pp-ordertogo
Browse, cart, and place orders at any OrderToGo.com restaurant from the terminal — pure-Go agent-native client... Trigger phrases: `order my usual`, `place my regular order`, `order from <restaurant>`, `what's my usual order`, `how much have I spent at`, `is <restaurant> open right now`, `use ordertogo`, `run ordertogo`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/food-and-dining/ordertogo/SKILL.md,
regenerated post-merge by tools/generate-skills/. Hand-edits here are
silently overwritten on the next regen. Edit the library/ source instead.
See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->
# OrderToGo — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `ordertogo-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install ordertogo --cli-only
```
2. Verify: `ordertogo-pp-cli --version`
3. Ensure the reported install directory is on `$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 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/food-and-dining/ordertogo/cmd/ordertogo-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.
## When to Use This CLI
Reach for this CLI when an agent needs to handle 'order my usual', 'is the restaurant open', 'how much have I spent here this month', or 'place this exact cart with a budget cap'. It's read-fast (everything cached locally after one sync), write-safe (every place command is gated behind --confirm + --max + verify-env short-circuit), and works for any OrderToGo customer regardless of metro.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Safe agent-driven ordering
- **`order plan`** — Recompose your previous order locally, validate against tax, and refuse to fire if total exceeds your --max cap.
_Reach for this when an agent needs to know 'will this fit my budget' before committing — answer comes from one structured call with no browser involvement._
```bash
ordertogo-pp-cli order plan --reuse-last --max 30 --json
```
- **`order place`** — Drive a headless Chrome via chromedp to complete the Braintree DropIn flow with your saved card, with the budget cap enforced before the browser opens.
_Use when an agent has a budget-validated plan and the user has confirmed; this is the one command that actually moves money._
```bash
ordertogo-pp-cli order place --reuse-last --confirm --max 30
```
### Local state that compounds
- **`usual`** — Cluster your historical orders by item-set similarity and surface the recurring set that defines 'your usual' at any restaurant you order from.
_Reach for this when a user says 'order my usual' and the agent needs to decide whether one obvious pattern exists or whether to ask which usual._
```bash
ordertogo-pp-cli usual --restaurant <slug> --json
```
- **`spending`** — Total spent, average order, days since last order, top items, and weekly cadence — all from local order history with one SQL query.
_Use when an agent needs to answer 'how much have I spent here' or 'how often do I order' without re-fetching history._
```bash
ordertogo-pp-cli spending --since 90d --json
```
- **`order plan`** — Pass --tip auto and the CLI applies your average tip percentage from history at this restaurant.
_Reach for this when an agent doesn't want to make the user pick a tip percentage — go with what's habitual._
```bash
ordertogo-pp-cli order plan --reuse-last --tip auto --json
```
### Reachability mitigation
- **`order plan`** — Refuse to fire if the restaurant is not currently open at the requested pickup time, using cached hours.
_Catches a class of agent failures before the payment flow opens._
```bash
ordertogo-pp-cli order plan --reuse-last --pickup-at '7:00 PM'
```
### Agent-native plumbing
- **`agent-context`** — Single-call structured dump: account, default restaurant, your usual, last-order summary, budget hint, days-since-last.
_Reach for this when an agent enters a session and needs a complete picture before suggesting any action._
```bash
ordertogo-pp-cli agent-context --json
```
- **`order place`** — All side-effect commands short-circuit when PRINTING_PRESS_VERIFY=1 is set, printing 'would place: <plan>' instead of submitting.
_Use when an agent or test harness wants to exercise the place path without real-world consequences._
```bash
PRINTING_PRESS_VERIFY=1 ordertogo-pp-cli order place --reuse-last --confirm --max 30
```
## Command Reference
**coupons** — Promotional coupons available to your account
- `ordertogo-pp-cli coupons list` — List active coupons for your account (endpoint shape inferred from web 'My Coupons' panel)
- `ordertogo-pp-cli coupons mark_used` — Mark a promotion code as used after applying it to an order
**giftcards** — Giftcard balances and history per restaurant
- `ordertogo-pp-cli giftcards` — List your giftcards across all restaurants (endpoint shape inferred from web 'My Giftcards' panel)
**notifications** — Notification badge for orders, rewards, and platform messages
- `ordertogo-pp-cli notifications` — Count of unread notifications for your account
**orders** — Order history, detail, validation, and tracking - the core ordering data path
- `ordertogo-pp-cli orders cancel` — Cancel your own order within the void window (typically before preparing-state)
- `ordertogo-pp-cli orders list` — List your order history across all restaurants (returns latest N orders, server-paginated)
- `ordertogo-pp-cli orders show` — Get order detail by orderid - items, options, totals, payment method, points earned, status timeline
- `ordertogo-pp-cli orders track` — HTML order tracking page (received → preparing → ready → picked up). Parsed for status by `order track`.
- `ordertogo-pp-cli orders validate` — Pre-validate a cart - returns an order token plus tax computation, used by `order plan` before any payment surface opens
**payment** — Braintree client token for payment-method nonce generation (used internally by chromedp headless flow)
- `ordertogo-pp-cli payment braintree_token` — Returns a Braintree client token used by the DropIn UI to mint a single-use payment nonce. Hand-driven by chromedp...
- `ordertogo-pp-cli payment checkout` — Submit order with payment nonce and customer details. Body must include `nonce` from Braintree client. The CLI uses...
**restaurants** — Restaurants on the OrderToGo platform - filter by location, view detail, list multi-location chains
- `ordertogo-pp-cli restaurants list` — List restaurants in a location code (e.g. sto for Seattle area)
- `ordertogo-pp-cli restaurants menu` — Full menu for a restaurant with categories, items, and modifier options
- `ordertogo-pp-cli restaurants show` — Show restaurant detail - hours, address, phone, location code, multi-location chain mapping
**rewards** — Reward points balances per restaurant
- `ordertogo-pp-cli rewards` — List your reward points across all restaurants (endpoint shape inferred from web 'My Rewards' panel)
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
ordertogo-pp-cli which "<capability in your own words>"
```
`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
### Order your usual under a cap
```bash
ordertogo-pp-cli orders plan --reuse-last --max 30 --json --select totals.subtotal,totals.tax,totals.tip,totals.total,items.name
```
Compose your usual cart, Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.