# Pp Travelclick > Search any TravelClick-powered hotel's own rates directly -- room types, rate plans, fee-inclusive pricing, and the cheapest night to book -- without opening a browser tab per property. Trigger phrases: `check travelclick rates`, `search made hotel availability`, `find the cheapest night at this hotel`, `validate this corporate hotel code`, `compare these boutique hotels`, `use travelclick`, `run travelclick`. - Skill: `mvanhorn-printing-press-libra/pp-travelclick` (Agent Skill) - Install (CLI): `npx skillmds add mvanhorn-printing-press-libra/pp-travelclick` - Raw SKILL.md: https://api.skillmd.com/api/skills/mvanhorn-printing-press-libra/pp-travelclick/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - License: Apache-2.0 - Author: mvanhorn (https://skillmd.com/u/mvanhorn-printing-press-libra) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/mvanhorn-printing-press-libra/pp-travelclick --- # TravelClick — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `travelclick-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install travelclick --cli-only ``` 2. Verify: `travelclick-pp-cli --version` 3. Ensure the reported install directory is on `$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 1.26.6 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/travel/travelclick/cmd/travelclick-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. TravelClick/iHotelier powers the direct-booking widget for thousands of independent and boutique hotels. This CLI calls the same JSON API the widget itself uses to search availability, scan a date range for the lowest rate, validate corporate/group codes, and compare several hotels side by side. Search and info only -- no reservation, no guest PII, no payment data ever touches it. ## When to Use This CLI Use this CLI when checking a specific independent or boutique hotel's own direct rates -- price-matching against an OTA, finding the cheapest date for a stay, validating a corporate or event code, or comparing a handful of TravelClick-powered properties for the same trip. ## Anti-triggers Do not use this CLI for: - Do not use this CLI to make or modify a reservation -- it is search/info only and has no booking command by design. - Do not use this CLI for hotels that don't use TravelClick/iHotelier as their booking engine -- check that the hotel's booking URL is bookings.travelclick.com first. - Do not use this CLI to look up a guest's existing reservation, loyalty account, or payment details -- those require guest login and are out of scope. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Cross-hotel local queries - **`rates compare`** — Check several boutique hotels for the same dates in one call, ranked by lowest fee-inclusive total. _Reach for this when the user names more than one property for the same trip instead of calling 'rates search' repeatedly._ ```bash travelclick-pp-cli rates compare --hotels 102306,, --check-in 2026-09-15 --check-out 2026-09-18 ``` - **`rates cheapest-night`** — Scan several hotels' calendars at once and return the single best hotel+date combination. _Reach for this when the user is flexible on both hotel and date, not just date._ ```bash travelclick-pp-cli rates cheapest-night --hotels made-nyc, --from 2026-09-01 --to 2026-10-31 ``` - **`codes check-all`** — Test one corporate or group code against every saved hotel at once. _Reach for this when the user has a code but isn't sure which of their saved hotels honors it._ ```bash travelclick-pp-cli codes check-all ACME2026 --type corporate --hotels made-nyc, ``` ### Local state that compounds - **`hotels alias`** — Give a memorable name to a TravelClick hotel ID instead of memorizing a 6-digit number. _Reach for this before repeated lookups against the same property so later commands can take the alias instead of the raw ID._ ```bash travelclick-pp-cli hotels alias add made-nyc 102306 ``` - **`analytics price-drift`** — Track how a hotel's rates move over time from your own saved search history. _Reach for this after the user has run a few 'rates search --save' calls and wants to know if a rate went up or down._ ```bash travelclick-pp-cli analytics price-drift --hotel 102306 ``` ## HTTP Transport This CLI uses Chrome-compatible HTTP transport for browser-facing endpoints. It does not require a resident browser process for normal API calls. ## Discovery Signals This CLI was generated with browser-observed traffic context. - Capture coverage: 5 API entries from 5 total network entries - Protocols: rest_json (75% confidence) - Auth signals: bearer_token — headers: Authorization - Candidate command ideas: create_multi_room — Derived from observed POST /ibe-shop/v1/hotel/{hotel_id}/basicavail/multi-room traffic.; get_TEST123 — Derived from observed GET /ibe-codes/v1/hotel/{hotel_id}/specialcodes/corporate/TEST123 