
Use long-tail HQ CLI functionality from Cowork via the host-side guarded `mcp__hq__hq_cli` tool and schema-driven `mcp__hq__hq_run` tool. Covers HQ commands not yet modeled as dedicated MCP tools while blocking browser/session flows and secret-value output.
Read and inspect HQ vault objects from a sandboxed Claude Code plugin host (Cowork) without a full sync, via the host-side `mcp__hq__hq_files` tool. Actions — browse (list), cat (read one object), acl (show access list), search (match object keys), shared-with-me (grants to you), get (materialize into local HQ). Same capability as `/hq-files`, routed through hq-pack-cowork's MCP server.
Send a direct message to a teammate from a sandboxed Claude Code plugin host (Cowork) via the host-side `mcp__hq__hq_dm` tool. Delivers an HQ Sync menubar notification to anyone you share an active company with; optionally attaches a one-click agent prompt, a detail body, or schedules delivery. Same capability as `/dm`, routed through hq-pack-cowork's MCP server.
Run a full HQ sync (all cloud-backed companies, bidirectional) from a sandboxed Claude Code plugin host (Cowork) by calling the host-side `hq_sync` MCP tool. Same engine as AppBar HQ Sync and the `/hq-sync` skill, but routed through the hq-pack-cowork MCP server so it works even when the `hq` binary and `~/.hq` auth are not reachable from the agent's bash sandbox.
--- name: hq-cowork-search description: Hybrid full-text + semantic search across HQ content (policies, skills, knowledge, workers, projects, per-company collections) from a sandboxed Claude Code plugin host (Cowork). Calls the host-side `hq_search` MCP tool, which wraps `qmd query` (hybrid: expansion + RRF + rerank — the recommended search mode). Use when the agent needs to find HQ content but `qmd` isn't reachable from its bash sandbox. allowed-tools: mcp__hq__hq_search --- # /hq-cowork-searc
--- name: hq-cowork-secrets description: Use HQ secrets from a sandboxed Claude Code plugin host (Cowork). The host-side MCP server never returns a secret value itself: `mcp__hq__hq_secrets_exec` runs a command on the host with named secrets injected as env vars (only the command's output returns), and refuses to launch a shell or value-printing binary; `mcp__hq__hq_secrets_list` lists secret NAMES/metadata only. These tools run host commands with the user's privileges, so treat them as host-tru
Share an HQ vault path from a sandboxed Claude Code plugin host (Cowork) by calling the host-side `hq_share` MCP tool. Without `--with`, mints an encrypted single-use share-session URL (default 15-min expiry). With `--with`, grants direct ACL access to a person, group, or `@all`. Same capability as `/hq-share`, routed through hq-pack-cowork's MCP server so it works from a sandboxed agent.
Install hq-pack-cowork for Claude Code / Cowork from an HQ install, build the Cowork upload artifact, and show the exact Cowork smoke-test steps. Use this to make installing the HQ Cowork plugin easy for an HQ user.
Discovery + dispatch entry point for native HQ inside Cowork (or any sandboxed Claude Code plugin host). Enumerates every HQ capability available through hq-pack-cowork's host-side MCP server (identity, sync, qmd/search, secrets, vault files, team & membership, packages & modules, meeting intelligence, feedback, schema-backed runs, guarded long-tail CLI) and routes to the right `mcp__hq__*` tool while preserving default HQ behavior through a different transport. Use when the agent needs HQ but `hq`/`qmd` aren't reachable from its bash sandbox and isn't sure which tool to call.
Read HQ meeting intelligence (recorded meetings, attached sources, extracted signals) from a sandboxed Claude Code plugin host (Cowork) via the host-side `mcp__hq__hq_meetings`, `mcp__hq__hq_sources`, and `mcp__hq__hq_signals` tools. List/get/search meetings, pull transcripts and AI notes, browse sources (meeting/email/slack/linear/notion) and signals (action_item/commitment/decision/key_point/risk/summary). Read-only; routed through hq-pack-cowork's MCP server.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Generate 1080x1080 HTML social graphics for HQ update posts. Dark monochrome terminal aesthetic with tree structures, color-coded categories, and {company} branding. Use when creating visuals for social posts about HQ features, workers, or releases.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Generate 1080x1080 HTML social graphics for HQ update posts. Dark monochrome terminal aesthetic with tree structures, color-coded categories, and {company} branding. Use when creating visuals for social posts about HQ features, workers, or releases.