What is concept-guardrails?

A runtime that injects declared module boundaries into an agent's context when the agent edits nearby files. A module boundary describes which parts of a codebase belong together and may interact.

Use it in projects that keep architecture or concept specifications near implementation files and want those boundaries available during edits.

It helps prevent edits from crossing architectural boundaries without the agent seeing the relevant rules. The input does not describe its full runtime behavior beyond this context injection.

concept-guardrails — Plugin for Claude Code by ontology-of-everything

Install

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.

Clone the repo

git clone --depth 1 https://github.com/ontology-of-everything/SemanticSkills

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/ontology-of-everything/semanticskills/runtime/github.svg)](https://agentmods.dev/plugins/ontology-of-everything/semanticskills/runtime)

Your own site

<a href="https://agentmods.dev/plugins/ontology-of-everything/semanticskills/runtime"><img src="https://agentmods.dev/badge/plugins/ontology-of-everything/semanticskills/runtime/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/ontology-of-everything/semanticskills/runtime"><img src="https://agentmods.dev/badge/plugins/ontology-of-everything/semanticskills/runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

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 2mo 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.

skills/concept-guardrails/runtime/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "concept-guardrails",
  "description": "wyx 中文版运行时 — 当 agent 编辑规格附近的文件时，自动把已声明的模块边界注入上下文",
  "version": "0.26.0",
  "author": {
    "name": "jlifyio"
  },
  "homepage": "https://github.com/jlifyio/wyx",
  "repository": "https://github.com/jlifyio/wyx",
  "license": "MIT",
  "keywords": [
    "architecture",
    "guardrails",
    "module-boundaries",
    "context-injection",
    "hooks",
    "concept-spec",
    "drift-detection",
    "claude-code"
  ]
}

Contents

What it installs

The manifest is a name and a version. 3 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.

Changes

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.

2mo ago Changed 4a65e06c2fc9
2mo ago First seen · 22 lines scan A 2a1f6c52f184

Subscribe to this mod's changes

concept-guardrails is a plugin published in the GitHub repository ontology-of-everything/SemanticSkills (8 stars, last pushed 2mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.

Building agents Claude Code agent-skills claude-code-skill claude-skills huawei-cloud semantic-skills

concept-guardrails next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
concept-guardrailsontology-of-everything/SemanticSkills	Plugin	8	2mo ago	Apache-2.0	A	—	Claude Code
polish-open-source-proseting-hong-shieh/polish-open-source-prose	Plugin	8	15d ago	Apache-2.0	A	—	Claude Code
aident-loadoutAident-AI/aident-skill	Plugin	7	29d ago	MIT	A	—	Cursor
diagrammerAnish-Reddy-K/diagrammer	Plugin	3	5d ago	MIT	A	—	Claude Code
guardrailsadewale/guardrails-skill	Plugin	2	6d ago	MIT	A	—	Claude Code
codex-councilehzawad/codex-council	Plugin	2	19d ago	MIT	A	—	Claude Code
marcoraccromp/marcora-mcp	Plugin	0	yesterday	MIT	A	—	Claude Code