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.
Plugin audits from marketplace maintainerd in Vycari/maintainerd. Commands read from the repo's manifest — 2 days ago.
audit-architectureWalk the repo's source in the configured language looking for technical debt — oversized files, DRY violations, dead code, missing tests, sloppy typing, weak abstractions, and drift against the repo's documented invariants. Categorize each finding into a discrete unit of work; open a focused PR for
audit-depsScheduled dependency-health sweep — outdated packages (behind on patch/minor/major), deprecated or end-of-life packages, unused declared dependencies, phantom (used-but-undeclared) dependencies, lockfile drift, and license issues. Routes one focused PR for mechanically-safe fixes (a batched routine-
audit-design-docsReview design/architecture/planning docs, validate each claim against the code, fix drift, and add docs for uncovered load-bearing subsystems. Use when the user asks to "review planning docs", "audit the design docs", "validate docs against the code", "sync docs with the codebase", "find doc gaps",
audit-product-docsValidate the repo's user-facing / product / contributor docs against the code (settings/config names + defaults, command/action IDs, file paths, schedule/cron formats, tool/function names), patch drift in place, and add new docs only for user-visible features that aren't covered. Use when the user a
audit-securityScheduled security sweep of the whole repo — known-vulnerable dependencies (CVEs), secrets/credentials committed to the tree or git history, and hardcoded config / permissive defaults. Severity-ranked; opens a focused PR for mechanically-safe fixes and files an issue for anything needing judgment —
audit-testsThe repo's test-suite health expert. Reviews the test suite the way a senior staff engineer who cares about test quality would — coverage gaps on critical paths, inappropriate or excessive mocking (mocking what you own, mocks that never assert, asserting on mock internals over behavior), weak or abs
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
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.
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
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
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Without good data, your agent gives generic advice. Keyword research, competitor research, backlinks, and site audits. All for $10/month.
12 skills · 1 MCP server
Connect providers and targets, write eval suites, and set up or run red team scans with promptfoo
4 skills
Automates browser interactions for web testing, form filling, screenshots, and data extraction
1 skill
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.