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 ontology-of-everything/SemanticSkills --skill concept-auditgit clone --depth 1 https://github.com/ontology-of-everything/SemanticSkillsWrote 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/ontology-of-everything/semanticskills/concept-audit)<a href="https://agentmods.dev/skills/ontology-of-everything/semanticskills/concept-audit"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/concept-audit/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/ontology-of-everything/semanticskills/concept-audit"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/concept-audit.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 | $0.00041 | $0.00845 |
| Opus 5 | $0.00020 | $0.00423 |
| Sonnet 5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
concept-audit 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 today.
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
概念审计
仅在用户显式调用 $concept-audit 时运行。只读对照概念模型与代码，回答独立性和组合正确性，并检查漂移、判据与产品子集。输出带证据、影响与修复路由的报告；不修改文件。无规格时只审可验证的代码性质，注明不能判断的契约。
执行
- 范围：查全部 CONCEPT/SYNCS、总体 PRD 及其暂存规格链接，读取当前实现与测试。记录版本、方言、覆盖与未核实部分。
- 漂移：读 drift-checklist.md，逐规格/实现对账，含 schema、动作/query 签名与错误 case。规格多时按该文分批扫描。
- 独立性：逐概念核对互引（包括公开 API）、共享可变状态、私有实现访问、传输类型污染及定义依赖。局部类型参数同名不算引用另一概念。
- 组合：读 composition-checklist.md，检查完成事件、绑定、flow 合取/隔离、失败、重放、循环与用户联动。
- 判据：以单一目的、完整行为、独立性、熟悉性检查 conflation/fragmentation；新颖与基础设施身份本身不是缺陷，先明确使用者（含 API 程序员）与价值。
- 依赖/子集：分别核验 PRD 产品依赖与代码约束；用具体合理子集判断是否被不当耦合阻断，并检查其剩余 sync/入口与构建支持。不能要求产品图与代码图同构。
- 聚合：跨规格核对 include、动作/query、参数、输出与图。合并同一根因，保留受影响位置；未执行类别不算通过。
报告
# 审计报告 <日期>
范围：<规格/代码版本、未核实与跳过原因>
Summary：<覆盖数量、发现数、严重度分布>
| 维度/发现 | 位置 | 当前证据及影响 | 严重度 | 修复路由 |
| --- | --- | --- | --- | --- |
## 独立性与组合覆盖
<每个概念、入口/规则组的结论或未核实项>
## 跨规格与系统性模式
<合并根因并列受影响路径>
## 修复顺序
<模型 → 文档 → 代码，按实际根因决定>
严重度按漂移参考中的影响规则校准；规格沉默不等于禁止，新增遗漏与矛盾分开。没有当前证据不报 Medium 以上；只有完整核验后才断言不存在。每条发现一个当前修复目标：模型 → concept-design；文档 → concept-prd；代码 → concept-implementation。存在连续修复阶段时列依赖顺序，不让路由替代根因判断。
交付须覆盖五维、逐概念独立性与逐入口/规则组组合结论，或注明不足。欠/过同步附用户场景；报告全程只读。核验判据出处时读 sources.md；安装包不依赖伴生技能文件才能审计。
What ships with it
4 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.
- today Changed · -12 tokens per session 701dfec02259
- 3d ago First seen · 46 lines · 53 tokens per session scan A 8df4a2e79003
concept-audit is a skill published in the GitHub repository ontology-of-everything/SemanticSkills (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 845 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 2026-09-08.
Other skills, from other repositories
vet
Thorough codebase investigation that finds and fixes real problems. Maps architecture, scans every layer (structural, correctness, security, reliability, performance, hygiene), prioritized report with evidence, fix plan, executes collaboratively. A senior engineer doing a full review with authority to fix. Use when…
code-quality-loop
Iterative review-fix loop: reviews code, auto-fixes issues, repeats until clean or stuck. Finishes with reorganize (for large changes), simplify + test consolidation.
unused-code-audit
A code-audit skill for proving whether files, exports, functions, components, types, or helpers have real users before removal.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".