--- name: pp-hostfully description: "Hostfully reservations and guest messaging — plus caller-ID lookup, quotes, and multi-unit vacancy analysis. Trigger phrases: `who's checking in today`, `who is this caller`, `quote a stay`, `check guest messages`, `find a vacancy window`, `use hostfully`." author: "Greg Mushen" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - hostfully-pp-cli install: - kind: go bins: [hostfully-pp-cli] module: github.com/mvanhorn/printing-press-library/library/travel/hostfully/cmd/hostfully-pp-cli --- # Hostfully — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `hostfully-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install hostfully --cli-only ``` 2. Verify: `hostfully-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.9 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/travel/hostfully/cmd/hostfully-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Reads current operational data (today's guests, availability, caller identity, quotes) live from Hostfully, and keeps a local SQLite archive for historical analysis such as occupancy, turnover and vacancy windows. Unit numbers are discovered from your agency's properties, or pinned with HOSTFULLY_UNITS. ## When to Use This CLI Use this CLI for day-to-day Hostfully operations: identifying callers, checking today's arrivals and departures, live availability, quoting stays, reading and answering guest messages, and planning around vacancy. Use the archive-backed analytics for occupancy, turnover and channel questions. Channel analytics break bookings down by source such as Airbnb, Booking.com, VRBO and direct. Reads are the default; `inbox reply` is the single command that sends a guest message, and it requires --yes (preview with --dry-run). Unit numbers map to properties via `hostfully-pp-cli units`. ## Anti-triggers Do not use this CLI for: - Changing rates, rules or listing content (use the Hostfully web app) - Creating or cancelling reservations - Payment refunds or payouts ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Live guest operations - **`whois`** — Look up a guest by phone number or name and get every stay, payment status and reservation access PIN. _Reach for this first when a guest calls or texts and you need to know who they are and which stay they mean._ ```bash hostfully-pp-cli whois "+1 555 010 0199" --agent ``` - **`inbox`** — Read recent guest messages and threads, and reply through the reservation thread with a dry-run guard. _Use to triage new guest messages and draft or send replies without opening the web app._ ```bash hostfully-pp-cli inbox messages --since 24h --agent ``` - **`quote`** — Price a stay for a property and dates with rent, taxes and fees itemized. _Use when a prospective guest asks what a stay costs._ ```bash hostfully-pp-cli quote --unit 1 --check-in 2026-11-06 --check-out 2026-11-08 --guests 2 --agent ``` - **`jobs`** — List cleaning and maintenance jobs with service and provider identity, including cancelled jobs. _Use to reconcile a cleaning or service vendor's invoice against scheduled jobs._ ```bash hostfully-pp-cli jobs --from 2026-10-01 --to 2026-10-31 --agent ``` ### Planning and analytics - **`vacancy`** — Find consecutive vacant days across several units at once. _Use to plan work or owner stays that need several units free together._ ```bash hostfully-pp-cli vacancy --units 1,2 --consecutive 2 --agent ``` - **`maintenance`** — Find maintenance slots across units around upcoming bookings. _Use when scheduling repairs that must not disturb guests._ ```bash hostfully-pp-cli maintenance --units all --min-days 1 --agent ``` - **`turnover`** — See cleaning windows between each checkout and the next check-in. _Use to build the week's cleaning schedule._ ```bash hostfully-pp-cli turnover --days 7 --agent ``` - **`occupancy`** — Per-unit and overall occupancy for any period. _Use for monthly performance reviews._ ```bash hostfully-pp-cli occupancy --month 2026-09 --agent ``` - **`channels`** — Break down where bookings come from over a period. _Use to see which channels drive bookings._ ```bash hostfully-pp-cli channels --period 90d --agent ``` - **`revenue`** — Estimate revenue per unit and month from booked nights. _Use for quick revenue snapshots._ ```bash hostfully-pp-cli revenue --month 2026-09 --agent ``` - **`patterns`** — Spot weekday/weekend and seasonal booking trends. _Use for pricing and staffing decisions._ ```bash hostfully-pp-cli patterns --weeks 12 --agent ``` ## Command Reference **leads** — Reservations and bookings across all properties - `hostfully-pp-cli leads` — List leads (reservations) with date and property filters **properties** — Rental properties/units managed