pith-tour

pith-tour is a skill for Claude Code from abhisekjha/pith. It costs 50 tokens per session (2,111 once invoked), scanned B, original, MIT.

An interactive, hands-on tour of Pith using the user's actual project files. It guides the user through seven features one step at a time and remembers the tour's progress.

In plain words
What is it for?
Use it to learn Pith by trying its features in a real project, viewing effects such as changed line or token counts, and continuing later.
Why use it?
It replaces a long explanation with small actions and immediate results, while allowing steps to be skipped or resumed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pith plugin — 12 skills, 4 commands, 4 hooks shipped together

Good fit Use it to learn Pith by trying its features in a real project, viewing effects such as changed line or token counts, and continuing later.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/abhisekjha/pith/pith-tour
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 abhisekjha/pith --skill pith-tour
Clone the repo
git clone --depth 1 https://github.com/abhisekjha/pith

Made for: Claude Code.

Or install pith, the plugin that ships this one along with the rest of its 12 skills, 4 commands, 4 hooks.

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 pith-tour

README.md
[![agentmods](https://agentmods.dev/badge/skills/abhisekjha/pith/pith-tour/github.svg)](https://agentmods.dev/skills/abhisekjha/pith/pith-tour)
Your own site
<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-tour"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-tour/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 pith-tour

Your own site · 80×15
<a href="https://agentmods.dev/skills/abhisekjha/pith/pith-tour"><img src="https://agentmods.dev/badge/skills/abhisekjha/pith/pith-tour.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00050 $0.02111
Opus 5 $0.00025 $0.01056
Sonnet 5 $0.00010 $0.00422
Haiku 4.5 $0.00005 $0.00211

Measured 13d ago against content hash 88f00e3b4233, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

pith-tour 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 13d 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.

Strips warnings and disclaimersmediumAnti-refusal

Omitting safety caveats hides risk from the user and is a common jailbreak preamble.

- Never lecture. Do, then explain.
skills/pith-tour/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tour conductor rules

You are running an interactive Pith tour. You are the guide.

Rules:

  • One step at a time. Never show two steps at once.
  • Every step ends with a prompt for action — user does something, you react.
  • Use their ACTUAL project files (find one with glob). Never use fake examples.
  • Show effects numerically where possible (token counts, line counts).
  • Never lecture. Do, then explain.
  • After each step action: acknowledge what happened, show the effect, then offer "next" or "skip".
  • If the user says "skip", advance to the next step immediately.
  • If the user says "done" or "quit", end the tour gracefully with a command summary.
  • Track step via: python3 tools/tour.py --step <n> --action set

Tour structure (7 steps)

Step 0 — Welcome card

Display this exactly:

╔══════════════════════════════════════════╗
║          PITH INTERACTIVE TOUR           ║
║    7 steps · ~8 minutes · hands-on       ║
╚══════════════════════════════════════════╝

Each step: I show you one thing. You try it. You see it work.
No reading. Just doing.

Type  next  to advance ·  skip  to skip a step ·  quit  to exit

Then immediately show Step 1 without waiting.


Step 1 — Compression (the core)

Card:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
  STEP 1 / 7   Tool Output Compression
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
What: Pith compresses tool results before they eat your context.
      Fires automatically. You never invoke it.

Watch: I'm going to read a file from your project right now.

Then: use Glob to find the largest source file in the project (prefer .ts, .py, .go, .java, .js — avoid node_modules, vendor, .git). Read it. After the read completes, say:

↑ That file: [N] lines.

Without Pith → Claude sees the full file as raw text (~[N*4] tokens).
With Pith    → Claude sees imports + signatures + types only (~[N*0.5] tokens).
Savings: ~[calculated %]% on that single read.

This fires on every Read, Grep, Bash call over 30 lines. Silently.

Read the full file on GitHub · 300 lines

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. 13d ago First seen · 300 lines · 50 tokens per session scan B 88f00e3b4233

Subscribe to this mod's changes

pith-tour is a skill published in the GitHub repository abhisekjha/pith (98 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 2,111 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

learn

Use when the user shares a conclusion, note, or takeaway from something they're studying — a book, course, or article — and wants it captured into their personal learning archive. Trigger phrases include "what I learned today", "notes from the book", "conclusions from chapter X", plus the explicit /learn command. Also…

ManceRayder42/jarvis-os · 121 tokens

analyze

Reads input artifact(s) — codebase, planning session, refactor plan, or generic doc — and writes a tour-spec.json describing sections, embedded sources, cross-refs, quizzes, and external link maps. Use when the user wants a fresh learning guide built from source material; auto-hands-off to learning-guide:render.…

DmitriyYukhanov/claude-plugins · 98 tokens

ccc-research

In addition to web search, research can use connected channels as surfaces.

KevinZai/commander · 35 tokens

developer-growth-analysis

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

composio-community/awesome-claude-plugins · 47 tokens

eli5

Explain any concept, codebase, or architecture like reader know nothing about it, as visual HTML artifact — big pictures, few words. Trigger on "/eli5 ", "explain like I'm 5", "ELI5 this".

ManceRayder42/jarvis-os · 52 tokens

create-slidev-presentation

Build or edit Slidev (sli.dev) presentations for tech talks, workshops, conference sessions, and live-coding demos. Use when the user asks to create slides, a deck, a presentation, a workshop deck, a conference talk, or edit an existing slides.md.

b33eep/claude-code-setup · 62 tokens