Agent skill

Pp 1password

by mvanhorn in mvanhorn/printing-press-library

Printing Press CLI for 1Password. An agent skill from mvanhorn/printing-press-library.

Apache-2.0Auto-check: notes

Install Pp 1password

skills CLI
$ npx skills add mvanhorn/printing-press-library --skill pp-1password -a claude-code

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

GitHub CLI
$ gh skill install mvanhorn/printing-press-library pp-1password --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/library/auth/1password .claude/skills/pp-1password && 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-1password
GitHub stars
2.1k
Token cost
~3.8k tokens
SKILL.md length
1,528 words
Files
124
Skills in repo
506
Repo updated
First seen
Licence
Apache-2.0

At a glance

Printing Press CLI for 1Password. An agent skill from mvanhorn/printing-press-library.

  • Works in 3 steps: Install via the Printing Press… → Verify: 1password-pp-cli --version → Ensure the reported install directory is…
  • SKILL.md covers Prerequisites: Install the CLI, When Not to Use This CLI, Unique Capabilities and Recipes, plus 10 more sections
  • Calls go, claude and npx; needs API_TOKEN and OP_SERVICE_ACCOUNT_TOKEN

What it does

Pp 1password is an agent skill from mvanhorn/printing-press-library. Printing Press CLI for 1Password. Agent-safe command layer over the official 1Password CLI and SDK service-account workflows.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 128 other files (for example `.golangci.yml`, `.goreleaser.yaml` and `.manuscripts/20260608-220213/proofs/dogfood-research-sync.json`).

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.

Example prompts

  • “/pp-1password”

Requirements

  • Node.js
  • A credential in API_TOKEN
  • A credential in OP_SERVICE_ACCOUNT_TOKEN
  • Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and…
  2. Verify: 1password-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

What it can do on your machine

Read from SKILL.md and the folder at commit 76de244. 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:

    • API_TOKEN
    • OP_SERVICE_ACCOUNT_TOKEN

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

Context cost

Pp 1password loads about 3.8k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 1,528 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

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.

  • NoteMentions a .env fileSKILL.md:73
    t --task "deploy using op run --env-file .env" --json
  • NoteMentions a .env fileSKILL.md:77
    - **`env plan`** — Parse .env, config, or shell files for missing variables and map them to safe op:// references.
  • 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 76de244, republished under its Apache-2.0 licence (© mvanhorn). 1,528 words, ~3,760 tokens.

Download SKILL.mdSave it as .claude/skills/pp-1password/SKILL.md (or your agent's skills folder). This skill also uses 123 other files; get the full folder from GitHub.
name
pp-1password
description
Printing Press CLI for 1Password. Agent-safe command layer over the official 1Password CLI and SDK service-account workflows.
allowed-tools
Read, Bash
author
Cathryn Lavery
license
Apache-2.0
argument-hint
<command> [args] | install cli|mcp

1Password — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the 1password-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 1password --cli-only
  2. Verify: 1password-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/auth/1password/cmd/1password-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.

Use 1Password from agents without turning every task into a secret reveal. The CLI resolves fuzzy requests to exact op:// references, audits metadata, checks policy, and only calls op read, op inject, or op run after an explicit plan.

When Not to Use This CLI

Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI is intended for secret-reference planning, metadata audits, policy checks, and tightly gated local op read / op inject workflows.

Unique Capabilities

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

Secrets
  • secrets resolve — Resolve fuzzy agent requests to exact op:// vault/item/field references without printing values.

    Prevents accidental broad reads and gives later commands an exact reference to use.

    bash
    1password-pp-cli secrets resolve --query "token" --json
  • secrets read — Read only an exact op:// reference, with policy checks and an explicit --reveal gate before values are printed.

