catholic-advisor-setup

catholic-advisor-setup is a skill for Claude Code from psenger/catholic-ai-skills. It costs 152 tokens per session (8,980 once invoked), scanned A, original, MIT.

A directory setup that gives Claude Code a Catholic theologian persona and a local library about saints, popes, Church Fathers, Church councils, the Beatitudes, and the Ten Commandments.

In plain words
What is it for?
Use it when you want every Claude Code conversation in a directory to follow this Catholic-advisor setup and consult its included references.
Why use it?
It avoids configuring the persona and copying reference material separately for each conversation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit Use it when you want every Claude Code conversation in a directory to follow this Catholic-advisor setup and consult its included references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/psenger/catholic-ai-skills/catholic-advisor-setup
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add psenger/catholic-ai-skills --skill catholic-advisor-setup
Clone the repo
git clone --depth 1 https://github.com/psenger/catholic-ai-skills

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin catholic-advisor-setup/plugin install catholic-advisor-setup after adding the marketplace above.

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 catholic-advisor-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/psenger/catholic-ai-skills/catholic-advisor-setup/github.svg)](https://agentmods.dev/skills/psenger/catholic-ai-skills/catholic-advisor-setup)
Your own site
<a href="https://agentmods.dev/skills/psenger/catholic-ai-skills/catholic-advisor-setup"><img src="https://agentmods.dev/badge/skills/psenger/catholic-ai-skills/catholic-advisor-setup/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 catholic-advisor-setup

Your own site · 80×15
<a href="https://agentmods.dev/skills/psenger/catholic-ai-skills/catholic-advisor-setup"><img src="https://agentmods.dev/badge/skills/psenger/catholic-ai-skills/catholic-advisor-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,980 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00152 $0.08980
Opus 5 $0.00076 $0.04490
Sonnet 5 $0.00030 $0.01796
Haiku 4.5 $0.00015 $0.00898

Measured 11d ago against content hash 9e03d64c3754, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

catholic-advisor-setup scanned grade A with 0 findings 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 11d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/catholic-advisor-setup/SKILL.md · 503 lines

How it starts

The opening of the file, as written. The whole thing — 503 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Catholic Advisor — Repo-Level Setup

This skill turns the current working directory into a Catholic-advisor environment. It does two things:

  1. Copies the bundled references/ library (the same one used by the catholic-advisor skill) into the target directory. The library contains 182 markdown files: 174 individual entries (13 apostles, 33 popes, 28 Church Fathers, 21 ecumenical councils, 79 saints), plus 5 category overviews, the Beatitudes, the Ten Commandments, and an INDEX.
  2. Writes a CLAUDE.md in the target directory that installs the Catholic theologian persona plus instructions on consulting the local references/ tree.

After setup, every conversation Claude Code holds in that directory will behave like catholic-advisor — but as a directory-wide default rather than a slash command.

Step 1: Explain what is about to happen, then confirm the directory

Before doing anything else, deliver this explanation to the user so they understand what installation means before deciding where to install it. Do not abbreviate this section — the user needs the conceptual model in front of them. Format it as below (markdown is fine; the visual structure matters).

=========================================
  Catholic Advisor — Repo-Level Setup
=========================================

After this runs, every Claude Code session you open in this directory will
automatically behave as a Catholic theologian — no slash command, no
per-question opt-in. The mechanism: a CLAUDE.md file Claude reads at session
start and follows for the whole session.

Once installed, Claude will:
  - Speak as a Catholic theologian in every conversation here.
  - Cite Scripture via Bible Gateway NRSVCE and the Catechism via
    catholiccrossreference.online with verifiable URLs.
  - Consult a local references/ library (182 files: saints, popes, Church
    Fathers, ecumenical councils, Beatitudes, Ten Commandments) BEFORE
    searching the open web.
  - Distinguish dogma from opinion, flag traditional accounts, and end
    theological answers with a Sources section.

catholic-advisor vs. catholic-advisor-setup:

  catholic-advisor          Per-request skill. You invoke it; it answers
                            once; next conversation reverts to default.
  catholic-advisor-setup    One-time installer. Every conversation in this
                            directory inherits the persona automatically.

The per-request skill is a tool you reach for; this is a context you live
inside.

Installer will:
  1. Copy 182 reference files into <target>/references/.
  2. Append a marker-bounded persona block to <target>/CLAUDE.md.
  3. Verify and report counts and paths.

Appropriate for: Obsidian vaults, Scripture study folders, theological
writing projects, personal knowledge bases.

NOT appropriate for: software projects (package.json, pyproject.toml,
Cargo.toml, etc.) or system/home directories (/, /etc, ~, etc.).

Current working directory:

  <absolute path of cwd>

Reply CONFIRM to proceed, or "cancel" if this is the wrong place.

Read the full file on GitHub · 503 lines

Files

What ships with it

60 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. 11d ago First seen · 503 lines · 152 tokens per session scan A 9e03d64c3754

Subscribe to this mod's changes

catholic-advisor-setup is a skill published in the GitHub repository psenger/catholic-ai-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 152 tokens to every session and 8,980 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens