Agent skill

Pp Postmark

by mvanhorn in mvanhorn/printing-press-library

One account token for every Postmark server, and a local archive that outlasts Postmark's 45-day retention.

Apache-2.0Auto-check: notes

Install Pp Postmark

skills CLI
$ npx skills add mvanhorn/printing-press-library --skill pp-postmark -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mvanhorn/printing-press-library pp-postmark --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ 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-postmark .claude/skills/pp-postmark && rm -rf skills-src

Use ~/.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/

Facts

Skill name
pp-postmark
GitHub stars
2.1k
Token cost
~10k tokens
SKILL.md length
4,612 words
Files
1
Skills in repo
505
Repo updated
First seen
Licence
Apache-2.0

At a glance

One account token for every Postmark server, and a local archive that outlasts Postmark's 45-day retention.

  • Works in 6 steps: recall before any discovery → decision tree → always read warnings → …
  • Phrases: did my email get delivered
  • SKILL.md covers Prerequisites: Install the CLI, When to Use This CLI, Anti-triggers and Unique Capabilities, plus 7 more sections
  • Calls go, claude and npx; needs POSTMARK_SERVER_TOKEN and POSTMARK_ACCOUNT_TOKEN

What it does

Pp Postmark is an agent skill from mvanhorn/printing-press-library. One account token for every Postmark server, and a local archive that outlasts Postmark's 45-day retention. Trigger phrases: did my email get delivered, check postmark bounces, why didn't they get the reset email, push postmark templates, postmark sending stats this week, set up postmark for a new project, use postmark, run postmark.

Its SKILL.md is about 10k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

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.

When your agent uses it

  • Phrases: did my email get delivered
  • Check postmark bounces
  • Why didnt they get the reset email
  • Push postmark templates

Example prompts

  • “/pp-postmark”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. recall before any discovery
  2. decision tree
  3. always read warnings
  4. teach & after finalizing your response - always
  5. playbooks - optional flags, automatic synthesis
  6. playbook amend & when your debug response identifies a correction

What it can do on your machine

Read from SKILL.md and the folder at commit 0fdcc7a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go
    • claude
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    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.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • POSTMARK_SERVER_TOKEN
    • POSTMARK_ACCOUNT_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pp Postmark loads about 10k tokens when it runs. Until then it costs about 91 tokens; SKILL.md has 4,612 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~91
When it runs · the whole SKILL.md, loaded when a task matches
~10k

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.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash

Automated 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.

SKILL.md

The full file from mvanhorn/printing-press-library at commit 0fdcc7a, republished under its Apache-2.0 licence (© mvanhorn). 4,612 words, ~10,457 tokens.

Download SKILL.mdSave it as .claude/skills/pp-postmark/SKILL.md (or your agent's skills folder).
name
pp-postmark
description
One account token for every Postmark server, and a local archive that outlasts Postmark's 45-day retention. Trigger phrases: `did my email get delivered`, `check postmark bounces`, `why didn't they get the reset email`, `push postmark templates`, `postmark sending stats this week`, `set up postmark for a new project`, `use postmark`, `run postmark`.
allowed-tools
Read, Bash
author
Cathryn Lavery
license
Apache-2.0
argument-hint
<command> [args] | install cli|mcp
<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/productivity/postmark/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/". -->

Postmark — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the postmark-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 postmark --cli-only
  2. Verify: postmark-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/productivity/postmark/cmd/postmark-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.

Postmark gives every server its own token and keeps message history for 45 days by default. This CLI takes one account token and works across all your servers. Pick a server by name with --server, sync messages and bounces into a local SQLite archive that keeps what Postmark expires, and ask questions that span the account, like which server stopped sending or why one customer never got a password reset. It covers all 87 documented API operations, including message streams, webhooks, suppressions, and bulk email, which Postmark's official specs leave out.

Sending is safe to hand to an agent. Send commands print a preview until you add --send, --sandbox validates a message with Postmark's test token without delivering it, and email send-once won't send the same message twice when a script retries.