by the agency - `hostfully-pp-cli properties` — List all properties for the agency **channels** - `hostfully-pp-cli channels` — Break down where bookings come from over a period. **inbox** - `hostfully-pp-cli inbox` — Read recent guest messages and threads, and reply through the reservation thread with a dry-run guard. **jobs** - `hostfully-pp-cli jobs` — List cleaning and maintenance jobs with service and provider identity, including cancelled jobs. **maintenance** - `hostfully-pp-cli maintenance` — Find maintenance slots across units around upcoming bookings. **occupancy** - `hostfully-pp-cli occupancy` — Per-unit and overall occupancy for any period. **patterns** - `hostfully-pp-cli patterns` — Spot weekday/weekend and seasonal booking trends. **quote** - `hostfully-pp-cli quote` — Price a stay for a property and dates with rent, taxes and fees itemized. **revenue** - `hostfully-pp-cli revenue` — Estimate revenue per unit and month from booked nights. **turnover** - `hostfully-pp-cli turnover` — See cleaning windows between each checkout and the next check-in. **vacancy** - `hostfully-pp-cli vacancy` — Find consecutive vacant days across several units at once. **whois** - `hostfully-pp-cli whois` — Look up a guest by phone number or name and get every stay, payment status and reservation access PIN. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash hostfully-pp-cli which "" ``` `which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query. `--json` (and other machine formats) keep that exit-2 contract and write `{"matches":[]}` on stdout so agents can inspect the envelope without treating a miss as success. ## Recipes ### Who is calling ```bash hostfully-pp-cli whois "+1 555 010 0199" --agent ``` Resolve a phone number to the guest's stays, payment status and access PIN. ### Today's operations ```bash hostfully-pp-cli today --agent ``` Daily summary of check-ins, check-outs, in-house guests and vacant units. ### Narrow the unit map ```bash hostfully-pp-cli units --agent --select units.unit,units.propertyUid ``` Pull only unit numbers and property UIDs when wiring another tool to this CLI. ### Maintenance window ```bash hostfully-pp-cli vacancy --units 1,2 --consecutive 2 --agent ``` Find two consecutive days where units 1 and 2 are both empty. ## Auth Setup Set HOSTFULLY_API_KEY to an agency API key and HOSTFULLY_AGENCY_ID to the agency UID; every Hostfully request is agency-scoped. Unit numbers used by today, availability, whois, quote, vacancy and the other per-unit commands come from HOSTFULLY_UNITS ("1=,2="), a units.json file, synced properties, or live discovery of the agency's properties; run `hostfully-pp-cli units` to see the mapping. The property time zone comes from HOSTFULLY_TIMEZONE or the properties themselves. `inbox reply` is the one command that sends a guest message: it requires --yes and supports --dry-run. Run `hostfully-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. Global format flags share one contract on promoted, novel, sync, and `--deliver` paths: - `--json` — one JSON document on stdout (sync progress events go to stderr) - `--compact` — keep identity/status/timestamp fields; does not change the document vs stream shape - `--csv` / `--plain` — tabular rows (collection envelopes unwrap to the row array) - `--quiet` — one identity value per row, no envelope - **Pipeable** — JSON on stdout, errors on stderr - **Filterable** — `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs: ```bash hostfully-pp-cli leads --agency-uid 550e8400-e29b-41d4-a716-446655440000 --agent ``` - **Previewable** — `--dry-run` shows the request without sending - **Offline-friendly** — sync/search commands can use the local SQLite store when available - **Non-interactive** — never prompts, every input is a flag - **Read-only** — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` Parse `.results` for data and `.meta.source` to know whether it's live or local. A human-readable `N results (live)` summary is printed to stderr only when stdout is a terminal AND no machine-format flag (`--json`, `--csv`, `--compact`, `--quiet`, `--plain`, `--select`) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `HOSTFULLY_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `HOSTFULLY_CONFIG_DIR`, `HOSTFULLY_DATA_DIR`, `HOSTFULLY_STATE_DIR`, `HOSTFULLY_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `HOSTFULLY_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.toml` and profiles. `data` contains `credentials.toml`, `data.db`, cookies, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `hostfully-pp-cli doctor --fail-on warn` to surface path and credential-location warnings. `agent-context` exposes a schema