Pp Bento logo

Pp Bento

CommunityPopular
mvanhorn
pp-bento

Every Bento feature, plus the ones their own CLI does not have. Trigger phrases: `import this list to Bento`, `scrub these emails before sending`, `show my Bento subscribers`, `build a win-back cohort`, `preview this Bento broadcast`, `sync Bento`, `use bento`, `run bento`.

Overview

Publishermvanhorn
Repositoryprinting-press-library
Skill namepp-bento
Stars
2K
Forks
614
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mvanhorn on GitHub. Read the source before you install it.

Installation

Install the Pp Bento AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git /tmp/printing-press-library
mkdir -p .claude/skills
cp -r /tmp/printing-press-library/cli-skills/pp-bento .claude/skills/pp-bento
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pp Bento in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pp Bento on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pp Bento is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bento — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the bento-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 bento --cli-only
  2. Verify: bento-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):

bash
go install github.com/mvanhorn/printing-press-library/library/marketing/bento/cmd/bento-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 bento-pp-cli when you need a fast offline view over your Bento account (FTS, JOINs, cohort builds), when you're scripting CI/CD imports, when you need transactional send from a Go process without dragging in Node, or when you're bridging Vendure / non-native ecom platforms to Bento via webhook + $purchase events. Pair with Claude Desktop / Cursor via MCP for natural-language access to every command.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Sync Integrity

  • sync diff — Show exactly which subscribers, tags, fields, or templates changed between two local snapshots since Bento has no since filter.

    Use this when you need to detect drift between Bento and your local source of truth, or audit what changed since the last sync.

    bash
    bento sync diff --since 2026-05-19 --resource subscribers --json
  • tags drift — Surface tags whose subscriber counts swung more than N% week-over-week, catching misfiring workflows.

    Run weekly to catch silently-broken automations adding or removing tags unexpectedly.

    bash
    bento tags drift --window 30d --threshold 25 --json

List Hygiene

  • hygiene scrub — Run validation + jesses_ruleset + blacklist + content_moderation in one pass and emit a clean CSV plus a rejected CSV with reasons.

    Reach for this before importing any list you didn't generate yourself. Bad list = ISP penalty.

    bash
    bento hygiene scrub --in leads.csv --out-clean clean.csv --out-rejected rejected.csv

Vendure Bridge

  • events purchase-replay — Dry-run a Vendure order export against the Bento $purchase mapping and show the exact batch payload before sending.

    Use before any Vendure -> Bento purchase sync to catch shape mismatches without polluting subscriber history.

    bash
    bento events purchase-replay --from vendure-orders.json --dry-run --json
  • events review-window — Emit a dated Bento event stream for orders shipped N days ago, skipping any order your existing third-party review platform already triggered.

    Use when running a Bento-side review trigger alongside a third-party review platform without double-mailing.

    bash
    bento events review-window --shipped-csv orders.csv --delay 10d --skip-stamped --dry-run
  • fields lint — Diff local custom fields against a Vendure customer-schema file and flag missing, renamed, or type-mismatched fields.

    Use after any Vendure schema change to verify Bento custom fields still align.

    bash
    bento fields lint --against vendure-schema.json --json

Safety Rails

  • events lint — Warn when a payload uses /fetch/commands subscribe but the intent (welcome flow, tag-triggered automation) requires /batch/events to fire automations.

    Run this on any payload bound for /fetch/commands or /batch/events to catch silent automation misfires.

    bash
    bento events lint --file events.jsonl --json
  • subscribers pre-delete — Show tags, events, revenue, and active automations a subscriber set carries before you file a GDPR data_deletion_request.

    Always run before any GDPR/CCPA batch deletion to confirm the right cohort and surface revenue impact.

    bash
    bento subscribers pre-delete --emails-from gdpr-batch.txt --json

Retention

  • subscribers churn-risk — Rank subscribers by days-since-last-open/click against your cohort baseline before the next broadcast goes out.

    Use before queuing a broadcast to identify the cohort most likely to mark as spam.

    bash
    bento subscribers churn-risk --threshold high --limit 100 --json
  • subscribers winback — Build a CSV of customers who bought once, lapsed 180+ days, and never opened the last 3 broadcasts.