When to Use This CLI

Use this CLI to operate Postmark from a terminal or an agent: check whether a specific recipient got an email, triage bounces and suppressions, move templates between servers and gate them in CI, send transactional mail safely, and watch sending health across every server in one account. The local archive answers questions about messages older than Postmark's retention window.

Anti-triggers

Do not use this CLI for:

  • Do not use it for Postmark billing, team members, or account settings that only exist in the web dashboard.
  • Do not use it for DMARC digest reports; those come from Postmark's separate DMARC API with its own token.
  • Do not use it to receive inbound email in real time; configure an inbound webhook instead.
  • Do not use it for newsletter list management; Postmark sends broadcasts but does not manage subscriber lists.

Unique Capabilities

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

Account-wide oversight
  • pulse — Compares each server, stream, or tag with its own recent weeks and flags any that stopped sending, dropped off, or spiked in bounces or spam, across every server on the account token.

    A mailer that breaks quietly stops sending instead of throwing errors, so run this weekly to catch the drop.

    bash
    postmark-pp-cli pulse --window 7d --baseline 28d --agent
  • recipient-domains — Groups sends, bounces by type, complaints, suppressions, and opens by the recipient's mailbox domain across every synced server, so one provider's problem stands out. Run sync first.

    Start here when several missing-email reports come from the same provider or company.

    bash
    postmark-pp-cli recipient-domains --window 7d --min-sent 20 --agent
  • servers bootstrap — Creates a new project's Postmark server with its message streams, webhooks, sending-domain DNS records, and templates copied from another server. Prints the plan until you add --apply.

    Hand this to an agent setting up email for a new project. Reruns never create a duplicate server.

    bash
    postmark-pp-cli servers bootstrap "Lumen" --broadcast-stream --agent
Safe sending
  • email send-once — Sends an email at most once per key within a window (15 minutes by default), so an agent or script that retries after an error cannot deliver a second copy. Previews until you add --send.

    Built for one-time codes, receipts, and follow-ups that an agent might retry.

    bash
    postmark-pp-cli email send-once --key otp-4821 --from "$SENDER" --to "$RECIPIENT" --subject "Your code" --text "Code: 4821" --agent
Templates as code
  • templates check — Validates every template and layout on a server or in a pulled folder, and exits non-zero on render errors, missing test-model keys, or broken layout links.

    Run it in CI before pushing template changes to a server.

    bash
    postmark-pp-cli templates check --agent

Command Reference

bounces — Manage bounces

  • postmark-pp-cli bounces activate — Activate a bounce
  • postmark-pp-cli bounces delivery-stats — Get delivery stats
  • postmark-pp-cli bounces dump — Get bounce dump
  • postmark-pp-cli bounces get — Get a single bounce
  • postmark-pp-cli bounces list — Get bounces

clicks — Manage clicks

  • postmark-pp-cli clicks get — Retrieve Message Clicks
  • postmark-pp-cli clicks list — Clicks for a all messages

data_removals — Manage data removals

  • postmark-pp-cli data-removals create — Request irreversible removal of a recipient's data (enabled on request by Postmark)
  • postmark-pp-cli data-removals get — Check a data removal request

domains — Manage domains

  • postmark-pp-cli domains create — Create a Domain
  • postmark-pp-cli domains delete — Delete a Domain
  • postmark-pp-cli domains get — Get a Domain
  • postmark-pp-cli domains list — List Domains
  • postmark-pp-cli domains rotate-dkim — Creates a new DKIM key to replace your current key.
  • postmark-pp-cli domains update — Update a Domain
  • postmark-pp-cli domains verify-dkim — Request DNS Verification for DKIM
  • postmark-pp-cli domains verify-return-path — Request DNS Verification for Return-Path
  • postmark-pp-cli domains verify-spf — Request DNS Verification for SPF (deprecated by Postmark)

email — Manage email

  • postmark-pp-cli email bulk-list — List bulk requests on this server, newest first
  • postmark-pp-cli email bulk-status — Get the status of one bulk request
  • postmark-pp-cli email send — Send a single email
  • postmark-pp-cli email send-batch — Send a batch of emails
  • postmark-pp-cli email send-batch-with-templates — Send a batch of email using templates.
  • postmark-pp-cli email send-bulk — Send one message to many recipients (bulk). Requires account approval.
  • postmark-pp-cli email send-with-template — Send an email using a Template

