React Router Development
remix-run/react-router
Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.
Every Shopper storefront in one CLI — catalog, cart, delivery schedule, charge calendar, and spend analytics no web UI surfaces.
$ npx skills add mvanhorn/printing-press-library --skill pp-shopper -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mvanhorn/printing-press-library pp-shopper --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-shopper .claude/skills/pp-shopper && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pp-shopper" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopper into .claude/skills/pp-shopper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-shopper", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopperType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mvanhorn/printing-press-library --skill pp-shopper -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mvanhorn/printing-press-library pp-shopper --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cli-skills/pp-shopper .agents/skills/pp-shopper && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pp-shopper" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopper into .agents/skills/pp-shopper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-shopper", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-shopper -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mvanhorn/printing-press-library pp-shopper --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cli-skills/pp-shopper .cursor/skills/pp-shopper && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pp-shopper" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopper into .cursor/skills/pp-shopper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-shopper", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mvanhorn/printing-press-library.git --path cli-skills/pp-shopper--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mvanhorn/printing-press-library --skill pp-shopper -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mvanhorn/printing-press-library pp-shopper --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cli-skills/pp-shopper .gemini/skills/pp-shopper && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pp-shopper" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopper into .gemini/skills/pp-shopper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-shopper", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mvanhorn/printing-press-library pp-shopperInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mvanhorn/printing-press-library --skill pp-shopper -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .github/skills && cp -r skills-src/cli-skills/pp-shopper .github/skills/pp-shopper && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pp-shopper" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopper into .github/skills/pp-shopper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-shopper", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mvanhorn/printing-press-library --skill pp-shopper -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mvanhorn/printing-press-library pp-shopper --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cli-skills/pp-shopper .opencode/skills/pp-shopper && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pp-shopper" agent skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-shopper into .opencode/skills/pp-shopper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pp-shopper", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
pp-shopperEvery Shopper storefront in one CLI — catalog, cart, delivery schedule, charge calendar, and spend analytics no web UI surfaces.
Pp Shopper is an agent skill from mvanhorn/printing-press-library. Every Shopper storefront in one CLI — catalog, cart, delivery schedule, charge calendar, and spend analytics no web UI surfaces. Trigger phrases: check my Shopper basket, when is my next Shopper delivery, when will Shopper charge me, show my Shopper spend, use shopper-pp-cli, search Shopper catalog, add item to Shopper cart, Shopper charge calendar, Shopper cashback tier.
Its SKILL.md is about 9.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Frontend & Design, covering Frontend development. The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 76de244. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadBashFrom allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
goclaudenpxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SHOPPER_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Pp Shopper loads about 9.3k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 3,895 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Read, BashAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from mvanhorn/printing-press-library at commit 76de244, republished under its Apache-2.0 licence (© mvanhorn). 3,895 words, ~9,297 tokens.
.claude/skills/pp-shopper/SKILL.md (or your agent's skills folder).<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/commerce/shopper/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/". -->
This skill drives the shopper-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:npx -y @mvanhorn/printing-press-library install shopper --cli-onlyshopper-pp-cli --version$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:
go install github.com/mvanhorn/printing-press-library/library/commerce/shopper/cmd/shopper-pp-cli@latestIf --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.
shopper-pp-cli covers all six Shopper storefronts (Compra Programada, Fresh, Pet, Compra Única, Now, Now Bebidas) with correct store/cluster scoping, full siteapi REST surface, browser-deep-link helpers for subscription mutations, and a local SQLite layer for offline product search, basket diffs, price tracking, and cross-store spend rollup.
Use shopper-pp-cli when automating Shopper basket management, monitoring charge schedules, analyzing spend patterns across storefronts, or building agent workflows around the Shopper subscription cycle. Ideal for recurring-basket optimization, pre-cycle audit, and delivery-schedule awareness.
Do not use this CLI for:
These capabilities aren't available in any other tool for this API.
charge-calendar — Every upcoming cycle's charge date, edit-lock deadline, and delivery date in one timeline so you never miss an edit window or get surprised by a charge.
Use when an agent needs to know whether the edit window is still open before modifying a recurring basket.
shopper-pp-cli charge-calendar --store programada --agentbasket diff — Compares your current recurring basket against a previous cycle's snapshot to show exactly what was added, dropped, or re-quantified before the template locks.
Use when an agent needs to verify what changed in the basket since the last confirmed delivery cycle.
shopper-pp-cli basket diff --store programada --agentcashback optimize — Computes the cheapest set of items to add (or whether to wait) to cross the next cashback tier, favoring things you'll need anyway.
