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.
npx skills add ArcBlock/agent-skills --skill issue-reviewgit clone --depth 1 https://github.com/ArcBlock/agent-skillsWrote 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.
[](https://agentmods.dev/skills/arcblock/agent-skills/issue-review)<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>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 | $0.00078 | $0.24246 |
| Opus 5 | $0.00039 | $0.12123 |
| Sonnet 5 | $0.00016 | $0.04849 |
| Haiku 4.5 | $0.00008 | $0.02425 |
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** 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.mdfirst. This skill is repo-agnostic; arc is the reference implementation. Use the profile'srepo_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。
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.
- 6d ago First seen · 693 lines · 78 tokens per session scan A f80d6c0e0c80
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.