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 zuoyebang/aiweave --skill io-reviewgit clone --depth 1 https://github.com/zuoyebang/aiweaveWrote 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/zuoyebang/aiweave/io-review)<a href="https://agentmods.dev/skills/zuoyebang/aiweave/io-review"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/io-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.
<a href="https://agentmods.dev/skills/zuoyebang/aiweave/io-review"><img src="https://agentmods.dev/badge/skills/zuoyebang/aiweave/io-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00120 | $0.02415 |
| Opus 5 | $0.00060 | $0.01208 |
| Sonnet 5 | $0.00024 | $0.00483 |
| Haiku 4.5 | $0.00012 | $0.00242 |
Grade A, and why
io-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
审计代码的 IO 铁律与聚合并行约束。范围:$ARGUMENTS(空则审计 git diff main..HEAD)。
公共步骤模板见 skills-spec/01_skill_authoring_guide.md §A-§E。本 Skill 不生成代码,故第 5 步测试同步不适用。
本 Skill 是审计类 Skill(审计类第 6 个)。"代码 ↔ IO 铁律"一致性审计。
第 0 步:🚫 模块 + 启用状态检查
- 读
BUILD_STATUS.md§0 —— 命中 🚫 模块的文件跳过审计 - 读
INDEX.md§0 AIWeave 采纳进度 —— 如docs-spec/25_io_aggregation标 ⬜ 未启用 → 跳过本 Skill,提示"本工程未启用 25,跳过 io-review"
第 1 步:读取约束源
读以下文件(按顺序):
docs/architecture/io_contract.md—— §1 IO 往返预算 + §2 三条铁律 + §2.1/§2.2 豁免登记 + §3 聚合器模式 + §4 并行原语 + §5 聚合约束docs/architecture/ai_dev_guide.md§10.7 —— grep 锚 rule-id 索引(R-IO-*)docs/architecture/performance_contract.md§4 —— 单次延迟预算(避免与 25 双源真相)docs/BUILD_STATUS.md§11 —— 约束清单状态轨道
第 2 步:扫描代码范围
按 $ARGUMENTS 确定扫描范围:
- 空 / 当前 PR:
git diff main..HEAD --name-only取新增/修改的 .go 文件 loop-only:仅取含for/range的文件- 文件路径:直接以该路径为范围
第 3 步:依赖链分析(铁律二的关键)
对每段"连续多次读"的代码,判定查询间是否存在真实数据依赖:
- 后一次查询的入参取自前一次查询的结果(外键 / 返回字段)→ 真实依赖,串行合法
- 后一次查询入参与前一次结果无关 → 伪串行,命中铁律二
依赖链是 io-review 区分"违规"与"必要串行"的核心,不可机械只看"连续 await"。
第 4 步:grep 锚检查
grep 锚定位为"信号级"非"判定级"。所有命中标 🟡 待复核;最终判定由人工 reviewer 决定。 已在 io_contract.md §2.1 / §2.2 豁免登记表登记的位置 → 跳过;命中但未登记 → 标记。
检查 R-IO-N-PLUS-1:循环内单条查询(铁律一 / N+1)
范围:所有路径
grep 模式:'for [^{]*\{[\s\S]{0,300}?\.(Find|First|Take|Get|Query|Load|HGet|MGet?|Call)\('
误报排除:
- 调用的已是批量 API(FindByIDs / In(...) / Pluck / Scan / 批量 MGET)
- 循环次数硬编码 ≤ {Loop-safe-N}(如 < 5)
- io_contract.md §2.1 已登记豁免 / 行末 // aiweave:allow=R-IO-N-PLUS-1
判定:命中且未豁免 → 🔴 严重(违反铁律一)
检查 R-IO-SERIAL-ORCH:独立串行查询编排(铁律二)
范围:所有路径
信号:连续 ≥ 2 个 {读操作} 各自 if err != nil 串行展开
判定(结合第 3 步依赖链分析):
- 无真实依赖(伪串行)→ 🔴 严重(违反铁律二),建议改聚合器 / 扇出并行
- 有真实依赖 → 跳过(合法),可提示"是否可预取合并"
误报排除:
- io_contract.md §2.2 已登记依赖链豁免 / 行末 // aiweave:allow=R-IO-SERIAL-ORCH
检查 R-IO-LOOP-WRITE:循环内单条写
范围:所有路径
grep 模式:'for [^{]*\{[\s\S]{0,300}?\.(Create|Save|Insert|Update|HSet|Set|Exec)\('
误报排除:
- 批量写 / pipeline(CreateInBatches / pipeline.Exec)
- 循环次数硬编码 ≤ {Loop-safe-N}
- 行末 // aiweave:allow=R-IO-LOOP-WRITE
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.
- 10d ago First seen · 167 lines · 120 tokens per session scan A 31890be921ef
io-review is a skill published in the GitHub repository zuoyebang/aiweave (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 120 tokens to every session and 2,415 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
graphql-contract-review
Review a GraphQL schema and a Backend-for-Frontend (BFF) contract BEFORE implementation, against a GraphQL-specific checklist: schema shape and nullability (null-bubbling), errors-as-data unions, N+1 and DataLoader, query cost and depth limits, cursor-connection pagination, federation entity ownership, breaking-change…
code-reviewer-nodejs
Node.js backend code review skill. Focused on systematic review of Node.js runtime characteristics, covering async patterns, event loop, stream processing, middleware design, process management, error handling, and security. Use this skill when reviewing Node.js backend code (Express/Koa/Fastify routes, middleware…
sdd-apply
Skill "sdd-apply" from Gentleman-Programming/gentle-ai, covering execution role, language domain contract, purpose, what you receive and execution and persistence contract.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
mold
Turn a high-leverage design decision into an approved spec through grounded dialogue. Use it when a leverage trigger fires (auth, irreversible effects, concurrency, contracts, destructive ops, a new slice, a cross-slice dependency, an invariant gap) or when the user asks for a spec or design. Typical phrases include…