    Turns value access into a narrow, auditable action instead of a fuzzy search.

    bash
    1password-pp-cli secrets read op://Engineering/GitHub/token --dry-run --json
  • secrets explain — Explain why a particular item and field was selected for a task without revealing the field value.

    bash
    1password-pp-cli secrets explain --query "token" --json
  • secrets preflight — Check whether a planned task or command appears to require secret values, documents, cards, or write permissions.

    bash
    1password-pp-cli secrets preflight --task "deploy using op run --env-file .env" --json
Environment
  • env plan — Parse .env, config, or shell files for missing variables and map them to safe op:// references.

    bash
    1password-pp-cli env plan API_TOKEN= --json
  • env inject — Wrap op inject with a redacted plan first and require --write before producing an output file.

    bash
    1password-pp-cli env inject --in-file README.md --out-file injected.env --json
Items
  • items classify — Find secure notes that look like API credentials, logins, SSH keys, cards, or documents.

    bash
    1password-pp-cli items classify --json
  • items duplicates — Detect duplicate titles, URLs, usernames, and likely copied credentials across vaults without printing secret values.

    bash
    1password-pp-cli items duplicates --json
  • items ownership — Flag shared or service credentials missing owner, purpose, rotation, or environment tags.

    bash
    1password-pp-cli items ownership --json
Cards
  • cards audit — Find cards stored as notes or logins, missing owner/purpose tags, or CVV-like fields without printing card values.

    bash
    1password-pp-cli cards audit --json
  • cards resolve — Return card item and field references without printing card numbers, expiry values, or CVVs.

    bash
    1password-pp-cli cards resolve --query "card" --json
Documents
  • documents inventory — List document metadata and exact references without downloading document contents.

    bash
    1password-pp-cli documents inventory --json
  • documents audit — Flag sensitive filenames, oversized docs, private-key/cert-like documents, and documents in shared vaults.

    bash
    1password-pp-cli documents audit --json
  • documents read — Stream one exact document or attachment reference only after policy checks and an explicit --reveal gate. Use this for in-memory consumers; never place document bytes in a client profile.

    bash
    1password-pp-cli documents read op://Engineering/Google-Analytics/service-account.json --reveal --agent
Sharing
  • share preflight — Before sharing an item, show recipient, item category, included fields, expiry, and risk.

    bash
    1password-pp-cli share preflight --ref op://Engineering/GitHub/token --recipient recipient --expires-in 1d --json
  • share audit — Report whether existing/shareable item link inspection is supported by op or the SDK and document unsupported status clearly.

    bash
    1password-pp-cli share audit --json
Policy
  • policy check — Enforce rules such as never reading credit-card values, exact refs for production, and required owner tags.

    bash
    1password-pp-cli policy check --ref op://Production/API/token --require-exact --json
Access
  • access scope — Summarize what the current service account or op session can access by vault, category, and count without values.

    bash
    1password-pp-cli access scope --json
  • rate-limit status — Wrap op service-account ratelimit so agents can avoid burning quota.

    bash
    1password-pp-cli rate-limit status --json
Agent
  • agent grant-plan — Suggest the minimum service-account vault permissions needed for a task.

    bash
    1password-pp-cli agent grant-plan --task "read staging deploy token" --json
Runtime
  • run plan — Inspect an op run command or env files and show which secret references will resolve before executing.

    bash
    1password-pp-cli run plan --command "npm test" --json
Audit
  • audit stale — Flag items that appear old, untagged, duplicated, or probably unused from metadata.

    bash
    1password-pp-cli audit stale --days 180 --json
  • audit misplaced — Find API keys, cards, documents, or SSH material saved in the wrong 1Password category.

    bash
    1password-pp-cli audit misplaced --json

Recipes

Resolve a secret request without revealing the value
bash
1password-pp-cli secrets resolve --query "token" --json

Returns exact op:// references and candidate metadata with values redacted so a later step can require an exact reference.

Plan environment injection before writing output
bash
1password-pp-cli env inject --in-file README.md --out-file injected.env --json

Shows the references op inject would resolve and keeps will_write false unless --write is explicitly supplied.