traffic.; get_avail — Derived from observed GET /ibe-shop/v1/hotel/{hotel_id}/avail traffic.; get_info — Derived from observed GET /ibe-entity/v1/hotel/{hotel_id}/info traffic. - Caveats: error_status_cluster: Endpoint cluster only observed error HTTP statuses.; error_status_cluster: Endpoint cluster only observed error HTTP statuses. ## Command Reference **codes** — Validate special rate codes (corporate/rate-access or group-attendee) against a hotel before applying them to a search. - `travelclick-pp-cli codes validate-corporate` — Check whether a corporate / rate-access code is valid for this hotel. - `travelclick-pp-cli codes validate-group` — Check whether a group-attendee code is valid for this hotel. **hotel** — Read-only hotel property information: address, policies, check-in/out times, and amenities. No PII, no reservation data. - `travelclick-pp-cli hotel ` — Fetch a hotel's public profile: name, address, geolocation, check-in/out times, accepted cards **rates** — Search room availability and rate plans for specific dates, or scan a date range for the cheapest night. - `travelclick-pp-cli rates calendar` — Scan a date range (up to ~60 days) - `travelclick-pp-cli rates search` — Search available rooms and rate plans for a hotel between check-in and check-out. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash travelclick-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. ## Recipes ### Cheapest room+rate for a stay ```bash travelclick-pp-cli rates search 102306 --check-in 2026-09-15 --check-out 2026-09-18 --agent --select roomStays.roomTypes.roomTypeName,roomStays.roomTypes.averageRates.rate,roomStays.roomTypes.averageRates.rateExternalCode ``` Narrows the deeply-nested avail response to just room name, rate, and rate code per plan instead of the full policy/amenity/image payload. ### Find the cheapest night in a month ```bash travelclick-pp-cli rates calendar 102306 --from 2026-09-01 --to 2026-09-30 --json ``` Returns the lowest rate for every day in the range so you can sort for the minimum. ### Check a corporate code before searching ```bash travelclick-pp-cli codes validate-corporate 102306 ACME2026 ``` Confirms whether a rate-access code is live for this hotel. **Validating a code does not currently let you search rates for it** — see Known Limitations below before assuming this recipe's name describes the full workflow. ### Compare three boutique hotels for the same weekend ```bash travelclick-pp-cli rates compare --hotels 102306,, --check-in 2026-09-15 --check-out 2026-09-18 ``` Fans out the search across hotels and ranks them by lowest fee-inclusive total. ## Known Limitations **No way to search rates for a specific corporate/rate-access code.** `codes validate-corporate` and `codes validate-group` can only confirm whether a code is valid — `rates search` has no `--corporate-code`, `--rate-plan-id`, or equivalent parameter to actually filter results to that code's rate plan once validated. Confirmed by checking the discovery sample for `codes validate-corporate`: the only captured response is a 404 (`INVALID_CORP_ID`, from testing an intentionally-fake `TEST123` code) — discovery never observed what a *successful* validation returns, so neither the generator nor this CLI's author ever saw whether that response carries a rate plan ID, a discount code, or anything `rates search` could consume. The "Check a corporate code before searching" recipe above validates the code but cannot actually chain into a filtered search; treat it as a standalone validity check only. **Real, verified workaround**: the booking widget itself accepts a page-level `RatePlanId` query parameter that pre-selects a specific corporate rate — `https://reservations.travelclick.com/{hotel_id}?RatePlanId={id}` (redirects to `bookings.travelclick.com/{hotel_id}?RatePlanId={id}#/guestsandrooms`). Verified working directly against a real hotel ID with a valid corporate `RatePlanId`: the page loads with that specific negotiated rate pre-selected under Accommodations, and its real price is readable from the rendered page. This is a *page-level* UI parameter, not a confirmed `/ibe-shop/v1/hotel/{hotel_id}/avail` API query parameter — it was not captured at the network level, only observed working through the rendered widget, so it cannot be wired into `rates search`'s params without a fresh discovery pass that captures the underlying API call while this URL parameter is present. Until then, a specific corporate rate's real price has to be read from the widget directly (this URL pattern), not from this CLI. (The specific hotel/rate-plan pair used to verify this is omitted deliberately: pairing a real `RatePlanId` with the corporation it belongs to discloses that company's negotiated pricing to anyone who reads this file, so