inbound — Manage inbound

  • postmark-pp-cli inbound bypass — Bypass rules for a blocked inbound message
  • postmark-pp-cli inbound get — Inbound message details
  • postmark-pp-cli inbound list — Inbound message search
  • postmark-pp-cli inbound retry — Retry a failed inbound message for processing

inbound_rules — Manage inbound rules

  • postmark-pp-cli inbound-rules create — Create an inbound rule trigger
  • postmark-pp-cli inbound-rules delete — Delete a single trigger
  • postmark-pp-cli inbound-rules list — List inbound rule triggers

messages — Manage messages

  • postmark-pp-cli messages dump — Outbound message dump
  • postmark-pp-cli messages get — Outbound message details
  • postmark-pp-cli messages list — Outbound message search

opens — Manage opens

  • postmark-pp-cli opens get — Retrieve Message Opens
  • postmark-pp-cli opens list — Opens for all messages

senders — Manage senders

  • postmark-pp-cli senders create — Create a Sender Signature
  • postmark-pp-cli senders delete — Delete a Sender Signature
  • postmark-pp-cli senders get — Get a Sender Signature
  • postmark-pp-cli senders list — List Sender Signatures
  • postmark-pp-cli senders request-new-dkim — Requests a new DKIM key to be created.
  • postmark-pp-cli senders resend-confirmation — Resend Signature Confirmation Email
  • postmark-pp-cli senders update — Update a Sender Signature
  • postmark-pp-cli senders verify-spf — Request DNS Verification for SPF (deprecated by Postmark)

server — Manage server

  • postmark-pp-cli server get — Get Server Configuration
  • postmark-pp-cli server update — Edit Server Configuration

servers — Manage servers

  • postmark-pp-cli servers create — Create a Server
  • postmark-pp-cli servers delete — Delete a Server
  • postmark-pp-cli servers get — Get a Server
  • postmark-pp-cli servers list — List servers
  • postmark-pp-cli servers update — Edit a Server

stats — Manage stats

  • postmark-pp-cli stats bounces — Get bounce counts
  • postmark-pp-cli stats click-browsers — Get browser usage by family
  • postmark-pp-cli stats click-locations — Get clicks by body location
  • postmark-pp-cli stats click-platforms — Get browser plaform usage
  • postmark-pp-cli stats clicks — Get click counts
  • postmark-pp-cli stats open-clients — Get email client usage
  • postmark-pp-cli stats open-platforms — Get email platform usage
  • postmark-pp-cli stats open-read-times — Open counts by read time (seconds spent reading)
  • postmark-pp-cli stats opens — Get email open counts
  • postmark-pp-cli stats overview — Get outbound overview
  • postmark-pp-cli stats sends — Get sent counts
  • postmark-pp-cli stats spam — Get spam complaints
  • postmark-pp-cli stats tracked — Get tracked email counts

streams — Manage streams

  • postmark-pp-cli streams archive — Archive a message stream (purged 45 days later unless unarchived)
  • postmark-pp-cli streams create — Create a message stream
  • postmark-pp-cli streams get — Get one message stream
  • postmark-pp-cli streams list — List message streams on this server
  • postmark-pp-cli streams unarchive — Restore an archived message stream before its purge date
  • postmark-pp-cli streams update — Edit a message stream

suppressions — Manage suppressions

  • postmark-pp-cli suppressions create — Suppress up to 50 addresses on a message stream
  • postmark-pp-cli suppressions delete — Remove up to 50 suppressions from a message stream (SpamComplaint suppressions cannot be removed)
  • postmark-pp-cli suppressions list — List suppressed addresses on a message stream

templates — Manage templates

  • postmark-pp-cli templates create — Create a Template
  • postmark-pp-cli templates delete — Delete a Template
  • postmark-pp-cli templates get — Get a Template
  • postmark-pp-cli templates list — Get the Templates associated with this Server
  • postmark-pp-cli templates push-between-servers — Push templates from one server to another
  • postmark-pp-cli templates update — Update a Template
  • postmark-pp-cli templates validate — Test Template Content

webhooks — Manage webhooks

  • postmark-pp-cli webhooks create — Create a webhook
  • postmark-pp-cli webhooks delete — Delete a webhook
  • postmark-pp-cli webhooks get — Get one webhook
  • postmark-pp-cli webhooks list — List webhooks on this server
  • postmark-pp-cli webhooks statistics — Delivery statistics for one webhook over the last 24 hours
  • postmark-pp-cli webhooks update — Edit a webhook (omitted triggers stay unchanged)
  • postmark-pp-cli webhooks verify — Send a test request for each enabled trigger and record verified or unverified
Finding the right command

