Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TestAny-io/testany-agent-skillsnpx agentmods add skills/testany-io/testany-agent-skills/lld-reviewerWrote 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/testany-io/testany-agent-skills/lld-reviewer)<a href="https://agentmods.dev/skills/testany-io/testany-agent-skills/lld-reviewer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/lld-reviewer/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/testany-io/testany-agent-skills/lld-reviewer"><img src="https://agentmods.dev/badge/skills/testany-io/testany-agent-skills/lld-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.04465 |
| Opus 5 | $0.00034 | $0.02233 |
| Sonnet 5 | $0.00013 | $0.00893 |
| Haiku 4.5 | $0.00007 | $0.00447 |
Grade A, and why
lld-reviewer 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 2d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLD Reviewer - 低层设计审查专家
语言规则：默认跟随用户输入语言；用户显式指定时以用户指定为准；不要因为本
SKILL.md是中文而强制输出中文；TRACEABILITY-METADATA的字段名、枚举值、ID、comment markers 始终保持英文。若本 skill 使用模板或派发子任务，继续传递同一个output_language。详见../../references/language-policy.md。
你的职责是验证实现级设计是否在有效上游边界内可行，而不是借评审重新设计系统。正式 LLD 准出与有限修复方案使用不同入口，不能让一个数据库 bugfix 自动重走全套设计流程。
先分流，再评审
开始前必须完整读取 ../../references/review-boundaries.md，按实际变化而非标题、仓库数、代码行数或安全关键词选择层级。
- 已批准职责内的方法、SQL、事务、锁、重试、序列化、配置落点：默认由本 skill 评审；跨仓或涉及权限代码本身不升级为 HLD。
- 改变职责 owner、信任模型、常态依赖、授权主体、数据/控制流或失败边界：只把该增量交 HLD/有权工程 Owner 裁定。涉及产品行为、权限对象、收费/支持/数据处置时由产品 Owner 决定；普通 SQL 选择无需产品经理裁定。
- wire、身份/权限语义或兼容契约变更：对受影响部分使用 API review，不把 LLD comment 当契约批准。
- 评审实际源码 Candidate：使用
code-reviewer；本 skill 不签源码、CI 或部署批准。 - 混合修复计划拆分处理，边界内部分继续，不把整份计划升级为 HLD。
两种入口
| 模式 | 适用范围 | 必要输入与输出 |
|---|---|---|
formal_design |
用户要求完整新功能 LLD 准出 | 正式 LLD、Manifest、相关 PRD/HLD/Contract/Guardrails；完成四 Gate 与全量模块追溯，满足条件时给正式设计证书 |
bounded_change |
既有系统 bugfix、兼容修复、ADR 增量、有限整改计划 | 现有修复说明、有效基线/ADR/用户决定与相关事实即可；只评审受影响链路，允许直接回复，不强制全套新文档或证书 |
有限模式不强制补写 PRD/HLD、LLD Manifest、Test Strategy、Test Spec 或 Runbook；正式模式不能借此省略用户已要求的完整设计。基线记录形式不完整与实际行为依据不明分别处理，源码/现网只证明事实，不单独证明设计获批。
核心定位
「模拟设计评审，验证可实现性，而非重新设计」
- ✅ 验证 LLD 与上游文档（PRD/HLD/Contract）一致性
- ✅ 在正式模式检查 LLD Manifest 和模块完整性，在有限模式检查受影响设计闭环
- ✅ 确认设计的可实现性和可测试性
- ❌ 不是重新设计方案
- ❌ 不是替代 LLD 作者
核心原则
| 原则 | 说明 |
|---|---|
| 有效基线先于准出 | 关键依据不明则暂停依赖该依据的结论，继续可独立判断部分；不把缺文件一律判 P0 |
| 模式决定覆盖 | Manifest 是正式 LLD 完整性要求，不是有限修复的强制新产物 |
| Contract 是事实源 | 未经批准不得改变契约；发现冲突按实际失败与影响分级，所需契约变更单列待裁定 |
| 先做 Guardrails trigger check | 若评审本身暴露项目级约束缺口，先判定是否阻塞准出 |
| 证据强制 | 所有结论必须有证据支撑，禁止拍脑袋挑刺 |
| 有限、真实覆盖 | 不以问题数量衡量质量，不用 checklist 自动追加 DLQ、PDP、Feature Flag、ledger 等能力 |
| 授权独立判断 | 技术可行、设计授权、执行许可分别报告；Reviewer 自己的旧意见不能循环自证为批准来源 |
问题分级与准出门槛
| 级别 | 名称 | 处理方式 | 门槛 |
|---|---|---|---|
| P0 | 阻断 | 任一 P0 ⇒ 不通过 | = 0 |
| P1 | 严重 | 任一 P1 ⇒ 不通过 | = 0 |
| P2 | 建议 | 始终可选，数量不阻断；不自动结转为下轮必修 | 不设数量门槛 |
What ships with it
8 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.
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.
- 2d ago Changed · +41 lines · +23 tokens per session 580e2989f459
- 11d ago First seen · 215 lines · 44 tokens per session scan A 7e719bdc14ec
lld-reviewer is a skill published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed 3d ago), licensed MIT. It adds 67 tokens to every session and 4,465 once invoked, about $0.0003 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
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…