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-guardrailsgit 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-guardrails)<a href="https://agentmods.dev/skills/ontology-of-everything/semanticskills/concept-guardrails"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/concept-guardrails/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-guardrails"><img src="https://agentmods.dev/badge/skills/ontology-of-everything/semanticskills/concept-guardrails.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 | $0.00056 | $0.01278 |
| Opus 5 | $0.00028 | $0.00639 |
| Sonnet 5 | $0.00011 | $0.00256 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
concept-guardrails 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
概念护栏
把模块边界声明为与代码共存的规格，核对规格与代码，派生架构地图。流程源自 jlifyio/wyx v0.26.0（MIT，见 LICENSE.upstream），记法改为本仓 Jackson 方言，runtime/ 脚本保留上游版本。仅在用户显式调用 $concept-guardrails 时运行。
选择模式
调用形式 $concept-guardrails <模式> [路径或描述]。
| 模式 | 任务与产出 | 执行前读 |
|---|---|---|
audit |
覆盖审计：列已有规格、候选与按依赖排序的命令计划；只读 | audit.md |
concept |
回填 / 新建 / 发现概念候选，产出 CONCEPT.md |
concept.md |
drift |
对照三类规格与代码，输出漂移报告；只读 | drift-detection.md |
pipeline |
回填 / 新建 / 发现数据管道，产出 PIPELINE.md |
pipeline.md |
sync |
回填 / 新建 / 发现跨概念协调，产出 SYNCS.md |
sync.md |
map |
从全部规格派生 ARCHITECTURE.md |
map.md |
参数路由：路径 → 回填；描述 → 新建；无参数 → 该模式的发现子模式（只列候选，不写规格）。未指定模式、或项目尚无任何规格时走 audit。需求拆分用 concept-design；已确认模型批量转录用 concept-prd；全面独立性与组合审计用 concept-audit。伴生技能未安装时报告缺口与交接内容，不假定其文件可读。
共用执行约定
- 先读已有规格、实现与项目约定。回填描述现状，并单列缺陷；更新既有模块时先改规格再改实现。
- 写规格前呈现草案或 diff。用户已授权创建、更新或修复时直接完成；只有模型取舍未定或写入超出授权时才请求确认。只读审计不写历史文件，也不自动修复。
CONCEPT.md放所属模块，PIPELINE.md与所属概念共目录；跨模块管道放组合层。避免根目录概念规格成为无关模块的兜底边界。- 每个概念一份权威规格；每个 syncs 包一份
SYNCS.md，按 flow 归组、保持规则可追踪。规格变化且已有地图时，指出需运行map；已要求更新地图则一并完成。
记法
只消费和产出本仓 Jackson 方言，与 concept-design / concept-prd 一致：
| 内容 | 记法 |
|---|---|
| 概念 | purpose / principle / state / actions，可选 notes；类型参数抽象上下文，四节不依赖其他概念定义 |
| 组合 | app / include / sync；when / where / then，// flow: 分组；跨概念边只在 SYNCS.md |
| 管道 | purpose / sources / stages / outputs / invariants / triggers / data boundary |
| 图 | 从 sync 块派生同步图；产品依赖以总体 PRD 为准，不从 sync 推导 |
principle 与 operational principle 是同一术语；新写用前者，读取兼容后者。所谓"零点名"检查的是语义依赖：局部类型参数恰好名为 User 不算引用 User 概念。
不消费 wyx 原生格式。遇到 ## interactions / ## dependencies / ## known coupling / ## dispatching / ## coordination graph / ## sync: 等旧段落，标为待迁移并报告；用户授权迁移时按本记法重写整份文档族（CONCEPT、SYNCS、PIPELINE 一起），逐条保留触发、绑定、效果与错误路径，不能只改标题或混写两种格式。
完成条件
What ships with it
14 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.
- agents/openai.yaml 386 B
- LICENSE.upstream 1.0 KB
- references/audit.md 2.8 KB
- references/concept.md 6.6 KB
- references/drift-detection.md 6.3 KB
- references/hooks-runtime.md 2.8 KB
- references/map.md 3.7 KB
- references/pipeline.md 4.1 KB
- references/sync.md 5.2 KB
- runtime/.claude-plugin/plugin.json 539 B
- runtime/hooks/hooks.json 970 B
- runtime/scripts/drift-context.sh 10 KB runs code
- runtime/scripts/post-check.sh 4.4 KB runs code
- runtime/scripts/session-start.sh 14 KB runs code
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.
- yesterday Changed · +4 lines · +11 tokens per session c2a440371322
- 4d ago First seen · 54 lines · 45 tokens per session scan A 4587f8bb009e
concept-guardrails is a skill published in the GitHub repository ontology-of-everything/SemanticSkills (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,278 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 2026-09-08.
Other skills, from other repositories
ship-it-or-fix-it
Oracle-frozen Builder and independent-Judge convergence cycle. Load ONLY when the operator explicitly sets Governance Dial G2 for the task, or explicitly names this skill or an active work unit already running it. Never auto-activate on task class, such as security, auth, or payments. If a task seems to warrant G2 and…
test-verification
Requires behavioral, failure-path, and durable-seam evidence for tests and review. Use when writing tests, reviewing test coverage, assessing behavioral test quality, or accepting high-risk behavior on test evidence.
gemini-cli-agent
Gemini CLI sub-agent system for cost-efficient analysis using the gemini binary. Use when piping large contexts to cheaper Google Gemini models (gemini-3-flash-preview, gemini-3.1-pro-preview) for security audits, architecture reviews, or QA analysis. For frontier models (Gemini 3.8 Flash and above), use agy-cli-agent…
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…
security-audit
Conduct a security-led audit of code, systems, APIs, infrastructure, dependencies, and AI workflows with threat modeling and exploitability-backed remediation. Use when security risk is the primary concern. Do not use for a generic code review, database design, or non-security debugging.
code-review
Review a specific implementation, change set, PR, function, or service for broad correctness and production-readiness findings. Use when code-quality is the primary concern. Do not use when security, performance, architecture, dependencies, or tests are the exclusive requested discipline.