Use when an agent is finalising a basket and wants to maximise cashback return before the edit window closes.
shopper-pp-cli cashback optimize --tier 2399 --store programada --agentcart list-items — Lists what is actually in the basket: product, department, quantity, unit price and line total, with paused lines reported separately.
Reads GET /cart/list, the endpoint behind the web basket page. cart list-summary reads GET /cart/summary, which returns totals only and carries no item array — so it can tell you the basket costs R$ 27,96 but never what made it up. basket diff, price-watch --only-basket and any agent reasoning about basket contents read through this command.
shopper-pp-cli cart list-items --store programada --agentprice-watch — Tracks the price history of the SKUs you actually buy and alerts when one rises or drops meaningfully versus your own purchase baseline.
Use when an agent needs to know if a subscribed product has changed price significantly since the last order.
shopper-pp-cli price-watch --store programada --agentrestock predict — Predicts when you'll run out of each staple from your historical buying cadence and suggests what to add to the upcoming basket.
Use when an agent needs to pre-populate a recurring basket with items likely running low before the next cycle.
shopper-pp-cli restock predict --store programada --agentcatalog drift — Flags products you buy that were discontinued, silently swapped, or kept their price while shrinking the pack, surfacing the real R$/kg or R$/L change.
Use when an agent needs to audit whether the recurring basket still contains the same products as originally added.
shopper-pp-cli catalog drift --store programada --agentcheckout preview — Aggregates cart totals, next delivery date, charge date, minimum-order status, and accepted payment types into one pre-checkout view before you open the browser.
Use when an agent needs to confirm basket readiness and charge schedule before directing the user to open the browser for final payment.
shopper-pp-cli checkout preview --store programada --agentaddress — Saved delivery addresses with per-address available-store information
shopper-pp-cli address — List delivery addresses and which stores are available at each addresscart — Cart: view summary, add products, remove products
shopper-pp-cli cart add — Add a product to the cart or increase its quantityshopper-pp-cli cart list-items — List the products actually in the cart (name, quantity, unit price, line total)shopper-pp-cli cart list-summary — Show basket TOTALS only (value, cashback tier, minimum-order status) — use cart list-items for the contentsshopper-pp-cli cart remove — Remove units of a product; --quantity N removes N unitscatalog — Product catalog: search, departments, banners, suggestions
shopper-pp-cli catalog create-count — Count products matching a search query and optional filtersshopper-pp-cli catalog create-filters — Get available filter options for a search queryshopper-pp-cli catalog create-search — Search the product catalog by query with optional brand/type/metadata filtersshopper-pp-cli catalog get-view — Get details for a specific catalog bannershopper-pp-cli catalog list-banners — List promotional banners for the current storeshopper-pp-cli catalog list-departments — List product departments/categories for the current storeshopper-pp-cli catalog list-news — List new product arrivals for the current storeshopper-pp-cli catalog list-suggest — Get search suggestions for a query prefixdelivery — Delivery schedule: upcoming delivery date, edit-lock window, and reschedule calendar
shopper-pp-cli delivery list-calendar — Get delivery reschedule calendar — allowed date range and disabled daysshopper-pp-cli delivery list-summary — Show scheduled delivery date, current delivery status, and store messagefeatures — Storefront configuration, feature toggles, and timer state
shopper-pp-cli features create-select — Select active store (sets session context; no-op for header-scoped reads)shopper-pp-cli features create-start — Start a named feature timershopper-pp-cli features create-view — Mark a feature toggle as viewedshopper-pp-cli features list-stores — List all available storefronts with store IDs, cluster IDs, payment parameters, and feature flagsshopper-pp-cli features list-tick — Get current timer stateshopper-pp-cli features list-toggle — Get active feature toggles for the current storeorders — Purchase history and spend — reads from GET /orders/orders (web 'Histórico de compras')
shopper-pp-cli orders — List past orders for the active store (newest-first, paginated by size)session — Session and social-login validation
shopper-pp-cli session — Validate social-login session statusThis printed CLI owns bounded freshness only for registered store-backed read command paths. In --data-source auto mode, those paths check sync_state and may run a bounded refresh before reading local data. --data-source local never refreshes. --data-source live reads the API and does not mutate the local store. Set SHOPPER_NO_AUTO_REFRESH=1 to skip the freshness hook without changing source selection.
