A guided document for learning a software project. It explains the technologies, what each file does, and follows one real user action through the code with checked file paths, setup steps, safe experiments, and a glossary.

Use it to create a tour of a repository, a subfolder, or the files changed in a Git range. It helps teammates or non-developers learn where code lives and how a user-visible flow works.

Large or newly generated codebases can be difficult to understand and easy to explore unsafely. This gives a human a tested reading order without changing the source code.

code-tour — Skill for Claude Code by joymin5655/Agent

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 joymin5655/Agent --skill code-tour

Clone the repo

git clone --depth 1 https://github.com/joymin5655/Agent

Made for: Claude Code.

Or install agent-harness-extras, the plugin that ships this one along with the rest of its 10 skills, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joymin5655/agent/code-tour/github.svg)](https://agentmods.dev/skills/joymin5655/agent/code-tour)

Your own site

<a href="https://agentmods.dev/skills/joymin5655/agent/code-tour"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/code-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joymin5655/agent/code-tour"><img src="https://agentmods.dev/badge/skills/joymin5655/agent/code-tour.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,690 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.

Model	Per session	Once invoked
Fable 5.1	$0.00115	$0.01690
Opus 5.5	$0.00046	$0.00676
Sonnet 5.5	$0.00023	$0.00338
Haiku 4.5	$0.00012	$0.00169

Measured 21d ago against content hash c41d7023a9be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-tour 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 21d 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.

extras/skills/code-tour/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/code-tour

Goal

Generated code is only leverage if a human can read it. This skill writes one tour: a file a person follows top to bottom to learn where things live, how one real flow travels through the code, and what they can safely change to see it react. The tour is a map. It never edits the code it describes, and every path in it must exist.

Arguments:

target — repo root (default), a sub-directory, or a git range (<base>..HEAD) to tour only what a build changed.
--audience — self (default: terse, assumes a developer), teammate (adds the why behind stack choices), non-dev (every term in the glossary, no unexplained command).
--out — default <project>/docs/TOUR.md.

Steps

1. Identify the stack

Read the manifests that exist (package.json, pyproject.toml, Package.swift, go.mod, Cargo.toml, …), the framework config files and the README. For a range target, read git diff --stat <range> first. Note the start time (date '+%Y-%m-%d %H:%M:%S') for the untouched-tree check in step 7.

Done when: the language, framework, runtime, data store and deploy target are each stated with the file:line they come from, as none (no <config file>) when the project has none, or as unknown.

2. Derive the file-role rules

Find the 3–6 rules a reader needs to place any file, such as "app/**/page.tsx is a screen and its folder path is the URL", "app/api/**/route.ts is a server endpoint", or "supabase/migrations/*.sql is an ordered schema change". Use CodeGraph when .codegraph/ exists, otherwise serena or Glob/Grep. Name folders the reader should skip, such as dependency or build-output folders.

Done when: the rules form a table rule | glob | matching files, and every glob matches at least one real file.

3. Trace one flow

Pick the most important user-visible flow (for a range target, the flow the change serves) and follow it from entry to storage: screen → client state → endpoint → domain logic → database or external service. A project without some layer (a front-end-only app has no endpoint) stops at its last real layer and says which layers do not exist. Write at most 12 reading steps. Each step gives:

Read the full file on GitHub · 139 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.

21d ago First seen · 139 lines · 115 tokens per session scan A c41d7023a9be

Subscribe to this mod's changes

code-tour is a skill published in the GitHub repository joymin5655/Agent (2 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 1,690 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-16.

Claude Code LLM Learning and teaching Writing and docs agent-infrastructure ai-agents devtools policy-as-code

code-tour next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-tourjoymin5655/Agent	Skill	2	yesterday	MIT	A	115	Claude Code
canvasNousResearch/hermes-agent	Skill	261k	yesterday	MIT	A	12	Claude Code, Codex
playwrightopenai/openai-agents-python	Skill	31k	yesterday	MIT	A	19	Claude Code, Codex
context7-docsupstash/context7	Skill	64k	yesterday	MIT	A	157	Claude Code, Codex
show-mehumanlayer/humanlayer	Skill	13k	yesterday	Apache-2.0	A	25	Claude Code
ace-rsi-toolkitPrism-Shadow/penguin-harness	Skill	3.2k	yesterday	Apache-2.0	A	69	Claude Code, Codex
eli5genkit-ai/genkit	Skill	6.6k	yesterday	Apache-2.0	A	16	Claude Code, Codex