# Pp Texas Roadhouse > Printing Press CLI for Texas Roadhouse. Waitlist: find a nearby store, read the quote, join and leave the list. Trigger phrases: `join the waitlist`, `Texas Roadhouse wait`, `roadhouse nearby`. - Skill: `mvanhorn-printing-press-libra/pp-texas-roadhouse` (Agent Skill) - Install (CLI): `npx skillmds add mvanhorn-printing-press-libra/pp-texas-roadhouse` - Raw SKILL.md: https://api.skillmd.com/api/skills/mvanhorn-printing-press-libra/pp-texas-roadhouse/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-texas-roadhouse --- # Texas Roadhouse - call ahead seating ## Prerequisites: Install the CLI This skill drives the `texas-roadhouse-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install texas-roadhouse --cli-only ``` 2. Verify: `texas-roadhouse-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/food-and-dining/texas-roadhouse/cmd/texas-roadhouse-pp-cli@6695fc0c66c9f1a5670c049428bd79752e231751 ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Waitlist CLI for Texas Roadhouse. Find a nearby store, read the quote, join and leave the list. **Unofficial integration:** This skill is not affiliated with or endorsed by Texas Roadhouse. It uses browser-observed, undocumented endpoints that may change without notice. A waitlist submission sends the guest's name, email address, phone number, and party details to Texas Roadhouse. Do not put that identity on argv flags. Agents pass stdin JSON, `--guest-file`, or `TEXAS_ROADHOUSE_GUEST_*` env vars. `--dry-run` redacts guest fields. Hidden name/email/phone flags are a private `--yes` path only. Live `submit` / `checkin` / `cancel` require `--yes`. **MCP privacy boundary:** the MCP server intentionally does not expose waitlist `submit`, because MCP hosts can retain tool-call arguments in transcripts or logs. Use the CLI's stdin JSON, `--guest-file`, environment, or interactive-prompt flow for a guest join. **Last endpoint verification:** 2026-08-29. A Cloudflare challenge or HTTP 403 can mean the browser-facing endpoint changed or rejected the Chrome-compatible transport; retrying a mutation is unsafe until `--dry-run` and a fresh read request succeed. ## 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: 7 API entries from 7 total network entries - Protocols: rest_json (75% confidence) - Candidate command ideas: get_mapbox.places — Derived from observed GET /api/mapbox/geocoding/v5/mapbox.places/{id} traffic.; get_quote — Derived from observed GET /api/texasroadhouse/waitlist/{waitlist_id}/quote traffic.; get_settings — Derived from observed GET /api/texasroadhouse/waitlist/{waitlist_id}/settings traffic.; get_test — Derived from observed GET /api/texasroadhouse/waitlist/{waitlist_id}/test traffic.; list_near — Derived from observed GET /api/stores/near traffic. ## Command Reference **mapbox** — Operations on mapbox.places - `texas-roadhouse-pp-cli mapbox ` — GET /api/mapbox/geocoding/v5/mapbox.places/{id} **stores** — Operations on near - `texas-roadhouse-pp-cli stores` — GET /api/stores/near **texasroadhouse** — Operations on test - `texas-roadhouse-pp-cli texasroadhouse cancel` — Cancel a waitlist request. Guests can also text `REMOVE` to leave; CLI leave is this cancel command. Live cancel requires `--yes`; `--dry-run` previews without POSTing. - `texas-roadhouse-pp-cli texasroadhouse checkin` — Mark the party HERE after the guest texts `HERE` once everyone has arrived (text `REMOVE` to leave). Not a host-stand visit. Live check-in requires `--yes`; `--dry-run` previews without POSTing. - `texas-roadhouse-pp-cli texasroadhouse get-quote` — GET /api/texasroadhouse/waitlist/{waitlist_id}/quote - `texas-roadhouse-pp-cli texasroadhouse get-settings` — GET /api/texasroadhouse/waitlist/{waitlist_id}/settings - `texas-roadhouse-pp-cli texasroadhouse get-status` — GET waitlist request status. Query clientid=texasroadhouse. - `texas-roadhouse-pp-cli texasroadhouse get-test` — GET /api/texasroadhouse/waitlist/{waitlist_id}/test - `texas-roadhouse-pp-cli texasroadhouse submit` — Join a store waitlist. Guest PII comes from stdin JSON, `--guest-file`, or `TEXAS_ROADHOUSE_GUEST_*` env vars, not argv flags. Live join requires `--yes`; `--dry-run` previews a redacted body without POSTing. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash texas-roadhouse-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. ## Auth Setup No authentication required. Run `texas-roadhouse-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 texas-roadhouse-pp-cli mapbox 65804 --agent --select bbox,center,context ``` - **Previewable** — `--dry-run` shows the request without sending - **Offline-friendly** — sync/search commands can use the local SQLite store when available - **Non-interactive** — `--agent` never prompts; guest name/email/phone belong on stdin JSON, `--guest-file`, or env vars, not argv flags - **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 `TEXAS_ROADHOUSE_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `TEXAS_ROADHOUSE_CONFIG_DIR`, `TEXAS_ROADHOUSE_DATA_DIR`, `TEXAS_ROADHOUSE_STATE_DIR`, `TEXAS_ROADHOUSE_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `TEXAS_ROADHOUSE_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 `texas-roadhouse-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": { "texas-roadhouse": { "command": "texas-roadhouse-pp-mcp", "env": { "TEXAS_ROADHOUSE_HOME": "/srv/texas-roadhouse" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `TEXAS_ROADHOUSE_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 `TEXAS_ROADHOUSE_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 texas-roadhouse-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": ["", "texas-roadhouse-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 `texas-roadhouse-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; `texas-roadhouse-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. - `lookup_refresh_available` (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run `texas-roadhouse-pp-cli sync` to refresh entity lookups. - 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 texas-roadhouse-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. texas-roadhouse-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). texas-roadhouse-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 texas-roadhouse-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 `texas-roadhouse-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. - `TEXAS_ROADHOUSE_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: ``` texas-roadhouse-pp-cli feedback "the --since flag is inclusive but docs say exclusive" texas-roadhouse-pp-cli feedback --stdin < notes.txt texas-roadhouse-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `TEXAS_ROADHOUSE_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `TEXAS_ROADHOUSE_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. ``` texas-roadhouse-pp-cli profile save briefing --json texas-roadhouse-pp-cli --profile briefing mapbox 65804 texas-roadhouse-pp-cli profile list --json texas-roadhouse-pp-cli profile show briefing texas-roadhouse-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 | | 5 | API error (upstream issue) | | 7 | Rate limited (wait and retry) | | 10 | Config error | ## Waitlist join flow (present, then confirm) This is the human choreography. The CLI lists stores. The agent presents them. The CLI never picks a store. When a human wants on a Texas Roadhouse waitlist: 1. `recall` the question first (`get on the Texas Roadhouse waitlist`). 2. Geocode the place they named (`mapbox`). If they named no place, ask for a city or use their last known area. Do not invent coordinates. 3. `stores --lat … --long … --limit 4 --radius 80`. Use each store's `extref` as `waitlist_id`, not the internal `id`. 4. `texasroadhouse get-quote ` for those four. 5. **STOP.** Present 3–4 stores with name, street address, city, distance, and wait. Wait for the human to name one store and a party size (1–6). 6. Repeat consent. Dry-run `submit --stdin` only after that pick. Guest name, email, and phone go in stdin JSON, `--guest-file`, or `TEXAS_ROADHOUSE_GUEST_*` — not argv flags: ```bash printf '%s\n' '{"EmailAddress":"guest@example.test","FirstName":"Test","LastName":"User","PrimaryPhoneAreaCode":"555","PrimaryPhoneNumber":"555-0100","PartySize":2,"WaitMinutes":10}' \ | texas-roadhouse-pp-cli texasroadhouse submit 218 --stdin --dry-run ``` Live `submit` only after an explicit yes (`--yes`). VIP Club stays off. The guest later texts HERE once everyone has arrived (REMOVE to leave); `checkin` is that HERE mark, not a host-stand visit, and still needs `--yes`. CLI leave is `texasroadhouse cancel`. ### How to present the options (every harness) Default that works everywhere (OpenClaw, Claude, Telegram, a terminal, Grok Bot): a numbered list, one store per line, then "Reply with the number (or store name) and party size." ``` 1. Store A — PII_ADDRESS_EXAMPLE — 18 mi — wait 0–10 (party 1–2) 2. Store B — PII_ADDRESS_EXAMPLE — 24 mi — wait 0–10 ``` If the host has selectable option cards (widgets, Slack buttons, AskUserQuestion), use those with the **same** labels: store name, address, wait. Still wait for the pick. Do not auto-select the closest store. ChatGPT, Codex, Claude, Hermes, OpenClaw, Telegram, Slack, Cursor, and a raw terminal all fit those two shapes. Claude AskUserQuestion and Slack buttons count as cards. ChatGPT, Codex, Hermes, OpenClaw, and Telegram default to the numbered list. If they already named the store ("Branson"), skip the list and confirm address + quote + party size only. ## Argument Parsing Parse `$ARGUMENTS`: 1. **Empty, `help`, or `--help`** → show `texas-roadhouse-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 Install the MCP binary from this CLI's published public-library entry or pre-built release, then register it: ```bash claude mcp add texas-roadhouse-pp-mcp -- texas-roadhouse-pp-mcp ``` Verify: `claude mcp list` ## Direct Use 1. Check if installed: `which texas-roadhouse-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 Command Reference above. 3. Execute with the `--agent` flag: ```bash texas-roadhouse-pp-cli [subcommand] [args] --agent ``` 4. If ambiguous, drill into subcommand help: `texas-roadhouse-pp-cli --help`.