Covered paths:
shopper-pp-cli addressshopper-pp-cli address getshopper-pp-cli address listshopper-pp-cli address searchshopper-pp-cli cartshopper-pp-cli cart getshopper-pp-cli cart listshopper-pp-cli cart searchshopper-pp-cli catalogshopper-pp-cli catalog getshopper-pp-cli catalog listshopper-pp-cli catalog searchshopper-pp-cli catalog-departmentsshopper-pp-cli catalog-departments getshopper-pp-cli catalog-departments listshopper-pp-cli catalog-departments searchshopper-pp-cli catalog-products-newsshopper-pp-cli catalog-products-news getshopper-pp-cli catalog-products-news listshopper-pp-cli catalog-products-news searchshopper-pp-cli catalog-search-suggestshopper-pp-cli catalog-search-suggest getshopper-pp-cli catalog-search-suggest listshopper-pp-cli catalog-search-suggest searchshopper-pp-cli deliveryshopper-pp-cli delivery getshopper-pp-cli delivery listshopper-pp-cli delivery searchshopper-pp-cli delivery-v2-calendarshopper-pp-cli delivery-v2-calendar getshopper-pp-cli delivery-v2-calendar listshopper-pp-cli delivery-v2-calendar searchshopper-pp-cli featuresshopper-pp-cli features getshopper-pp-cli features listshopper-pp-cli features searchshopper-pp-cli features-timer-tickshopper-pp-cli features-timer-tick getshopper-pp-cli features-timer-tick listshopper-pp-cli features-timer-tick searchshopper-pp-cli features-toggleshopper-pp-cli features-toggle getshopper-pp-cli features-toggle listshopper-pp-cli features-toggle searchshopper-pp-cli ordersshopper-pp-cli orders getshopper-pp-cli orders listshopper-pp-cli orders searchshopper-pp-cli sessionshopper-pp-cli session getshopper-pp-cli session listshopper-pp-cli session searchWhen JSON output uses the generated provenance envelope, freshness metadata appears at meta.freshness. Treat it as current-cache freshness for the covered command path, not a guarantee of complete historical backfill or API-specific enrichment.
When you know what you want to do but not which command does it, ask the CLI directly:
shopper-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.
These commands are declared by the spec author and require separate hand-written wiring; the generator does not emit Cobra registration for them. They are listed here for discoverability and are intentionally outside ## Command Reference so the verify-skill unknown-command check does not treat them as generator-owned paths.
shopper-pp-cli stores — List all available Shopper storefronts with IDs, cluster IDs, payment parameters, and capability flagsshopper-pp-cli checkout preview — Pre-checkout summary: basket totals, delivery date, charge date, min-order status, and accepted payment types (read-onlyshopper-pp-cli checkout open — Open the Shopper checkout page in the system browser (subscription-based payment via session login)shopper-pp-cli delivery reschedule [--store <store>] — Open the delivery reschedule calendar in the browser (POST /shop/minha-conta/alterar-data requires session cookie)shopper-pp-cli delivery skip — Open the skip-delivery page in the browser — subscription stores only (POST /shop/minha-conta/pular-entrega/ requiresshopper-pp-cli delivery suspend — Open the suspend-subscription page in the browser (POST /shop/minha-conta/suspender-entrega requires session cookie)shopper-pp-cli delivery boleto — Open the boleto-retrieval page in the browser to get the bank slip for the current ordershopper-pp-cli subscription pause — Open the subscription-pause page in the browser (POST /shop/carrinho/pause/ requires session cookie)shopper-pp-cli subscription resume — Open the subscription-resume page in the browser (POST /shop/carrinho/play/ requires session cookie)shopper-pp-cli payment cards — Show saved payment card count and open card-management in the browser (card add/delete is browser-requiredcart list-summary answers "how much", cart list-items answers "what". Line totals are sorted biggest-first, and paused products are listed apart so they never inflate the active count.
shopper-pp-cli cart list-items --store programada --agentPOST /cart/remove decrements a line by exactly one unit per call and ignores the quantity it is given, so the CLI issues one call per unit and stops early once the line is empty.