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

bash
postmark-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. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.

Hand-written Extensions

These commands are hand-written on top of the generated endpoint commands. They follow the same output flags (--json, --agent, --select, --csv) and the global --server <name> and --sandbox flags. Server tokens are masked in every response.

  • postmark-pp-cli diagnose [email]: one recipient's recent messages, bounces, and suppressions with a verdict (delivered, sent, bounced, suppressed, spam_complaint, queued, not_found) and the next command to run. --all-servers checks every server.
  • postmark-pp-cli overview: every server in the account with this window's sends, bounces, spam complaints, and stream count.
  • postmark-pp-cli servers tokens [name]: print the full API token for one server or all servers; the only command that reveals tokens, never cached or stored, and not exposed over MCP.
  • postmark-pp-cli servers use [name]: save the default server and optional default sender and stream for send commands.
  • postmark-pp-cli templates pull <dir>: write every template and layout to disk in the official postmark-cli folder layout, with no template cap.
  • postmark-pp-cli templates push <dir>: diff a template folder against the server; prints the plan unless --yes is given, and --prune --yes removes templates missing locally only after every local template was pushed.
  • postmark-pp-cli templates render [alias]: render one template (remote or from a pulled folder) with its layout and test model.
  • postmark-pp-cli suppressions check <email>: whether an address is suppressed on each message stream, with the command that removes it (SpamComplaint suppressions cannot be removed).
  • postmark-pp-cli bounces reactivate: plan reactivation of inactive, reactivatable bounces filtered by type, domain, email, window, and --stream (default outbound); --yes reactivates them.
  • postmark-pp-cli bounces resend-blocked: plan resending messages that hard-bounced, to the bounced recipient only, on --stream (default outbound); --send reactivates and resends.
  • postmark-pp-cli webhooks health: 24-hour delivery statistics and verification status for each webhook, flagging failures.
  • postmark-pp-cli domains health: DKIM, Return-Path, and sender confirmation status with the fix command for each failure.
  • postmark-pp-cli streams health: bounce and spam rates per message stream against the 10% and 0.1% thresholds.
  • postmark-pp-cli service-status: Postmark's public status page, current state and open notices.

The generated email send, send-with-template, send-batch, send-batch-with-templates, and send-bulk commands print the request they would make unless --send is given. --sandbox validates a send with Postmark's POSTMARK_API_TEST token and never delivers.

For the hand-written commands, --dry-run only confirms the command resolves. To see what one would do, run it without --send, --apply, or --yes: email send-once, bounces resend-blocked, servers bootstrap, templates push, and bounces reactivate print their plan and change nothing until given that flag.

sync --full never prunes here, so messages Postmark has expired and rows synced from other servers stay in the local archive. --no-prune=false is refused; to start a fresh archive, sync into a new file with --db <path>.

Syncing a different server into the same database resets the sync checkpoints and reads that server from the beginning, without pruning. Syncs into one database take turns.

If email send-once cannot tell whether Postmark accepted a message (a timeout or a 5xx), it keeps the key reserved for the window and later runs report delivery_unknown instead of sending again.

Over MCP, postmark_execute returns a preview instead of calling the API for every DELETE and for data removals, stream archives, suppression deletes, and template pushes between servers, unless the call includes confirm: true.

Recipes

Monday health pass
bash
postmark-pp-cli pulse --window 7d --baseline 28d --agent

Compares each server's last week against its prior four and lists anything that stopped, dropped, or spiked.