    Reach for this when scoping a reactivation campaign with a custom decay window.

    bash
    bento subscribers winback --lapsed 180d --last-purchased 90d --csv

Campaign Planning

  • broadcasts whatif — Estimate audience size, predicted opens, and hygiene-risk count for a draft broadcast before you queue it in the dashboard.

    Use before any broadcast send to sanity-check audience size and deliverability risk.

    bash
    bento broadcasts whatif --segment seg_abc --json

Discovery

  • subscribers find — Full-text search subscriber notes/fields plus structured filters in one query, exportable as CSV.

    Reach for this when building any ad-hoc cohort that isn't worth a segment in the dashboard.

    bash
    bento subscribers find "first order" --tagged customer --purchased-after 365d --csv

Command Reference

batch — Manage batch

  • bento-pp-cli batch create — This endpoint allows you to create multiple email broadcasts efficiently.
  • bento-pp-cli batch create-emails — This endpoint allows you to create and send multiple emails efficiently.
  • bento-pp-cli batch create-events — This endpoint allows you to send multiple events to your site.
  • bento-pp-cli batch create-subscribers — This endpoint allows for efficient bulk creation and updating of subscribers.

experimental — Access experimental APIs designed for specific use cases. Use with caution as these may change.

  • bento-pp-cli experimental create — This endpoint will return an opinionated moderation score based on the content provided.
  • bento-pp-cli experimental create-gender — This endpoint allows you to guess the gender of a subscriber based on their first name and last name.
  • bento-pp-cli experimental create-validation — This experimental endpoint provides basic validation for email addresses and associated user information.
  • bento-pp-cli experimental list — This experimental endpoint allows you to check if a domain or IP address is present on various blacklists.
  • bento-pp-cli experimental list-geolocation — This endpoint allows you to geolocate an IP address.

fetch — Manage fetch

  • bento-pp-cli fetch create — This endpoint allows you to execute various commands to modify subscriber data.
  • bento-pp-cli fetch create-fields — Creates a new custom field in your account. Custom fields allow you to store additional data about your subscribers.
  • bento-pp-cli fetch create-subscribers — Creates a new subscriber in your account and queues them for indexing.
  • bento-pp-cli fetch create-tags — Creates a new tag in your account for subscriber segmentation.
  • bento-pp-cli fetch list — Fetches a list of all broadcasts in your account, providing an overview of your email campaigns.
  • bento-pp-cli fetch list-fields — Fetches a list of all custom fields defined in your account.
  • bento-pp-cli fetch list-search — This endpoint allows for advanced searching of your subscriber base.
  • bento-pp-cli fetch list-subscribers — Fetch detailed information about one or multiple subscribers in your account.
  • bento-pp-cli fetch list-tags — Fetches a list of all tags in your account. Tags are useful for segmenting your subscriber base.

stats — Retrieve statistical data about your account. IMPORTANT — Never use these endpoints in client-side code.

  • bento-pp-cli stats list — Fetches statistics for a specific segment in your account.
  • bento-pp-cli stats list-site — Fetches overall statistics for your site. This includes counts of users, subscribers, and unsubscribers.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

bash
bento-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

Pre-import list hygiene before any cold outreach

bash
bento hygiene scrub --in cold-leads.csv --out-clean clean.csv --out-rejected rejected.csv --json

Chains validation + jesses_ruleset + blacklist + content_moderation in one pipeline so a dirty list never tanks deliverability.

Vendure -> Bento purchase event with dedupe

bash
bento events purchase-replay --from vendure-orders.json --skip-already-tracked --json --select 'events[].email,events[].details.unique.key'

Maps Vendure order JSON to Bento $purchase shape, validates dedupe keys, and emits the batch payload. --select narrows the deep nested response to just the fields agents need to confirm.

Find lapsed VIPs for a win-back broadcast

bash
bento subscribers winback --lapsed 180d --last-purchased 90d --tagged vip --csv > winback.csv

Three-way local JOIN that no Bento segment builder supports.

Audit before a GDPR batch deletion

bash
bento subscribers pre-delete --emails-from gdpr-batch.txt --json

Shows revenue, active automations, and tag exposure for each email before you queue irreversible anonymization.

Catch silently-broken workflows via tag drift

bash
bento tags drift --window 7d --threshold 30 --json

Surfaces tags whose subscriber counts shifted more than 30% week-over-week.

