Foundation: bootstrap (generates a repo's .claude/maintainerd.json config contract), doctor (validates that setup, and reports drift from a fleet's repo standard with --profile) and new-repo (creates or adopts a repo against that standard), plus the canonical config schema every other plugin reads. Install this first.
Plugin maintainerd-core from marketplace maintainerd in Vycari/maintainerd. Commands read from the repo's manifest — 2 days ago.
bootstrapGenerate the maintainerd config contract for a repo — write `.claude/maintainerd.json` and scaffold `.claude/guidelines/{coding,testing,invariants}.md` so the repo-ops, audits, research, and auto-dev skills can run here. Inspects the repo (language, GitHub slug, default branch, source/test dirs, lin
doctorValidate a repo's Maintainerd setup and report what's wrong — the companion to `bootstrap`. Checks that `.claude/maintainerd.json` exists, parses, and conforms to the schema; that the configured paths, commands, and guidelines files resolve; that the GitHub labels the skills apply actually exist; th
new-repoCreate a new repo — or adopt an existing one — against a repo profile, so every repo in a fleet is set up the same way. Reads a profile JSON (the standard: merge methods, branch protection, required checks, labels, coverage policy, the files every repo carries), resolves this repo's effective values
Scheduled findings that open PRs/issues, deliberately capped and conservative: audit-architecture, audit-tests, audit-security, audit-deps, audit-design-docs, audit-product-docs. Language and rules come from the repo config + guidelines files.
6 skills
Baseline maintainer dev flow: create-pr (pre-flight-gated PRs), address-review (iterate on bot + human PR feedback to approval), release (cut a versioned release), daily-changelog, and the daily-update meta-skill. Plus two PreToolUse Bash hooks: pr-template-guard and skip-label-race-guard. Config-driven via .claude/maintainerd.json.
5 skills · hooks
Autonomous issue-to-PR pipeline driven by an auto:* GitHub label state machine: create-issue (turn a rough request into a buildable issue), auto-dev (triage -> plan -> build -> address-review; never merges), and review-queue (the maintainer's console). Configurable label names, markers, and branch prefixes.
3 skills
Autonomous Dependabot queue management — the one maintainerd plugin that merges. dependabot gates each bot-authored dependency PR on all checks green, no requested changes, and a semver policy (patch/minor by default; majors held for you), merges one PR per non-overlapping file group, waits for the rebase, and repeats until the queue drains. A broken update is never fixed: it's diagnosed, filed as an issue, and labelled. Requires an explicit depsFlow.enabled opt-in.
1 skill
User-scoped narration that spans repos: worklog captures a day's shipped work (merged PRs enriched by the live session) into the user's Obsidian vault. Vault path lives in a user-level ~/.claude/maintainerd.json; a per-repo pointer maps each repo to its vault project.
1 skill
Proactive research skills that surface relevant outside knowledge and open a PR/digest: research-radar (periodic arXiv scan for papers relevant to this repo). Room for future research tooling. Themes and output paths come from the repo config.
1 skill
Scaffold, validate, and publish new Claude Code plugins with proper structure
3 skills · 1 command · 1 agent
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.
44 skills · 1 MCP server
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
Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.
1 skill · 9 commands
Configure, run, and interpret HawkScan DAST results. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into prioritized fix tasks for your coding agent.
1 skill · hooks
Study companion for the Deep Learning textbook by Goodfellow, Bengio & Courville (MIT Press, 2016), free to read at deeplearningbook.org. Twenty chapter files, a glossary, patterns and a cheatsheet index the whole book, and a delta reference dates it against 2026 practice with per-claim confidence levels: double descent qualifying the U-curve, AdamW splitting weight decay from L2, transformers displacing Chapter 10's recurrence, diffusion growing out of Chapter 18's score matching. Four stdlib tools make it executable — a prerequisite-closed reading-path planner that refuses goals the book does not cover, a training diagnostic running Chapter 11's rules in priority order so a NaN is never reported as overfitting, a capacity planner that ranks 'shrink the model' last when overparameterized, and a parameter/FLOP/activation-memory calculator that refuses a stack whose shapes do not connect. A companion, not a compilation: the book is copyrighted, so nothing here reproduces its text.
1 skill · 3 commands · 1 agent
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.