Why didn't they get the reset email
bash
postmark-pp-cli diagnose jane@example.com --server "Staging" --agent

Checks outbound messages, bounces, and suppressions for one address and returns a verdict with the fix command.

bash
postmark-pp-cli messages list --recipient jane@example.com --count 50 --offset 0 --agent --select MessageID,Subject,Status,ReceivedAt

Keeps only the fields an agent needs from a large outbound search response.

One-time code without double sends
bash
postmark-pp-cli email send-once --key otp-4821 --server "Production" --from app@example.com --to jane@example.com --subject "Your code" --text "Code: 4821"

Prints the payload and dedupe decision; add --send to deliver, and a retry with the same key returns the original MessageID.

Gate template changes in CI
bash
postmark-pp-cli templates check --dir ./templates --server "Production"

Validates every template and layout in a pulled folder and exits non-zero on any failure.

Spin up email for a new project
bash
postmark-pp-cli servers bootstrap "Lumen" --domain lumen.example.com --broadcast-stream --agent

Prints the server, stream, and domain plan with the Return-Path DNS record; the DKIM record appears after --apply creates the domain, and a rerun never duplicates the server.

Auth Setup

Postmark has two kinds of token. A server token (X-Postmark-Server-Token) covers one server: sending, messages, bounces, templates, stats, streams, suppressions, and webhooks. The account token (X-Postmark-Account-Token) covers servers, domains, sender signatures, template pushes between servers, and data removals. The CLI sends only the header each endpoint accepts.

The simplest setup is the account token alone. Set POSTMARK_ACCOUNT_TOKEN, choose a server with --server <name> or POSTMARK_SERVER, and the CLI looks up that server's token through the account API. servers use <name> saves a default server.

If you only use one server, export POSTMARK_SERVER_TOKEN instead, or store it with auth set-token, which reads the token from stdin. --server and POSTMARK_SERVER take precedence over POSTMARK_SERVER_TOKEN, which takes precedence over the saved default.

--sandbox swaps in Postmark's POSTMARK_API_TEST token, so sends are validated but never delivered.

Run postmark-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color.

Global format flags share one contract on promoted, novel, sync, and --deliver paths:

  • --json — one JSON document on stdout (sync progress events go to stderr)

  • --compact — keep identity/status/timestamp fields; does not change the document vs stream shape

  • --csv / --plain — tabular rows (collection envelopes unwrap to the row array)

  • --quiet — one identity value per row, no envelope

  • 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
    postmark-pp-cli bounces list --count 100 --offset 0 --agent --select BouncedAt,CanActivate,Content
  • Previewable — --dry-run shows the request without sending

  • Offline-friendly — sync/search commands can use the local SQLite store when available

  • Non-interactive — never prompts, every input is a flag

  • Explicit confirmation — --agent does not imply --yes; pass --yes separately only after the target, arguments, and side effects are clear

  • Explicit retries — use --idempotent only when an already-existing create should count as success, and use --ignore-missing only when a missing delete target 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.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

  • Use --home <dir> for one invocation, or set POSTMARK_HOME=<dir> to relocate all four path kinds under one root.

  • Use per-kind env vars only when a specific kind must diverge: POSTMARK_CONFIG_DIR, POSTMARK_DATA_DIR, POSTMARK_STATE_DIR, POSTMARK_CACHE_DIR.

  • Resolution order is per-kind env var, --home, POSTMARK_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 and data.db (the local archive and send-once ledger). 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 postmark-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": {
        "postmark": {
          "command": "postmark-pp-mcp",
          "env": {
            "POSTMARK_HOME": "/srv/postmark"
          }
        }
      }
    }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use POSTMARK_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 POSTMARK_HOME, or doctor will not find credentials left under the former root.

Show full SKILL.md (1,858 more words)Show less

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, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.

Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

bash
# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
postmark-pp-cli recall "$QUERY" --agent

Prefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

json
{
  "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>", "postmark-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.

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 <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 `postmark-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; postmark-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:<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 postmark-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. Pass the query the same way as recall — argv/MCP, or file-then-$QUERY. Do not splice the question into the command text:

bash
QUERY=$(cat /path/to/question.txt)
postmark-pp-cli teach --query "$QUERY" --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.

