pubky-app: Skill for Claude Code

.agents/skills/pubky-staging-invite/SKILL.md

pubky-staging-invite is a skill for Claude Code, Codex from pubky/pubky-app. It costs 49 tokens per session (550 once invoked), scanned A, original, MIT.

A tool that creates a one-time signup token for a Pubky staging server. A staging server is a non-production environment used for testing.

In plain words
What is it for?
It is for issuing the explicitly requested number of staging invite codes, using a saved administrator credential when available.
Why use it?
It prevents signup tokens from being created accidentally when someone is only asking how signup works. It also keeps the administrator password out of chat and command arguments.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is pubky/pubky-app's own configuration. It tells Claude Code and Codex how to work on pubky-app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pubky-app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pubky/pubky-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/pubky/pubky-app/dev/.agents/skills/pubky-staging-invite/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/pubky/pubky-app

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pubky-staging-invite

README.md
[![agentmods](https://agentmods.dev/badge/skills/pubky/pubky-app/pubky-staging-invite/github.svg)](https://agentmods.dev/skills/pubky/pubky-app/pubky-staging-invite)
Your own site
<a href="https://agentmods.dev/skills/pubky/pubky-app/pubky-staging-invite"><img src="https://agentmods.dev/badge/skills/pubky/pubky-app/pubky-staging-invite/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pubky-staging-invite

Your own site · 80×15
<a href="https://agentmods.dev/skills/pubky/pubky-app/pubky-staging-invite"><img src="https://agentmods.dev/badge/skills/pubky/pubky-app/pubky-staging-invite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 550 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00550
Opus 5.5 $0.00020 $0.00220
Sonnet 5.5 $0.00010 $0.00110
Haiku 4.5 $0.00005 $0.00055

Measured 1mo ago against content hash 31444a57d40b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pubky-staging-invite scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/configure.sh, scripts/generate.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

compatibility: Requires Bash, curl, and outbound HTTPS access to admin.homeserver.staging.pubky.app. Credential caching supports macOS Keychain and Linux Secret Service; the permission-restricted XDG file fallback on Lin
.agents/skills/pubky-staging-invite/SKILL.md · 39 lines

What it actually says

Pubky Staging Invite

Mint only the number of tokens the user explicitly requested. Generating a token changes server state; a question about signup or where to enter a token is not authorization to create one.

Generate a token

Resolve bundled script paths against the directory containing this SKILL.md, then invoke the generator by its resolved path. For example, when the current directory is the skill directory:

bash scripts/generate.sh

The script looks for the admin password in this order:

  1. PUBKY_STAGING_ADMIN_PASSWORD in the current process environment.
  2. macOS Keychain or Linux Secret Service.
  3. The Linux XDG credential file created by scripts/configure.sh when Secret Service is unavailable.

If no saved credential exists, ask the user to resolve and run the setup script the same way, once, in an interactive local terminal:

bash scripts/configure.sh

The setup script prompts without echoing the password. Do not ask the user to paste it into chat, put it in a command argument, or save it inside a repository. On headless Linux without Secret Service, the fallback file uses the XDG config directory with mode 0600 and refuses to save inside a Git worktree.

On success, scripts/generate.sh writes exactly one invite code to stdout. Return that code to the user without saving it. On failure, report the concise diagnostic from stderr and do not invent a code. Do not automatically retry a timeout or other ambiguous network failure because the first request may already have minted a token.

Each code is single-use and valid only for the staging homeserver 8um71us3fyw6h8wbcxb5ar3rwusy1a6u49ba7eabxpqi8gnetewy used by shop.pubky.app and staging Pubky App accounts.

The user enters it in Pubky App sign-up under Invite code. If a fresh code is rejected, first confirm that the app targets the staging homeserver and that an earlier signup attempt did not consume it.

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · +2 lines 31444a57d40b
  2. 1mo ago First seen · 37 lines · 49 tokens per session scan A 27d5bcf0ff71

Subscribe to this mod's changes

pubky-staging-invite is a skill published in the GitHub repository pubky/pubky-app (26 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 550 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.