# Take 3 units of product 36756 off the Compra Unica basket.
shopper-pp-cli cart remove --id 36756 --quantity 3 --store unica --agent
# Confirm the line is gone.
shopper-pp-cli cart list-items --store unica --agentcluster_id is an independent dimension, not a copy of the store id — five of the six storefronts share cluster 1 and only the ultra-fast pair sits on cluster 11. stores compares the CLI's baked table against the live payload and prints a store table drift warning on stderr if they disagree.
shopper-pp-cli stores --agent 2>drift.txt; cat drift.txtshopper-pp-cli charge-calendar --store programada --agent --select next_delivery_date,edit_lock_date,charge_dateReturns the key dates for the next cycle; compare edit_lock_date to today to know if the basket can still be changed.
shopper-pp-cli cashback optimize --store programada --agentComputes the cheapest catalog additions to cross the next cashback threshold using your live cart and synced product data.
shopper-pp-cli orders spend --agent --select store,month,totalQueries all 6 storefronts and returns a month-by-store spend matrix for budgeting analysis.
shopper-pp-cli price-watch --store programada --agent --select product_id,name,price_now,price_baseline,change_pctScans synced price history for products in your basket and flags meaningful price movements.
shopper-pp-cli checkout preview --store programada --agent --select total_amount,delivery_date,charge_date,min_order_met,payment_methodsAggregates cart/delivery/payment data so an agent can confirm basket readiness before directing the user to open the checkout browser.
Set SHOPPER_TOKEN to your Shopper JWT (from the siteapi Authorization header in browser DevTools). Run 'shopper-pp-cli doctor' to verify. The token is long-lived for the subscription cycle. Never store raw card numbers or CPF in config; card management always opens the browser.
Run shopper-pp-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
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:
shopper-pp-cli address --agent --select id,name,statusPreviewable — --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 retries — use --idempotent only when an already-existing create should count as success
Commands that read from the local store or the API wrap output in a provenance envelope:
{
"meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
"results": <data>
}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.
Agents should treat the CLI's path resolver as part of the runtime contract:
Use --home <dir> for one invocation, or set SHOPPER_HOME=<dir> to relocate all four path kinds under one root.
Use per-kind env vars only when a specific kind must diverge: SHOPPER_CONFIG_DIR, SHOPPER_DATA_DIR, SHOPPER_STATE_DIR, SHOPPER_CACHE_DIR.
Resolution order is per-kind env var, --home, SHOPPER_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 shopper-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:
{
"mcpServers": {
"shopper": {
"command": "shopper-pp-mcp",
"env": {
"SHOPPER_HOME": "/srv/shopper"
}
}
}
}Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use SHOPPER_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 SHOPPER_HOME, or doctor will not find credentials left under the former root.
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.
recall before any discoveryBefore list/search/drill commands on a new user question, run:
shopper-pp-cli recall "<user's question>" --agentThe response envelope:
{
"query": "...",
"normalized": "<normalized form>",
"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": ["<trial command>", "shopper-pp-cli learnings confirm 12"] }
],
"playbook": {
"query_family": "...",
"playbook": {
"steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
"entity_slots": ["$ENTITY"],
"expected_tool_calls": 3
},
"slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
"notes": "<workarounds + gotchas for this query family>"
},
"notes": "<duplicate surface for non-playbook callers>"
}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.
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 <id>` only after the trial verified the behavior.
Reject a wrong candidate with `learnings reject <id>`.
-> 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 `shopper-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 <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; shopper-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.
warningslow_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:<canonical> (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 shopper-pp-cli sync to refresh entity lookups.no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.teach & after finalizing your response - alwaysTeaching 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:
shopper-pp-cli teach --query "<user's question>" --resource-type <type> --resource <id1> --resource <id2>
# (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.
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:
# Common case: record both the resource learning AND the playbook in one call.
shopper-pp-cli teach \
--query "<user's question>" \
--resource <id> \
--playbook-file ~/playbooks/<shape>.json \
--playbook-notes-file ~/playbooks/<shape>-notes.md
# (append shell `&` to background it)
# Alternate: playbook-only (no resource to record alongside).
shopper-pp-cli teach-playbook \
--query "<user's question>" \
--playbook-file ~/playbooks/<shape>.json \
--notes-file ~/playbooks/<shape>-notes.mdPlaybook 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.
playbook amend & when your debug response identifies a correctionIf 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.
shopper-pp-cli playbook amend \
--query "<exact recall query string>" \
--add-note "<your concrete correction>"
# (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:
{meta, results}, payload nested two levels deeper than the docs claim).What does NOT belong in notes:
The amend command appends to the family's existing notes with a timestamped marker ([amend YYYY-MM-DDTHH:MMZ]: <text>). 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).
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:
If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend.
shopper-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.
--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.SHOPPER_NO_LEARN=true in the environment globally disables the pipeline.When you (or the agent) notice something off about this CLI, record it:
shopper-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
shopper-pp-cli feedback --stdin < notes.txt
shopper-pp-cli feedback list --json --limit 10Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless SHOPPER_FEEDBACK_ENDPOINT is set AND either --send is passed or SHOPPER_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.