Command Reference

op — Inspect the local 1Password CLI authentication surface

  • 1password-pp-cli op — Show whether op is installed and authenticated without reading secret values
Finding the right command

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

bash
1password-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.

Show full SKILL.md (746 more words)Show less

Auth Setup

Install the official 1Password CLI (op) and authenticate it before using this wrapper.

For automation, set a 1Password service-account token:

bash
export OP_SERVICE_ACCOUNT_TOKEN="<service-account-token>"

Prefer named Keychain-backed tokens when an agent needs more than one 1Password account:

bash
1password-pp-cli service-accounts add team --account example-team.1password.com
1password-pp-cli service-accounts add sandbox --account example-sandbox.1password.com
1password-pp-cli --op-service-account team op --agent

Use the masked prompt for setup, or --token-stdin / --token-env NAME without putting a token in argv. On non-macOS systems, select an existing environment variable for one invocation with --op-service-account-token-env NAME. Never put these auth-selection flags in --profile; the CLI excludes them from profile persistence and MCP shellouts.

For a background macOS agent, use a consistently code-signed CLI. Migrate an entry created by an older binary once from a local interactive Terminal with 1password-pp-cli service-accounts repair-access <name> --json; this changes only Keychain access control and never reveals the token. Do not use --agent for this one-time operation because it deliberately disables interactive approval.

For local desktop workflows, sign in with op using the normal 1Password CLI or desktop-app integration. Use --op-account to set OP_ACCOUNT only for child op processes. Named/env service-account selection hard-fails when Connect variables are set or the selected token is unavailable.

Run 1password-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
    1password-pp-cli op --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

  • Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

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:

1password-pp-cli feedback "the --since flag is inclusive but docs say exclusive"
1password-pp-cli feedback --stdin < notes.txt
1password-pp-cli feedback list --json --limit 10

Entries are stored locally at ~/.local/share/1password-pp-cli/feedback.jsonl. They are never POSTed unless API_1PASSWORD_FEEDBACK_ENDPOINT is set AND either --send is passed or API_1PASSWORD_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.

1password-pp-cli profile save briefing --json
1password-pp-cli --profile briefing op
1password-pp-cli profile list --json
1password-pp-cli profile show briefing
1password-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.

Profiles never store or apply --op-service-account, --op-service-account-token-env, or --op-account; use the dedicated service-account selector on each invocation. Legacy authentication values are removed in memory when profiles are read; the next explicit profile write also removes them from disk.

Exit Codes

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

Argument Parsing

Parse $ARGUMENTS:

  1. Empty, help, or --help → show 1password-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/auth/1password/cmd/1password-pp-mcp@latest
  2. Register with Claude Code:
    bash
    claude mcp add 1password-pp-mcp -- 1password-pp-mcp
  3. Verify: claude mcp list

Direct Use

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

Files

SKILL.md and 123 other files in library/auth/1password of mvanhorn/printing-press-library.

  • SKILL.md
  • .golangci.yml
  • .goreleaser.yaml
  • .manuscripts/20260608-220213/proofs/dogfood-research-sync.json
  • .manuscripts/20260608-220213/proofs/phase5-acceptance.json
  • .manuscripts/20260608-220213/proofs/publish-package.json
  • .manuscripts/20260608-220213/proofs/publish-validate.json
  • .manuscripts/20260608-220213/proofs/shipcheck.json
  • .manuscripts/20260608-220213/research/1password-op-spec.yaml
  • .manuscripts/20260608-220213/research/research-brief.md
  • .manuscripts/20260608-220213/research/research.json
  • .printing-press-patches/.gitkeep
  • .printing-press-patches/1password-agent-safety-layer.json
  • .printing-press-patches/ambiguous-write-retries-disabled.json
  • .printing-press-patches/batch-rollback-reports-committed-count.json
  • .printing-press-patches/catalog-go-1264-vuln-floor.json
  • … and 108 more