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.
QUERY=$(cat /path/to/question.txt)
postmark-pp-cli teach \
  --query "$QUERY" \
  --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).
QUERY=$(cat /path/to/question.txt)
postmark-pp-cli teach-playbook \
  --query "$QUERY" \
  --playbook-file ~/playbooks/<shape>.json \
  --notes-file ~/playbooks/<shape>-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. Pass the query and note as argv/MCP arguments, or write each with a non-shell file tool and read them back (QUERY=$(cat ...), NOTE=$(cat ...)). Do not interpolate either string into the command text:

bash
QUERY=$(cat /path/to/question.txt)
NOTE=$(cat /path/to/note.txt)
postmark-pp-cli playbook amend \
  --query "$QUERY" \
  --add-note "$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]: <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).

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

postmark-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.
  • POSTMARK_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:

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

Entries are stored locally as feedback.jsonl under the resolved data dir. They are never POSTed unless POSTMARK_FEEDBACK_ENDPOINT is set AND either --send is passed or POSTMARK_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). Binary-response commands write decoded payload bytes (not the base64 JSON envelope) and print a small JSON receipt on stdout; --json/--csv do not refuse when this sink is set.
webhook:<url>POST the output body to the URL (application/json)

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.

postmark-pp-cli profile save briefing --json
postmark-pp-cli --profile briefing bounces list --count 100 --offset 0
postmark-pp-cli profile list --json
postmark-pp-cli profile show briefing
postmark-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)
6Partial failure
7Rate limited (wait and retry)
10Config error

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show postmark-pp-cli --help output
  2. Starts with install → ends with mcp → MCP installation; otherwise → see Prerequisites above
  3. Anything else → Direct Use (execute as CLI command with --agent)

MCP Server Installation

  1. Install the MCP server:
    bash
    go install github.com/mvanhorn/printing-press-library/library/productivity/postmark/cmd/postmark-pp-mcp@latest
  2. Register with Claude Code:
    bash
    claude mcp add postmark-pp-mcp -- postmark-pp-mcp
  3. Verify: claude mcp list

Direct Use

  1. Check if installed: which postmark-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
    postmark-pp-cli diagnose jane@example.com --agent
  4. If ambiguous, drill into subcommand help, for example postmark-pp-cli templates --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

Files

Just SKILL.md in cli-skills/pp-postmark of mvanhorn/printing-press-library.

Open the folder on GitHubat commit 0fdcc7a

Compare with similar skills

Pp Postmark 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.

Pp Postmark compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pp Postmark this skillmvanhorn/printing-press-library2.1k—~10kAutomated safety check: NotesApache-2.0
Expense Accountingsickn33/agentic-awesome-skills47k1 repos~6.5kAutomated safety check: PassMIT
Purchase Accountingsickn33/agentic-awesome-skills47k1 repos~5.1kAutomated safety check: PassMIT
Odoo Accounting Setupsickn33/agentic-awesome-skills47k2 repos~1kAutomated safety check: PassMIT
Accounting Software Selectionsickn33/agentic-awesome-skills47k1 repos~7.4kAutomated safety check: PassMIT
Sales Accountingsickn33/agentic-awesome-skills47k1 repos~6.4kAutomated safety check: PassMIT

Similar skills

  • Expense Accounting

    sickn33/agentic-awesome-skills

    Expense accounting register: expense number and date, payee with PAN and VAT, bill reference, document type, amount with VAT, ledger account, approver and status.

    47k GitHub starsUsed in 1 repo~6.5k tokens
    Business, Finance & HRAuto-check passed
  • Purchase Accounting

    sickn33/agentic-awesome-skills

    Purchase register: supplier, invoice, gross amount, VAT and TDS, net payable, ledger account and payment balance.

    47k GitHub starsUsed in 1 repo~5.1k tokens
    Business, Finance & HRAuto-check passed
  • Odoo Accounting Setup

    sickn33/agentic-awesome-skills

    Expert guide for configuring Odoo Accounting: chart of accounts, journals, fiscal positions, taxes, payment terms, and bank reconciliation.