v4 `paths` block for agents that need the resolved dirs. - For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags: ```json { "mcpServers": { "hostfully": { "command": "hostfully-pp-mcp", "env": { "HOSTFULLY_HOME": "/srv/hostfully" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `HOSTFULLY_HOME` or per-kind vars as durable fleet levers, and use `--home` only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing `HOSTFULLY_HOME`, or `doctor` will not find credentials left under the former root. ## Automatic learning This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a `flag_alias` candidate, and a `teach` on a query family without a playbook auto-synthesizes a `playbook_candidate` from the session's journal. Your job is judgment only: `recall` first, act on surfaced candidates, `teach` the final answer, `playbook amend` when you observe a correction. You never record failures by hand. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, pass the question as an argv or MCP tool argument to `recall --agent`. Do not interpolate user-controlled text into a shell command line. Quoted `recall ""` breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data: ```bash # Write the question verbatim with your file-writing tool (no shell involved). # Command substitution on a file only ever yields data — the shell never # parses the file's bytes as syntax. QUERY=$(cat /path/to/question.txt) hostfully-pp-cli recall "$QUERY" --agent ``` Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not. The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "hostfully-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and `learnings list` and `learnings candidates` are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught. ### Step 2: decision tree Read `candidates`, `playbook`, `notes`, `results[0]`, and warnings in that order: ``` if Candidates present (warnings include "candidates_present"): -> candidates are try-then-confirm, never facts. Follow each candidate's two-step next_action verbatim: run the trial command first, then run `learnings confirm ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> NEVER re-teach something recall surfaced as a candidate; confirm or reject that candidate instead of teaching a duplicate. -> candidates ride alongside playbooks and resource hits, not instead of them; continue with the branches below after acting on them. if Playbook present: -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose) -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries for the entity slot tokens. If a step's slot is unresolved, fall back to discovery for that step only. -> the Playbook's expected_tool_calls is a budget; if you find yourself running materially more, record the divergence via `hostfully-pp-cli playbook amend` at end-of-session. elif Notes present (no Playbook): -> read Notes verbatim before any discovery step; they carry known gotchas for this query family even when no structured choreography exists yet. elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2: -> skip discovery; fetch live data for Results[*].ResourceID in parallel elif Found AND Results[0].EntityMatch == "partial": -> candidate hint, NOT a hit; read the resource title to validate before trusting elif (any row in Mismatches[] when --debug-mismatches was passed): -> treat as cold start; the stored learning is for a different entity (different canonical resolved from query_entities) else: // Found == false, no playbook, no notes -> cold start; run discovery normally; teach the answer afterward (Step 4). If the family has no playbook yet, that teach auto-synthesizes a playbook candidate from this session's journal - you do not need to record one by hand. ``` Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a `Results[]` hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping `mismatches`; pass `--debug-mismatches` only when investigating cold-start surprises. Candidate judgment details: `learnings confirm ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `hostfully-pp-cli learnings candidates` lists the full open set. Graceful degradation: if `learnings confirm` is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol. ### Step 3: always read `warnings` - `low_confidence`: row exists at `confidence<2`. Treat as a hint, not a skip-discovery hit. - `resource_not_in_store`: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate. - `cross_alias_match` (per-result): the row was taught under a different alias and matched the live query's canonical via `entity_lookups` (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id. - `similar_shape_different_entity:` (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results