Assemble the evidence bundle, sampling and workpapers an auditor asks for — for one framework over one audit window — from Noru's graph plus the local files an integration cannot reach, and land the tested conclusion for each control back in Noru.
Plugin audit-pack from marketplace noru-grc-engineering in noru-tech/noru-grc-engineering. Commands read from the repo's manifest — 6 days ago.
audit-packAssemble the evidence bundle, the sampling and the workpapers an auditor asks for, for one framework over one audit window, from Noru's own graph plus the local files an integration cannot reach — then land the tested conclusion for each control back in Noru. Use when someone is preparing for an aud
/audit-pack:diffShow exactly which workpaper conclusions would be filed in Noru and what they would satisfy. Reads only; writes nothing.
/audit-pack:pushFile the reviewed workpaper conclusions in Noru as attributed evidence, mapped to the controls they are about. The pack itself stays local. Writes to the customer's system of record — requires explicit confirmation.
/audit-pack:scanAsk Noru what is in scope for a framework and a window, digest the local artifacts, draw the samples, and write a reviewable .noru/audit-pack.yml. Renders the pack once the manifest validates. Writes nothing to Noru.
noruconnects to: https://api.noru.tech/v1/mcp
Run consolidated branch reviews across independently installed GRC pieces, summarize live Noru work requiring attention with read scopes only, and check shared connection and repository context.
1 skill · 5 commands · 1 MCP server
Install, plan, apply, and verify enforceable GitHub merge gates for the GRC Engineering workflow without granting the Noru hub administration rights.
1 skill · 6 commands
Scan a repository for the AI systems, model providers and oversight points it actually contains, review the manifest in a PR, and land it in Noru as assets, vendors and evidence.
1 skill · 3 commands · 1 MCP server
Who wrote each change, who approved it, who merged it and who deployed it, for one window — with every separation that did not hold owned by a named person, and the forge configuration that was supposed to keep them apart.
1 skill · 3 commands · 1 MCP server
Inventory the coding agents, MCP servers and plugins a repository's development process depends on, decide with the user which organization stands behind each one, and land them in Noru as vendors plus one evidence record for the window — never anything per person.
1 skill · 3 commands · 1 MCP server
Work Noru's own evidence queue: see which catalogue expectations are unmet, stage local artifacts against them, and upload with control mappings.
1 skill · 3 commands · 1 MCP server
Design fluency for frontend development. 1 skill with 24 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
1 skill · 4 agents · hooks
ADR lifecycle management — create, index, supersede, and link Architecture Decision Records to code
5 skills · 1 command · 1 agent
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Install the "AAS Privacy & Compliance Engineering" workflow plugin from Agentic Awesome Skills.
6 skills
Deep vulnerability scanning of your own code, run entirely inside your Claude Code session at a chosen effort tier, with every finding challenged before it is reported and the verification tally computed in code. Turns surviving findings into targeted patches, each verified by a panel of agents, that you apply when you choose.
1 skill · 9 agents · hooks
Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).
1 skill · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.