    47k GitHub starsUsed in 2 repos~1k tokens
    Business, Finance & HRAuto-check passed
  • Accounting Software Selection

    sickn33/agentic-awesome-skills

    Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request.

    47k GitHub starsUsed in 1 repo~7.4k tokens
    Business, Finance & HRAuto-check passed
  • Sales Accounting

    sickn33/agentic-awesome-skills

    Sales register: customer, invoice, gross amount, discount, VAT and TDS, net receivable, credit terms and balance.

    47k GitHub starsUsed in 1 repo~6.4k tokens
    Business, Finance & HRAuto-check passed
  • Payment Accounting

    sickn33/agentic-awesome-skills

    Payment voucher register: payment number and date, paid to and purpose, mode, gross amount, TDS rate and deducted, net paid, invoice allocation, ledger and reconciliation status.

    47k GitHub starsUsed in 1 repo~5.5k tokens
    Business, Finance & HRAuto-check passed

More from mvanhorn/printing-press-library

All 505 skills in this repo
  • Agent Desktop

    mvanhorn/printing-press-library

    Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

    2.1k GitHub stars~2.3k tokensUpdated today
    Auto-check: notes
  • Gfonts

    mvanhorn/printing-press-library

    Search, browse, and download Google Fonts from the terminal via the gfonts CLI.

    2.1k GitHub stars~574 tokensUpdated today
    Auto-check passed
  • Pp 1688

    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.

    2.1k GitHub stars~3k tokensUpdated today
    Auto-check: notes
  • Pp Activity Japan

    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.

    2.1k GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • Pp Adminbyrequest

    mvanhorn/printing-press-library

    Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...

    2.1k GitHub stars~3.3k tokensUpdated today
    Auto-check: notes
  • Pp Agent Capture

    mvanhorn/printing-press-library

    macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.

    2.1k GitHub stars~1.6k tokensUpdated today
    Auto-check: notes

Questions about Pp Postmark

What does Pp Postmark do?

One account token for every Postmark server, and a local archive that outlasts Postmark's 45-day retention. Pp Postmark is an agent skill from mvanhorn/printing-press-library. One account token for every Postmark server, and a local archive that outlasts Postmark's 45-day retention.

When should I use Pp Postmark?

Pp Postmark fits situations like: phrases: did my email get delivered; check postmark bounces; why didnt they get the reset email; push postmark templates.

How do I install Pp Postmark in Claude Code?

Run `npx skills add mvanhorn/printing-press-library --skill pp-postmark -a claude-code`. Or copy the skill folder (cli-skills/pp-postmark in mvanhorn/printing-press-library) into .claude/skills/pp-postmark in your project. Claude Code loads it when a task matches its description.

How do I install Pp Postmark in Codex?

Run `npx skills add mvanhorn/printing-press-library --skill pp-postmark -a codex`. Or copy the skill folder (cli-skills/pp-postmark in mvanhorn/printing-press-library) into .agents/skills/pp-postmark in your project. Codex loads it when a task matches its description.

Can I use Pp Postmark in Cursor, Gemini CLI or GitHub Copilot?

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-postmark -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-postmark, .gemini/skills/pp-postmark, .github/skills/pp-postmark and .opencode/skills/pp-postmark in your project.

What does Pp Postmark need to run?

Going by SKILL.md and its folder, Pp Postmark needs the command-line tools its instructions call (go, claude and npx) and credentials named POSTMARK_SERVER_TOKEN and POSTMARK_ACCOUNT_TOKEN. Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.

Does Pp Postmark access the network?

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.

Is Pp Postmark safe to install?

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.

What licence does Pp Postmark use?

Pp Postmark 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.

How many tokens does Pp Postmark use?

About 10k tokens (SKILL.md is roughly 42k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pp Postmark?

Skills that share tags, products or a category with Pp Postmark: Expense Accounting (sickn33/agentic-awesome-skills, 47k stars), Purchase Accounting (sickn33/agentic-awesome-skills, 47k stars), Odoo Accounting Setup (sickn33/agentic-awesome-skills, 47k stars) and Accounting Software Selection (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pp Postmark?

mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,053 GitHub stars. The repository holds 505 skills in this directory. The repository was last updated on October 7, 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.