Every command accepts --deliver <sink>. 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:<path> | Atomically write output to <path> (tmp + rename) |
webhook:<url> | 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.
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.
shopper-pp-cli profile save briefing --json
shopper-pp-cli --profile briefing address
shopper-pp-cli profile list --json
shopper-pp-cli profile show briefing
shopper-pp-cli profile delete briefing --yesExplicit 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.
| 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 |
Parse $ARGUMENTS:
help, or --help → show shopper-pp-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)go install github.com/mvanhorn/printing-press-library/library/commerce/shopper/cmd/shopper-pp-mcp@latestclaude mcp add shopper-pp-mcp -- shopper-pp-mcpclaude mcp listwhich shopper-pp-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:shopper-pp-cli <command> [subcommand] [args] --agentshopper-pp-cli <command> --help.© mvanhorn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in cli-skills/pp-shopper of mvanhorn/printing-press-library.
Open the folder on GitHubat commit 76de244
Pp Shopper next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pp Shopper this skillmvanhorn/printing-press-library | 2.1k | — | ~9.3k | Automated safety check: Notes | Apache-2.0 | |
| React Router Developmentremix-run/react-router | 57k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| React UI State PatternsChrisWiles/claude-code-showcase | 6.1k | 8 repos | ~1.6k | Automated safety check: Pass | None | |
| GSAP in Vue, Nuxt and Sveltegreensock/gsap-skills | 16k | 4 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Svelte Core Best Practicesrilldata/rill | 2.9k | 4 repos | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Vuetify Playgroundvuetifyjs/vuetify | 41k | — | ~730 | Automated safety check: Pass | Custom licence |
remix-run/react-router
Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.
ChrisWiles/claude-code-showcase
Sets patterns for React interfaces: when to show loading spinners or skeletons, how to surface errors, how to disable buttons during async work and how to handle empty lists.
greensock/gsap-skills
Shows how to use GSAP in Vue, Nuxt, Svelte and other lifecycle-based frameworks: create after mount, scope selectors to the component, and revert on unmount.
rilldata/rill
Rules for writing idiomatic Svelte 5 code: when to reach for runes like state, derived and effect, and how to handle props, attachments and bindings.
vuetifyjs/vuetify
Maintains the Vuetify repo's local Playground.vue so contributors get a realistic reproduction and a short demo they can paste into a pull request description.
tabler/tabler
Starts the right Tabler dev server, keeps it from clashing with builds and verifies changes in the browser before a page or component is handed back.
mvanhorn/printing-press-library
Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.
mvanhorn/printing-press-library
Search, browse, and download Google Fonts from the terminal via the gfonts CLI.
mvanhorn/printing-press-library
The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.
mvanhorn/printing-press-library
Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.
mvanhorn/printing-press-library
Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...
mvanhorn/printing-press-library
macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.
Categories
Every Shopper storefront in one CLI — catalog, cart, delivery schedule, charge calendar, and spend analytics no web UI surfaces. Pp Shopper is an agent skill from mvanhorn/printing-press-library. Every Shopper storefront in one CLI — catalog, cart, delivery schedule, charge calendar, and spend analytics no web UI surfaces.
Pp Shopper fits situations like: phrases: check my Shopper basket; is my next Shopper delivery; will Shopper charge me; show my Shopper spend.
Run `npx skills add mvanhorn/printing-press-library --skill pp-shopper -a claude-code`. Or copy the skill folder (cli-skills/pp-shopper in mvanhorn/printing-press-library) into .claude/skills/pp-shopper in your project. Claude Code loads it when a task matches its description.
Run `npx skills add mvanhorn/printing-press-library --skill pp-shopper -a codex`. Or copy the skill folder (cli-skills/pp-shopper in mvanhorn/printing-press-library) into .agents/skills/pp-shopper in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-shopper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-shopper, .gemini/skills/pp-shopper, .github/skills/pp-shopper and .opencode/skills/pp-shopper in your project.
Going by SKILL.md and its folder, Pp Shopper needs the command-line tools its instructions call (go, claude and npx) and credentials named SHOPPER_TOKEN. Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
Pp Shopper is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 9.3k tokens (SKILL.md is roughly 37k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Pp Shopper: React Router Development (remix-run/react-router, 57k stars), React UI State Patterns (ChrisWiles/claude-code-showcase, 6.1k stars), GSAP in Vue, Nuxt and Svelte (greensock/gsap-skills, 16k stars) and Svelte Core Best Practices (rilldata/rill, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,056 GitHub stars. The repository holds 506 skills in this directory. The repository was last updated on October 9, 2026.
Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.