By armoriq
ArmorIQ intent-based security enforcement for GitHub Copilot CLI: pre-tool guardrails with intent verification, optional CSRG cryptographic proofs, and audit logging. Treat as a strong shell guardrail and audit layer — hooks fire on preToolUse / postToolUse / sessionStart / userPromptSubmitted via the official Copilot CLI plugin runtime.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
modeenforce = block on policy/intent failures (recommended). monitor = log only, never block.
${user_config.mode}api_keyYour ArmorIQ API key (get one at https://armoriq.ai). Leave blank to run in local-only mode without backend audit/intent.
${user_config.api_key}use_productionWhen true, talks to ArmorIQ production. When false, expects a local backend on 127.0.0.1.
${user_config.use_production}Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
intent_requiredWhen true, every tool invocation must be backed by a registered intent plan. Disable for advisory-only use.
${user_config.intent_required}crypto_policy_enabledBind policy rules to a Merkle tree so post-issuance tampering is detected.
${user_config.crypto_policy_enabled}
ArmorIQ intent-based security enforcement for GitHub Copilot CLI. Pre-tool guardrails, intent verification, optional cryptographic proofs, audit logging.
copilot plugin install armoriq/armorCopilot
The plugin runtime auto-discovers .claude-plugin/plugin.json inside plugins/armorcopilot/ and registers hooks + MCP servers.
After install, paste your ArmorIQ API key into the plugin's userConfig in Copilot CLI. Get one at https://armoriq.ai.
| Surface | Plugin behavior |
|---|---|
sessionStart / userPromptSubmitted | Injects directive telling Copilot to register its intent plan first |
preToolUse | Verifies the tool against the registered plan + policy. Blocks via {"permissionDecision":"deny",...} if out-of-plan or policy-denied |
postToolUse | Async audit row to ArmorIQ backend (fire-and-forget WAL) |
permissionRequest | Honors policy decisions before user is prompted |
| MCP tools | register_intent_plan, policy_update (natural-language), policy_read |
armorCopilot/
├── .claude-plugin/marketplace.json repo-level marketplace manifest
├── .agents/plugins/marketplace.json mirror (for non-Copilot agent runtimes)
├── plugins/armorcopilot/ the plugin itself
│ ├── .claude-plugin/plugin.json plugin manifest
│ ├── .mcp.json MCP server config
│ ├── hooks/hooks.json 5 hook events wired
│ ├── package.json npm deps
│ ├── README.md plugin-level docs
│ ├── assets/ logo + icons
│ └── scripts/ bootstrap + hook-router + policy-mcp + 12 lib modules
└── README.md this file
npx claudepluginhub armoriq/armorcopilot --plugin armorcopilotArmorIQ intent-based security enforcement for Claude Code: policy-based tool access control, intent verification, CSRG cryptographic proofs, and audit logging.
Build secure AI agents with ArmorIQ's Intent Assurance Plane (IAP). Provides cryptographic intent verification, prompt injection defense, policy enforcement, and audit trails for agentic systems — in Python and TypeScript.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.