vaaraio

vaaraio/vaara

Plugin Claude Code

Vaara runtime tool-call governance plugins for Claude Code.

vaaraio/vaara

Instructions file CodexOpenCode

AGENTS.md instructions for vaaraio/vaara, covering agents.md, what this is, integrating vaara into an application, working on this repository and conventions and constraints.

vaaraio/vaara

Skill Claude CodeCodex

Put an EU AI Act Article 14 human-oversight checkpoint and an Article 12 auditable record in front of a high-risk tool call. Use before an agent runs a consequential or irreversible action (writing to a clinical/genomic database, submitting a record to a regulator, moving money, deleting data, anything a human should…

vaaraio/vaara

Plugin Claude Code

Accountable autonomy for Claude Code. PreToolUse runs a two-layer check on Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and MCP calls (regex deny patterns on shell, web and file mutation; conformal risk scorer on MCP). PostToolUse writes a hash-chained SQLite audit record across the same set.

vaaraio/vaara

Command

Friendly settings for Vaara governance. Choose protection level, watch vs protect mode, and notifications, in plain language.

vaaraio/vaara

Command

Print Vaara governance stats from the Claude Code audit trail (records, event types, top tools, last 5 actions).

vaaraio/vaara

Hook

Runs when a session starts, executing run.sh via sh. From vaaraio/vaara.

vaaraio/vaara

Hook

Runs before the agent uses a tool for Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and mcp__.* tool calls, executing run.sh via sh. From vaaraio/vaara.

vaaraio/vaara

Hook

Runs after a tool call finishes for Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and mcp__.* tool calls, executing run.sh via sh. From vaaraio/vaara.

vaaraio/vaara

MCP server Claude CodeCodexCursor +2

Accountable Autonomy for AI agents under the EU AI Act: policy-gated tool calls, hash-chained tamper-evident audit trails with external time anchoring, and independently verifiable attestation plus execution receipts per MCP tool call. Runs locally from the vaara Python package.

vaaraio/vaara

MCP server Claude CodeCodexCursor +2

Accountable Autonomy for AI agents under the EU AI Act: policy-gated tool calls, hash-chained tamper-evident audit trails with external time anchoring, and independently verifiable attestation plus execution receipts per MCP tool call. Runs locally from the vaara Python package. Needs 2 environment variables to run.