A Claude Code security plugin that checks tool access against policies and verifies the intended action. It can also create cryptographic proofs and audit logs, with local-only operation available when no API key is provided.

It is used to enforce access policies, verify agent intent, produce CSRG proofs, and audit Claude Code tool use.

It helps control what the coding agent is allowed to do and records security-related decisions or activity.

armorclaude — Plugin for Claude Code by armoriq

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/armoriq/armorClaude

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/armoriq/armorclaude/armorclaude/github.svg)](https://agentmods.dev/plugins/armoriq/armorclaude/armorclaude)

Your own site

<a href="https://agentmods.dev/plugins/armoriq/armorclaude/armorclaude"><img src="https://agentmods.dev/badge/plugins/armoriq/armorclaude/armorclaude/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/armoriq/armorclaude/armorclaude"><img src="https://agentmods.dev/badge/plugins/armoriq/armorclaude/armorclaude.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 The manifest loads nothing itself; its 1 command, 8 hooks, 1 MCP server cost 0 tokens a session between them.

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

armorclaude 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.

.claude-plugin/plugin.json · 30 lines

What it actually says

{
  "name": "armorclaude",
  "version": "0.2.9",
  "description": "ArmorIQ intent-based security enforcement for Claude Code: policy-based tool access control, intent verification, CSRG cryptographic proofs, and audit logging.",
  "author": { "name": "ArmorIQ", "email": "[email protected]" },
  "homepage": "https://armoriq.ai/tools/armorclaude",
  "privacyPolicy": "https://armoriq.ai/privacy-policy",
  "repository": "https://github.com/armoriq/armorClaude",
  "license": "MIT",
  "keywords": ["security", "policy", "audit", "intent", "armoriq", "mcp"],
  "userConfig": {
    "api_key": {
      "type": "string",
      "title": "ArmorIQ API Key",
      "description": "Your ArmorIQ API key (get one at https://armoriq.ai). Leave blank to run in local-only mode without backend audit/intent.",
      "sensitive": true
    },
    "default_template": {
      "type": "string",
      "title": "Default policy template",
      "description": "Optional. One of: all-allow, strict-read-only, balanced, lockdown, architect, quality-guardian, velocity-machine, night-owl. On first run it is proposed (staged for your confirmation — never applied automatically). Leave blank to be shown the template picker instead."
    },
    "disable_observability": {
      "type": "boolean",
      "title": "Disable observability",
      "description": "Observability (execution traces sent to your ArmorIQ dashboard) is enabled by default. Set to true to turn it off."
    }
  }
}

Contents

What it installs

The manifest is a name and a version. 1 command, 8 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 0 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json 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.

marketplace.json 1.7 KB

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 First seen · 30 lines scan A 86b621ae9717

Subscribe to this mod's changes

armorclaude is a plugin published in the GitHub repository armoriq/armorClaude (47 stars, last pushed yesterday), licensed MIT. 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 2026-08-30.