / runtime 本身做全面代码审计(如「Swift/Kotlin 实现是否落后于 Node/CF 参考」)。无界任务,完整执行是契约——见下「★ System-audit」。
  • Research(研究类):issue 要求调研一个外部系统/技术与本系统的结合点(如「研究 perkeep 和 did space 的结合点」)。调研这一轮只产出 comment,不改 repo 代码;下一轮按 ratchet 转执行管道——见下「★ Research」(铁律 1 与铁律 10)。
  • Idea(想法类):issue 是一个内部提案/想法(如「提供一个 DID Space + MCP endpoint 给 loop 里的 agent」)——可能可行、可能不可行、可能太模糊、可能与现有设计矛盾。首轮是 clarify,不是执行;首轮产出 = 评估 comment + 澄清问题 + 行动声明,首轮不改 repo 代码、不开 spin-off;第二轮起按 ratchet 开工——见下「★ Idea」(铁律 2 与铁律 10)。

五类共用同一台引擎(读 → 对照现实 → 带证据落 comment),但投入档位和产出形态不同:doc-review 轻、doc-audit 按价值分档、system-audit 必须全量、research/idea 深调但首轮只落 comment(下面「省 token」那套不适用于 system-audit 和 research/idea 的调研深度)。research/idea 的「只落 comment」是首轮限定,不是永久状态——两者的铁律 10 都要求第二轮起转成动作,否则就是原地打转。

怎么判类型:issue 锚定单篇文档 = doc-review / doc-audit;issue 说「comprehensive audit」「review 整个 runtime / 跨平台是否一致」「需要完整 test run」「发现 gap/bug 开 issue」= system-audit;标题带 [research] / 正文是「研究一下 X 和我们的 Y」「调研 X 是否适合我们」= research;标题带 idea: / 正文自称「这是个 idea,首先需要分析可行性和价值」/ 是一段提案性质的构想(常附 Slack/讨论原文,无验收标准、无明确 spec)= idea。拿不准 audit 类就按 system-audit 的高标准做(宁可多投入,不可粗略);拿不准「指令还是想法」就按 idea 处理(先 clarify 的代价远低于把模糊想法当指令执行错方向)。

输出语言与写作规范(遵循 comment_language,信雅达)。 所有面向团队的产出——issue comment、spin-off issue 标题与正文、PR 描述正文、评估/验证报告——一律用 repo profile 的 comment_language 指定的正文语言(arc 默认:中文,团队阅读语言);代码标识符、路径、命令、path:line、测试输出保持原样(不翻译代码)。PR 与 commit 标题遵循 comment_language 的标题惯例——完整 Conventional Commits(type(scope): description,arc 默认标题全英文,冒号后的描述也用英文,不得混用);issue 标题(含 spin-off)随正文语言(arc 默认:中文)。追求信雅达,不堆砌:内容太多本身就是阅读负担——先给一句话结论,再给最少但足够的证据,不为显得全面而铺陈;每条断言配证据(文档 / 代码 path:line / 真实测试输出,UI 相关必附截图);长日志折叠进 <details>,不平铺刷屏。

Read the full file on GitHub · 693 lines

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. 6d ago First seen · 693 lines · 78 tokens per session scan A f80d6c0e0c80

Subscribe to this mod's changes

issue-review is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 24,246 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.