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/NOMARJ/sigilWrote 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/nomarj/sigil/claude-code)<a href="https://agentmods.dev/plugins/nomarj/sigil/claude-code"><img src="https://agentmods.dev/badge/plugins/nomarj/sigil/claude-code/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/nomarj/sigil/claude-code"><img src="https://agentmods.dev/badge/plugins/nomarj/sigil/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sigil-security 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 26d 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
{
"name": "sigil-security",
"version": "1.1.0",
"description": "Automated security auditing CLI for AI agent code. Scan repos, packages, and agent tooling for malicious patterns with quarantine-first workflow.",
"author": {
"name": "NOMARK",
"email": "[email protected]",
"url": "https://github.com/NOMARJ/sigil"
},
"homepage": "https://github.com/NOMARJ/sigil",
"repository": "https://github.com/NOMARJ/sigil",
"license": "Apache-2.0",
"keywords": [
"security",
"scanner",
"ai",
"agent",
"supply-chain",
"malware",
"audit",
"quarantine",
"mcp",
"threat-intelligence"
],
"skills": "./skills/",
"agents": "./agents/",
"hooks": "./hooks/hooks.json",
"mcpServers": {
"sigil": {
"command": "sigil",
"args": [
"mcp"
]
}
}
}
What it installs
The manifest is a name and a version. 6 skills, 2 agents, 2 hooks travel with it, and installing the plugin installs all of them — 484 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill generate-policy A 17 tokens
- Skill scan-repo A 119 tokens
- Skill fix-finding A 17 tokens
- Skill scan-package A 114 tokens
- Skill scan-file A 108 tokens
- Skill review-quarantine A 33 tokens
- Agent quarantine-manager A 33 tokens
- Agent security-auditor A 43 tokens
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
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.
- 26d ago Changed · -1 lines a9a0c602f604
- 1mo ago First seen · 38 lines scan A d8a3aa9efeaf
sigil-security is a plugin published in the GitHub repository NOMARJ/sigil (6 stars, last pushed 12d 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 2026-09-04.
Other plugins, from other repositories
agents-specialized-domains
Domain-specific expert agents for validation, knowledge-graph, and other specialized tasks.
budgetclaw
Zero-key Claude Code cost tracking, per project and per branch. Budget caps with SIGTERM enforcement, reads your local /.claude session logs, and syncs to a hosted team dashboard (Goei).
sandy-cli
Sandy: sandboxed TypeScript execution for AWS queries via the sandy CLI.
webview-devtools-mcp
DevTools for any WebView — no remote-debugging port required. Works in Safari/iOS WebView/Lark Web App and more.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.