Agent Claude Code
Usability evaluator playing the ADMIN persona on a self-hosted BearDrive hub — an IT admin deploying BearDrive for their company. Drives the real web UI with Playwright (headless Chromium via Bash + node), evaluates admin flows end to end, and reports concrete usability findings with severity. Use when hands-on…
Agent Claude Code
CTO-level engineering reviewer for BearDrive — audits architecture, reusability, and scalability across the Go backend (sync engine, hub, storage) and the React/TS frontend. Reads the real code, checks changes against the repo's invariants and seams, and returns prioritized findings with concrete refactor plans…
Agent Claude Code
Product designer who reviews the BearDrive web app's visual design, UX, and layout. Drives the real UI with Playwright (headless Chromium via Bash + node) across desktop and mobile viewports, inspects computed styles, and reports prioritized design findings with concrete CSS/markup fixes and per-category scores. Use…
Agent Claude Code
Veteran commercial-open-source (COSS) operator who reviews BearDrive's go-to-market — someone who has been both the OSS maintainer and the managed-cloud GM. Audits positioning, README/website/docs as funnel surfaces, the open↔paid line, licensing posture, launch readiness, community health, and metrics, benchmarked…
Agent Claude Code
Usability evaluator playing the END-USER persona on a self-hosted BearDrive hub — a non-admin employee onboarding for the first time. Drives the real web UI with Playwright (headless Chromium via Bash + node), walks the newcomer journey (signup, empty state, invite, browsing, sharing, palette), and reports usability…
Agent Claude Code
Defensive security agent for BearDrive. Takes the hacker's failing tests, fixes each hole at the choke point (not the symptom), keeps the repo's sync invariants intact, then updates the scoreboard and names which boundaries were never actually exercised. Use for the defense half of the security validation loop in…
Agent Claude Code
Offensive security agent for BearDrive. Attacks the hub's authorization boundaries — auth gate, per-project permissions, cross-org isolation, the /store sync proxy, uploads, share links, invites — and turns every real finding into a Go test that FAILS on the current tree. Never fixes anything, never grades. Use for a…
Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing check-arch-diagrams.sh. From runbear-io/beardrive.
Settings file Claude Code
Agent settings declaring 1 hook event (PreToolUse) and 8 allowed tools.
Skill Claude CodeCodex
Live end-to-end test of BearDrive's agent-first onboarding: run the real paste-prompt flow in a fresh headless Claude session (and optionally a full role-played user conversation) against a seeded local hub, asserting the scope hard-gate and hooks-via-init behaviors, and report transcripts plus doc-vs-reality…
Instructions file
Claude Code instructions for runbear-io/beardrive, covering claude.md, what this is, commands, architecture and invariants — do not break these.
Skill Claude CodeCodex
The conventions this team actually follows — naming, branching, review, and the decisions someone already made so nobody re-litigates them. Use when writing or reviewing code here, opening a PR, or when unsure "how do we do this".
Plugin Claude Code
Plugin marketplace listing 1 plugin: aweek.
Plugin Claude Code
Claude Code plugin for managing multiple AI agents on scheduled weekly plans. Each agent is a 1-to-1 wrapper around a Claude Code subagent with its own long-term goals, monthly objectives, weekly tasks, and token budget.
Instructions file
Instructions for runbear-io/aweek, covering claude.md, project overview, development environment, commands and skills.
Skill Claude CodeCodex
Display an agent's weekly plan as a calendar grid with day columns and hour rows.
Skill Claude CodeCodex
Show the project's .aweek/config.json knobs (plus the hardcoded scheduler/lock constants the dashboard surfaces) and edit the config-backed fields with a confirmation gate.
Skill Claude CodeCodex
Delegate a task from one agent to another via the async inbox queue.
Skill Claude CodeCodex
Hire (create) a new aweek agent — collect identity, then interview the user to author plan.md (long-term goals, monthly plans, strategies, notes) so the agent is plan-ready immediately.
Skill Claude CodeCodex
Manage an agent's lifecycle — resume paused agents, pause/stop agents, edit identity, or delete/archive agents.
Skill Claude CodeCodex
Edit an agent's free-form planning markdown and adjust weekly tasks from a single entry point.
Skill Claude CodeCodex
Filter the aweek agent roster by role, status, persona keyword, or budget and return a slug list that other skills can act on.
Skill Claude CodeCodex
Manage Google-Calendar-style recurring tasks per agent — daily/weekly/biweekly/monthly rules that expand into occurrences on the calendar and execute through the heartbeat loop.
Skill Claude CodeCodex
Agent → CEO report. Send a status report or question to the user (CEO) on behalf of an agent. Notifies the dashboard inbox and, when a Slack ceoChannel is configured, pushes a Slack message.