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 lunchpaillola/pipa-skills --skill pipa-setupgit clone --depth 1 https://github.com/lunchpaillola/pipa-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/lunchpaillola/pipa-skills/pipa-setup)<a href="https://agentmods.dev/skills/lunchpaillola/pipa-skills/pipa-setup"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-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/lunchpaillola/pipa-skills/pipa-setup"><img src="https://agentmods.dev/badge/skills/lunchpaillola/pipa-skills/pipa-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00035 | $0.01299 |
| Opus 5 | $0.00017 | $0.00649 |
| Sonnet 5 | $0.00007 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
pipa-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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipa Setup
Set up or update the global Pipa business profile at ~/.pipa/profile.md and optionally install the shared communication style at ~/.pipa/communication-style.md.
State Routing
- Check whether
~/.pipa/profile.mdexists. - If it is missing, offer setup as a soft, non-blocking next step. Do not interrupt concrete work.
- If
setup_status: incomplete, resume at the first unanswered question. If all three are answered or skipped, resume at communication-style review, then connector review. - If
setup_status: complete, show the existing profile and ask what should change. Preserve complete status and unchanged fields; review communication style or connectors only when requested.
Do not run connected-tool or memory checks until the user accepts setup.
Workflow
1. Ask The Core Questions
After the user accepts setup, treat clear answers or explicit skips in the current request as confirmed and save them before asking anything. Ask only the remaining questions, conversationally and one at a time:
What do you do?Who do you help or work with?How do you like to work?
Allow every question to be skipped. Ask a follow-up only when an answer is unclear. Do not add team structure, approval, process, or current-focus intake.
Before the first profile write, create ~/.pipa/ if it does not exist. After each answer or skip, save confirmed state with setup_status: incomplete. Preserve existing confirmed facts and never invent missing context.
Use this human-readable shape:
---
setup_status: incomplete
setup_version: 1
updated_at: <ISO-8601 timestamp>
---
# Pipa Profile
## What I Do
<confirmed answer, `Skipped`, or `TBD`>
## Who I Help Or Work With
<confirmed answer, `Skipped`, or `TBD`>
## How I Like To Work
<confirmed answer, `Skipped`, or `TBD`>
## Website Context
<confirmed website-supported business, offer, audience, or positioning facts; omit when unused>
2. Optionally Read A Company Website
If the user provides a company URL and wants drafting help, verify each requested page read and propose only supported facts about the business, offer, audience, or positioning. Report each requested page as used, partial, stale, empty, declined, unavailable, or failed; use not-requested only for pages outside the request's scope. Never treat a partial, stale, or declined page as empty or comprehensive. Continue setup safely from other usable input after a partial, stale, empty, declined, unavailable, or failed read, and cite the material page URLs used. Confirm proposed facts before saving them under Website Context; never overwrite user-provided content. Keep this read-only and best-effort. Do not add an enrichment service or reverse-lookup people by email. Connected-app review remains delegated to pipa-connectors, which must verify access through composio-mcp discovery and complete tool schemas rather than connector mappings.
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.
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 · 101 lines · 35 tokens per session scan A 403147059ae1
pipa-setup is a skill published in the GitHub repository lunchpaillola/pipa-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,299 once invoked, about $0.0002 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.
Other skills, from other repositories
autoresearch
Autonomously optimize any Claude Code skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Use when: optimize this skill, improve this skill, run autoresearch on, make this skill better, self-improve skill…
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
compound
Capture and compound learnings from conversations into reusable commands and skills through interactive dialogue.
obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…