Auth Setup

Bento uses HTTP Basic with publishable_key:secret_key, plus a site_uuid attached as ?site_uuid= on GETs and as a body field on POSTs. Set BENTO_PUBLISHABLE_KEY, BENTO_SECRET_KEY, and BENTO_SITE_UUID, or run bento auth set to store them in ~/.config/bento. The CLI sets a descriptive User-Agent automatically -- generic UAs are 403'd by Cloudflare.

Run bento-pp-cli doctor to verify setup.

Agent Mode

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:

    bash
    bento-pp-cli experimental list --agent --select id,name,status
  • 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 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": <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.

Agent Feedback

When you (or the agent) notice something off about this CLI, record it:

bento-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
bento-pp-cli feedback --stdin < notes.txt
bento-pp-cli feedback list --json --limit 10

Entries are stored locally at ~/.bento-pp-cli/feedback.jsonl. They are never POSTed unless BENTO_FEEDBACK_ENDPOINT is set AND either --send is passed or BENTO_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 <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:

SinkEffect
stdoutDefault; 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.

Named Profiles

A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.

bento-pp-cli profile save briefing --json
bento-pp-cli --profile briefing experimental list
bento-pp-cli profile list --json
bento-pp-cli profile show briefing
bento-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

CodeMeaning
0Success
2Usage error (wrong arguments)
3Resource not found
4Authentication required
5API error (upstream issue)
7Rate limited (wait and retry)
10Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show bento-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 bento-pp-mcp -- bento-pp-mcp

Verify: claude mcp list

Direct Use

  1. Check if installed: which bento-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
    bento-pp-cli <command> [subcommand] [args] --agent
  4. If ambiguous, drill into subcommand help: bento-pp-cli <command> --help.

Differences from the official Bento CLI

This CLI is an independent reimplementation. Compared to Bento's own @bentonow/bento-cli and bento-mcp, it adds:

  • Transactional email send (Ruby/PHP SDK only — not in the official CLI or MCP)
  • Batch commands API (/fetch/commands with subscribe/unsubscribe/add_tag) — only in the Python SDK upstream
  • Segments list/get endpoints — docs-only upstream
  • Every experimental endpoint (validation, jesses_ruleset, blacklist, content_moderation, gender, geolocation)
  • Data deletion requests endpoint (GDPR/CCPA)
  • A local SQLite store with FTS5 search across subscribers/tags/fields/broadcasts
  • 12 novel commands (snapshot diff, hygiene pipeline, purchase replay, churn-risk scoring, broadcast what-if, etc.) that have no upstream equivalent
  • Single Go binary — no Node runtime required
  • MCP server auto-derived from the Cobra command tree (every CLI command is reachable to agents)

Known Gaps

These are limits of the Bento API itself, not of this CLI. None of them can be solved by an API wrapper:

  • No broadcast send/schedule/stop endpoint. Broadcasts are dashboard-only — you can list and read them, but cannot trigger them via API.
  • No workflow create/edit/pause endpoint. Same — dashboard-only.
  • No sequence email reorder/delete endpoint. Edit individual emails inside a sequence in the dashboard.
  • No standalone email-template listing. Templates are only accessible nested under broadcasts and sequences.
  • No event history endpoint. Bento has POST /batch/events to write but no list endpoint to read event history back.
  • Bulk subscriber listing requires the Enterprise tier. Mitigated locally via subscribers fetch-batch (per-email pull) and subscribers import-csv (load a dashboard CSV export into the local store).
  • No subscriber DELETE. Use the GDPR /data_deletion_requests endpoint to anonymize.
  • No documented webhook signature verification. Bento does not publish a signing scheme for inbound webhooks.

Frequently asked questions

What does the Pp Bento AI skill do?

Every Bento feature, plus the ones their own CLI does not have. Trigger phrases: `import this list to Bento`, `scrub these emails before sending`, `show my Bento subscribers`, `build a win-back cohort`, `preview this Bento broadcast`, `sync Bento`, `use bento`, `run bento`.

Why use Pp Bento on TypingMind?

Because you install it once and use it with any model. Pp Bento is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pp Bento in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-bento. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pp Bento?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pp Bento?

As many as you like. As long as a model supports skills, you can use Pp Bento with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pp Bento AI skill free?

Yes. It is published on GitHub by mvanhorn under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