treat any `RatePlanId` you test with as sensitive and don't publish it alongside the company name.) **If you have a real corporate/rate-access code to test with**: re-running discovery's browser-sniff against `codes validate-corporate` with that valid code (not `TEST123`) would capture the missing successful-response shape, and re-sniffing `avail` while the widget has a `RatePlanId` selected would likely surface the real API-level parameter name. Either capture would unblock a durable fix; noting this so it doesn't require re-discovering the gap from scratch. ## Auth Setup TravelClick's widget mints a short-lived (~1 hour) OAuth2 client_credentials Bearer token client-side during page load. The exact token-mint endpoint was not isolated during discovery (it fires before any capture hook can attach), so this CLI cannot mint its own token yet -- capture one manually: open the hotel's booking page in Chrome, open DevTools' Network tab, filter for api.travelclick.com, click any request, and copy the Authorization header's value (everything after 'Bearer ') into TRAVELCLICK_TOKEN. Re-capture roughly every hour. Run `travelclick-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. - **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 travelclick-pp-cli rates search mock-value --check-in 2026-01-15 --check-out 2026-01-15 --agent --select timeSpan,roomTypes,allRoomTypes ``` - **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 - **Explicit confirmation** — `--agent` does not imply `--yes`; pass `--yes` separately only after the target, arguments, and side effects are clear - **Explicit retries** — use `--idempotent` only when an already-existing create should count as success ### 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 `TRAVELCLICK_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `TRAVELCLICK_CONFIG_DIR`, `TRAVELCLICK_DATA_DIR`, `TRAVELCLICK_STATE_DIR`, `TRAVELCLICK_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `TRAVELCLICK_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 `travelclick-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": { "travelclick": { "command": "travelclick-pp-mcp", "env": { "TRAVELCLICK_HOME": "/srv/travelclick" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `TRAVELCLICK_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 `TRAVELCLICK_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, run: ```bash travelclick-pp-cli recall "" --agent ``` 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": ["", "travelclick-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 `travelclick-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; `travelclick-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. - `ambiguous_alias` (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource. - `candidates_present` (top-level): the envelope carries a `candidates` section. Handle it via the candidates branch in Step 2 before anything else. - Top-level `no_learnings_for_query_family`: the table had no rows above the Jaccard floor. Pure cold start. ### Step 4: `teach &` after finalizing your response - always Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell `&` so the call returns immediately: ```bash travelclick-pp-cli teach --query "" --resource-type --resource --resource # (append shell `&` to background it) ``` Silent on success. Errors only land in `teach.log` under the resolved state dir. Teach the **most specific** resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded `entity_lookups` for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically. PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning. ### Step 5: playbooks - optional flags, automatic synthesis You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a `playbook_candidate` from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the **integrated one-call form** - record the resource learning and the playbook in the same `teach` invocation: ```bash # Common case: record both the resource learning AND the playbook in one call. travelclick-pp-cli teach \ --query "" \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). travelclick-pp-cli teach-playbook \ --query "" \ --playbook-file ~/playbooks/.json \ --notes-file ~/playbooks/-notes.md ``` Playbook files are JSON with `steps`, `entity_slots`, `expected_tool_calls`. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: `--playbook-json` and `--playbook-notes` on the integrated `teach` form, `--playbook-json` and `--notes` on `teach-playbook`. On the integrated `teach` form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone `teach-playbook` form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with `slots_resolved` binding the live query's canonical at recall time. When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with `slots_resolved` substitutions, skip the discovery that the choreography already documents, and read `notes` before any step. ### Step 6: `playbook amend &` when your debug response identifies a correction If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire `playbook amend` BEFORE emitting your user-facing response. Same fire-and-forget posture as `teach`. ```bash travelclick-pp-cli playbook amend \ --query "" \ --add-note "" # (append shell `&` to background it) ``` What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending: - A workaround for a CLI surface that silently drops or misorders a flag. - An undocumented endpoint shape (response wrapped in `{meta, results}`, payload nested two levels deeper than the docs claim). - Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased). What does NOT belong in notes: - The year-specific or entity-specific answer to the user's question. That's the response, not a learning. - Per-team / per-athlete / per-row data the playbook already retrieves at runtime. - Statements that paraphrase what the existing notes already say. The amend command appends to the family's existing notes with a timestamped marker (`[amend YYYY-MM-DDTHH:MMZ]: `). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land). #### PII discipline for amend notes `playbook amend` notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing: - **Do NOT embed** paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user. - **Acceptable**: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics. If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend. ### Measuring the loop `travelclick-pp-cli learnings stats` reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local `learn_events` table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI. ### Disabling learning - `--no-learn` on a single command short-circuits both `recall` and the `teach` write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings. - `TRAVELCLICK_NO_LEARN=true` in the environment globally disables the pipeline. ## Agent Feedback When you (or the agent) notice something off about this CLI, record it: ``` travelclick-pp-cli feedback "the --since flag is inclusive but docs say exclusive" travelclick-pp-cli feedback --stdin < notes.txt travelclick-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `TRAVELCLICK_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `TRAVELCLICK_FEEDBACK_AUTO_SEND=true`. Default behavior is local-only. Write what *surprised* you, not a bug report. Short, specific, one line: that is the part that compounds. ## Output Delivery Every command accepts `--deliver `. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported: | Sink | Effect | |------|--------| | `stdout` | Default; write to stdout only | | `file:` | Atomically write output to `` (tmp + rename) | | `webhook:` | POST the output body to the URL (`application/json` or `application/x-ndjson` when `--compact`) | Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr. ## Named Profiles A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run. ``` travelclick-pp-cli profile save briefing --json travelclick-pp-cli --profile briefing rates search mock-value --check-in 2026-01-15 --check-out 2026-01-15 travelclick-pp-cli profile list --json travelclick-pp-cli profile show briefing travelclick-pp-cli profile delete briefing --yes ``` Explicit flags always win over profile values; profile values win over defaults. `agent-context` lists all available profiles under `available_profiles` so introspecting agents discover them at runtime. ## Exit Codes | Code | Meaning | |------|---------| | 0 | Success | | 2 | Usage error (wrong arguments) | | 3 | Resource not found | | 4 | Authentication required | | 5 | API error (upstream issue) | | 7 | Rate limited (wait and retry) | | 10 | Config error | ## Argument Parsing Parse `$ARGUMENTS`: 1. **Empty, `help`, or `--help`** → show `travelclick-pp-cli --help` output 2. **Starts with `install`** → ends with `mcp` → MCP installation; otherwise → see Prerequisites above 3. **Anything else** → Direct Use (execute as CLI command with `--agent`) ## MCP Server Installation 1. Install the MCP server: ```bash go install github.com/mvanhorn/printing-press-library/library/travel/travelclick/cmd/travelclick-pp-mcp@latest ``` 2. Register with Claude Code: ```bash claude mcp add travelclick-pp-mcp -- travelclick-pp-mcp ``` 3. Verify: `claude mcp list` ## Direct Use 1. Check if installed: `which travelclick-pp-cli` If not found, offer to install (see Prerequisites at the top of this skill). 2. Match the user query to the best command from the Unique Capabilities and Command Reference above. 3. Execute with the `--agent` flag: ```bash travelclick-pp-cli [subcommand] [args] --agent ``` 4. If ambiguous, drill into subcommand help: `travelclick-pp-cli --help`.