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.
npx skills add tkcostello/pastor-ai-skills --skill pastor-setupgit clone --depth 1 https://github.com/tkcostello/pastor-ai-skillsWrote 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.
[](https://agentmods.dev/skills/tkcostello/pastor-ai-skills/pastor-setup)<a href="https://agentmods.dev/skills/tkcostello/pastor-ai-skills/pastor-setup"><img src="https://agentmods.dev/badge/skills/tkcostello/pastor-ai-skills/pastor-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.
<a href="https://agentmods.dev/skills/tkcostello/pastor-ai-skills/pastor-setup"><img src="https://agentmods.dev/badge/skills/tkcostello/pastor-ai-skills/pastor-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 3 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Rogue Agent · line 36 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01281 |
| Opus 5 | $0.00032 | $0.00641 |
| Sonnet 5 | $0.00013 | $0.00256 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade B, and why
pastor-setup scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
description: Use when setting up pastor-ai-skills for the first time, when a pastor wants to view or change their church profile (church name, denomination, attendance, congregation, community, Bible translation), or whe How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pastor Setup: Your Church Profile
One-time setup for every skill in the pastor-ai-skills collection. This skill runs a short guided interview, then saves a profile file that stores your church's context so you never have to repeat it. Every other skill reads this file automatically.
The profile lives at ~/.claude/pastor-profile.md.
What This Skill Does
- Checks whether
~/.claude/pastor-profile.mdalready exists. - If it exists: show the current values and ask what to change. Update only what the pastor asks to change.
- If it does not exist: run the interview below.
Interview Rules
These rules are non-negotiable:
- One question per message. Never bundle two questions together. Ask, wait for the answer, then ask the next.
- Acknowledge each answer in a few words before the next question. Like a person would. Not a form.
- Show progress. Prefix each question with where they are, like "2 of 6."
- Any answer can be "skip." Skipping an optional question is always fine. Move on without comment.
- Adapt. If an answer already covers a later question, don't ask it again. If an answer is interesting ("we're a military town"), one natural follow-up is allowed, but only one.
- Keep it warm and fast. The whole core round should feel like two minutes, not an intake form.
Round 1: The Core (6 questions, required)
Open with one sentence: this takes about two minutes, sets up every skill, and only happens once.
- Church name. "What's your church's name?"
- Their name and role. "And your name, as you'd want it to appear in content? Plus your role, if you're not the lead pastor." (Executive pastors, worship pastors, and comms directors use these tools too. Capture the role so skills write from the right seat.)
- Denomination or tradition. "What denomination or tradition are you part of? Totally fine to say nondenominational." (Default: nondenominational evangelical.)
- Attendance. "About how many people attend on an average weekend?"
- Location. "What city and state?" If they only give a city, that's enough.
- Bible translation. "Which Bible translation do you preach from?" (Default: NIV.)
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.
- 11d ago First seen · 90 lines · 65 tokens per session scan B e8695b66e1e7
pastor-setup is a skill published in the GitHub repository tkcostello/pastor-ai-skills (51 stars, last pushed 14d ago), licensed MIT. It adds 65 tokens to every session and 1,281 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…