Open the folder on GitHubat commit 76de244

Compare with similar skills

Pp 1password 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 1password compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pp 1password this skillmvanhorn/printing-press-library2.1k—~3.8kAutomated safety check: NotesApache-2.0
Brand Kit Print Collateralsickn33/agentic-awesome-skills47k1 repos~6.4kAutomated safety check: PassMIT
CSS Printthedaviddias/Front-End-Checklist74k—~422Automated safety check: PassMIT
1passwordtrpc-group/trpc-agent-go1.9k14 repos~656Automated safety check: PassApache-2.0
Safe PushJetBrains/intellij-community21k—~1.1kAutomated safety check: PassCustom licence
Safe RefactorJuliusBrussee/caveman111k1 repos~177Automated safety check: PassApache-2.0

Similar skills

  • Brand Kit Print Collateral

    sickn33/agentic-awesome-skills

    Print collateral spec: item, finished and trim size, bleed, colour mode, stock and GSM, finish, safe margin, print method, quantity and unit cost.

    47k GitHub starsUsed in 1 repo~6.4k tokens
    Marketing & SEOAuto-check passed
  • CSS Print

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Include a print stylesheet.

    74k GitHub stars~422 tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • 1password

    trpc-group/trpc-agent-go

    Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

    1.9k GitHub starsUsed in 14 repos~656 tokens
    AI & LLM EngineeringAuto-check passed
  • Safe Push

    JetBrains/intellij-community

    Official

    Push IntelliJ repository changes through the Safe Push workflow.

    21k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Safe Refactor

    JuliusBrussee/caveman

    Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

    111k GitHub starsUsed in 1 repo~177 tokens
    DevelopmentAuto-check passed
  • Printful

    Anil-matcha/awesome-muse-connectors

    Read Printful products and orders, create orders and mockups.

    1.3k GitHub stars~628 tokensUpdated 3 days ago
    Auto-check passed

More from mvanhorn/printing-press-library

All 506 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 1password

What does Pp 1password do?

Printing Press CLI for 1Password. An agent skill from mvanhorn/printing-press-library. Pp 1password is an agent skill from mvanhorn/printing-press-library. Printing Press CLI for 1Password.

How do I install Pp 1password in Claude Code?

Run `npx skills add mvanhorn/printing-press-library --skill pp-1password -a claude-code`. Or copy the skill folder (library/auth/1password in mvanhorn/printing-press-library) into .claude/skills/pp-1password in your project. Claude Code loads it when a task matches its description.

How do I install Pp 1password in Codex?

Run `npx skills add mvanhorn/printing-press-library --skill pp-1password -a codex`. Or copy the skill folder (library/auth/1password in mvanhorn/printing-press-library) into .agents/skills/pp-1password in your project. Codex loads it when a task matches its description.

Can I use Pp 1password 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-1password -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-1password, .gemini/skills/pp-1password, .github/skills/pp-1password and .opencode/skills/pp-1password in your project.

What does Pp 1password need to run?

Going by SKILL.md and its folder, Pp 1password needs the command-line tools its instructions call (go, claude and npx) and credentials named API_TOKEN and OP_SERVICE_ACCOUNT_TOKEN. Our summary lists: Node.js; A credential in API_TOKEN; A credential in OP_SERVICE_ACCOUNT_TOKEN. Its frontmatter pre-approves these tools: Read, Bash.

Does Pp 1password 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 1password safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; 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 1password use?

Pp 1password 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 1password use?

About 3.8k tokens (SKILL.md is roughly 15k 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 1password?

Skills that share tags, products or a category with Pp 1password: Brand Kit Print Collateral (sickn33/agentic-awesome-skills, 47k stars), CSS Print (thedaviddias/Front-End-Checklist, 74k stars), 1password (trpc-group/trpc-agent-go, 1.9k stars) and Safe Push (JetBrains/intellij-community, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pp 1password?

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.