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/lihaozheCharlie/TwhWikinpx agentmods add skills/lihaozhecharlie/twhwiki/quality-gateWrote 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/lihaozhecharlie/twhwiki/quality-gate)<a href="https://agentmods.dev/skills/lihaozhecharlie/twhwiki/quality-gate"><img src="https://agentmods.dev/badge/skills/lihaozhecharlie/twhwiki/quality-gate/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/lihaozhecharlie/twhwiki/quality-gate"><img src="https://agentmods.dev/badge/skills/lihaozhecharlie/twhwiki/quality-gate.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 | $0.00049 | $0.00805 |
| Opus 5 | $0.00024 | $0.00402 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
common-quality-gate 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 11d 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.
What it actually says
通用：质量门
在获授权的 Markdown 或 Skill 修改后、宣布构建完成前，或用户明确要求 wiki 健康检查时使用。验证不会扩大任务的写入范围。
先读
- 归档或移动页面时读取
skills/common/filing-rules.md。 - 读取被检查页面所属领域的负责 Skill。
- 检查解释性查询或构建时读取
skills/common/reasoning-lenses/SKILL.md，验证人物视角没有污染中性证据或越过领域边界。
内容检查
- 每个非显然判断都能追溯到原始笔记、已标注的对话材料或既有综合页。推断标为
推断或待查。 - 模板只提供结构，不构成生成占位内容的许可。省略无证据支持的项目、表格行、引文和章节。
- 按主要对象归档，并维护有用的双向导航。
- 不要在不同章节机械重复同一证据。
- 使用与领域匹配的语言；人物、城市、系统、状态、事件和人生阶段需要不同类型的判断。
- 当措辞本身是可沉淀证据时，保留用户准确原话。
- 优先做局部、精确的更新，避免宽泛重写。
- 使用共享人物视角时，人物原则不构成证据；日期、原句、实体、金额、事件顺序和可观察状态必须与中性证据卡一致。
- 主视角只负责解释，页面结构仍由领域 Skill 负责；辅助视角不能接管中心、结构和结尾。
- 重大重解释应在日志记录主视角、辅助任务和重跑范围。新增人物必须由动态发现脚本自动出现，下游 Skill 不得复制人物名单。
验证模式
只读维护
用户要求检查健康状况但未授权修复时，运行：
python3 tools/validate_wiki_links.py
python3 tools/validate_skill_system.py
获授权的 Markdown 修改后
在仓库根目录运行：
python3 tools/update_obsidian_tags.py
python3 tools/update_obsidian_tags.py
python3 tools/validate_wiki_links.py
第二次标签运行必须报告 updated=0；链接验证必须报告 missing=0 ambiguous=0。
获授权的 Skill 或配套工具修改后
还要运行：
python3 tools/validate_skill_system.py
可用时，对每个规范 Skill 运行系统自带的快速验证器。
需要人工复核的情况
修改格式错误的 YAML、已改名的原始笔记来源、歧义别名、实体数量的意外变化，以及需要用户判断的证据冲突前，先人工复核。
完成审计
- 把目标重述为具体交付物。
- 将每个请求类别映射到已修改或有意保持不变的产物。
- 检查代表性文件内容和验证器实际输出。
- 报告跳过的检查和未解决风险。
- 只要请求中的要求仍不确定，就继续处理。
验证器通过只能证明它覆盖的约束成立，不能证明用户要求的语义工作已经完成。
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 · 75 lines · 49 tokens per session scan A 5fdcbb129862
common-quality-gate is a skill published in the GitHub repository lihaozheCharlie/TwhWiki (24 stars, last pushed 6d ago), licensed MIT. It adds 49 tokens to every session and 805 once invoked, about $0.0002 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…