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.
git clone --depth 1 https://github.com/n24q02m/claude-pluginsWrote 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/plugins/n24q02m/claude-plugins/crg)<a href="https://agentmods.dev/plugins/n24q02m/claude-plugins/crg"><img src="https://agentmods.dev/badge/plugins/n24q02m/claude-plugins/crg/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/plugins/n24q02m/claude-plugins/crg"><img src="https://agentmods.dev/badge/plugins/n24q02m/claude-plugins/crg.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
crg 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 4d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "crg",
"description": "Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.",
"version": "3.31.0",
"userConfig": {
"EMBEDDING_MODELS": {
"type": "string",
"title": "Embedding model selection (optional)",
"description": "CSV 'provider/model,...'; selects the first entry without runtime fallback. Empty = local fastretrieval registry. Example: cohere/embed-v4.0 (paid; exact 1024 dimensions).",
"required": false
},
"LOCAL_EMBEDDING_MODEL": {
"type": "string",
"title": "Local embedding model (optional)",
"description": "Built-in fastretrieval model ID, or a local directory containing fastretrieval-manifest.json. External IDs require LOCAL_EMBEDDING_DIM.",
"required": false
},
"LOCAL_RERANK_MODEL": {
"type": "string",
"title": "Local reranker model (optional)",
"description": "Fastretrieval TextCrossEncoder model ID; empty = reranking disabled.",
"required": false
},
"LOCAL_EMBEDDING_DIM": {
"type": "number",
"title": "Local embedding dimension",
"description": "Required output dimension for an external LOCAL_EMBEDDING_MODEL ID without a manifest.",
"required": false
},
"LOCAL_EMBEDDING_MODEL_FILE": {
"type": "string",
"title": "Local embedding model file",
"description": "ONNX file path inside a manifest-backed local artifact directory.",
"required": false
},
"LOCAL_EMBEDDING_POOLING": {
"type": "string",
"title": "Local embedding pooling",
"description": "Explicit pooling for an external ID without a manifest: CLS, MEAN, LAST_TOKEN, or DISABLED.",
"required": false
},
"LOCAL_EMBEDDING_NORMALIZE": {
"type": "boolean",
"title": "Normalize local embeddings",
"description": "Apply explicit L2 normalization for an external ID without a manifest.",
"required": false
},
"HUWhat it installs
The manifest is a name and a version. 6 skills, 3 hooks travel with it, and installing the plugin installs all of them — 184 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 4d ago First seen · 91 lines scan A 0a3c69d76c13
crg is a plugin published in the GitHub repository n24q02m/claude-plugins (4 stars, last pushed today), 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 2026-11-02.
crg compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| crgn24q02m/claude-plugins | Plugin | 4 | today | Apache-2.0 | A | — | Claude Code |
| code-qualityFlorianBruniaux/claude-code-plugins | Plugin | 44 | 2d ago | MIT | A | — | Claude Code |
| pr-workflowFlorianBruniaux/claude-code-plugins | Plugin | 44 | 2d ago | MIT | A | — | Claude Code |
| code-contribution-analysisshopwareLabs/ai-coding-tools | Plugin | 45 | 10d ago | MIT | A | — | Claude Code |
| advandisab/swe-marketplace | Plugin | 21 | yesterday | MIT | A | — | Claude Code |
| reviewumputun/cc-thingz | Plugin | 493 | 3d ago | MIT | A | — | Claude Code |
| atc-skillsbrycewang-stanford/Awesome-Journal-Skills | Plugin | 1.4k | 1mo ago | MIT | A | — | Claude Code |