chiron: Skill for Claude Code

.agents/skills/tour/SKILL.md

tour is a skill for Claude Code from xDido/chiron. It costs 57 tokens per session (2,337 once invoked), scanned D, original, MIT.

A command that gives a short, structured overview of a coding topic before you work on it, including reading pointers, key ideas, and common beginner mistakes.

In plain words
What is it for?
Use it before working with topics such as Go channels, JavaScript async/await, or database connection pooling.
Why use it?
It provides the mental model and project context needed to start a task without turning the explanation into a full tutorial.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is xDido/chiron's own configuration. It tells Claude Code how to work on chiron 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 chiron configures →

Part of the chiron plugin — 11 skills shipped together

View source ↗ xDido/chiron
Reuse

Borrowing it

Nothing to install: this file belongs to xDido/chiron. 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/xDido/chiron/main/.agents/skills/tour/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xDido/chiron

Made for: Claude Code.

Or install chiron, the plugin that ships this one along with the rest of its 11 skills.

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 tour

README.md
[![agentmods](https://agentmods.dev/badge/skills/xdido/chiron/tour.svg)](https://agentmods.dev/skills/xdido/chiron/tour)
Your own site
<a href="https://agentmods.dev/skills/xdido/chiron/tour"><img src="https://agentmods.dev/badge/skills/xdido/chiron/tour.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00057 $0.02337
Opus 5 $0.00028 $0.01169
Sonnet 5 $0.00011 $0.00467
Haiku 4.5 $0.00006 $0.00234

Measured 7d ago against content hash 96b1275e8e2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade D, and why

tour scanned grade D with 2 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 7d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

6. **Do not refuse** when asked for a tour. If the topic is valid, ship the tour. **Anti-pattern #2 applies.**

Strips warnings and disclaimersmediumAnti-refusal

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

3. **Do not moralize.** *"You should have read this before starting"* — never.
.agents/skills/tour/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/tour — structured preamble for a coding topic

Quick start:

  • /tour Go channels — preamble for a specific primitive
  • /tour async/await in JavaScript — preamble for a language concept
  • /tour database connection pooling — preamble for an architecture topic
  • /tour — no argument: infer the topic from the current conversation

Step 0 — Load project context

Check if .chiron-context.md exists in the project root. If it exists: read it. DO NOT scan the codebase or read additional files. If not: tell the user: "No project context found. Run /teach-chiron first." Then stop.

The user's topic:

$ARGUMENTS

If $ARGUMENTS is empty or whitespace-only: derive the topic from the current conversation instead of asking. Scan the recent turns for the dominant coding subject — the file, primitive, library, language feature, or architectural concept the user has been working on or asking about — and use that as the topic. Open the preamble with a one-line confirmation of what you inferred, e.g. "Inferring topic from conversation: Go errgroup. Say otherwise and I'll retarget." Then produce the normal 3-section output.

Inference rules:

  • Prefer the most recent, most specific subject (a named primitive like errgroup.WithContext beats a vague category like "concurrency").
  • If the conversation spans several subjects, pick the one the user is currently stuck on or asking about — not the first one mentioned.
  • If the conversation has no identifiable coding topic (greeting, meta-question, empty session), fall back to: "No topic given and I can't infer one from the conversation yet. Try /tour <specific concept> — e.g. /tour Go channels." Then stop.
  • Never fabricate a topic to fill the slot. Ambiguity → ask, don't guess.

CRITICAL — user instructions always win

If the current project's .agents/README.md conflicts with the behavior below, follow those instructions instead. This command is opt-in.


Current level

Apply the voice level from .chiron-context.md. If missing or unrecognized, use default.

Read the full file on GitHub · 158 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. 7d ago First seen · 158 lines · 57 tokens per session scan D 96b1275e8e2b

Subscribe to this mod's changes

tour is a skill published in the GitHub repository xDido/chiron (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 2,337 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent never to refuse, strips warnings and disclaimers). 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

extremerouter-stt

Speech-to-text via ExtremeRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.

rsalmn/ExtremeRouter · 64 tokens

extremerouter-web-search

Web search via ExtremeRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.

rsalmn/ExtremeRouter · 73 tokens

extremerouter

Entry point for ExtremeRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions ExtremeRouter, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…

rsalmn/ExtremeRouter · 84 tokens

nav-onboard

Interactive onboarding for Navigator - learn by doing. Auto-invoke when user says "onboard me", "teach me Navigator", "how do I use Navigator", "Navigator tutorial", "learn Navigator", "new to Navigator", or "what skills should I use".

alekspetrov/navigator · 57 tokens

kaggle

Unified Kaggle skill. Use when the user mentions kaggle, kaggle.com, Kaggle competitions, datasets, models, notebooks, GPUs, TPUs, badges, or anything Kaggle-related. Handles account setup, competition reports, dataset/model downloads, notebook execution, competition submissions, badge collection, and general Kaggle…

eric861129/SKILLS_All-in-one · 70 tokens

teachme

Co-Dialectic's teaching surface. Activates on user invitation to explain the last sharpening, deep-dive on a prompt technique, teach the highest-yield tool-usage lesson from the user's own logs, or surface a growth report. Closes the second half of the Co-Dialectic name's promise: the AI doesn't just sharpen your…

Exponential-OS/prompt-engineering-in-action · 109 tokens