vibing-code-tour

vibing-code-tour is a skill for Claude Code, Codex from shabaraba/vibing.nvim. It costs 84 tokens per session (1,136 once invoked), scanned A, original, MIT.

A guided tour of how a feature or request moves through a codebase. It opens the real files at relevant lines and records the route in Neovim's quickfix list, which is a navigable list of locations.

In plain words
What is it for?
Explaining flows that cross several files, onboarding someone to unfamiliar code, and tracing a bug through a chain of function calls.
Why use it?
It makes a multi-file execution path easier to follow in the editor than a list of file names in chat. You can revisit each step with Neovim's next and previous commands.

Skill for Claude CodeCodex

Part of the vibing-nvim plugin — 12 skills, 1 agent shipped together

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.

agentmods
npx agentmods add skills/shabaraba/vibing.nvim/vibing-code-tour
Any agent
npx skills add shabaraba/vibing.nvim --skill vibing-code-tour
Clone the repo
git clone --depth 1 https://github.com/shabaraba/vibing.nvim

Made for: Claude Code, Codex.

Or install vibing-nvim, the plugin that ships this one along with the rest of its 12 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.

agentmods badge for vibing-code-tour

README.md
[![agentmods](https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-code-tour.svg)](https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-code-tour)
Your own site
<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/vibing-code-tour"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/vibing-code-tour.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,136 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00084 $0.01136
Opus 5 $0.00042 $0.00568
Sonnet 5 $0.00017 $0.00227
Haiku 4.5 $0.00008 $0.00114

Measured 5d ago against content hash 6c40b9206068, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

vibing-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 5d 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.

claude-plugin/skills/vibing-code-tour/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibing-code-tour

A list of file:line references in a chat message is something the user still has to go open themselves. This skill instead drives their editor: each stop of the explanation is a real file opened at a real line, and the whole route is left behind in the quickfix list so they can walk it again afterwards with :cnext / :cprev.

Requires the vibing-nvim MCP tools (a running Neovim). Without them, fall back to explaining the flow as text with file:line references, and say that's what you're doing.

When to use it

  • A flow that crosses three or more files, or several hops of a call chain
  • Onboarding-style questions: "how does X work", "where does this request go"
  • Tracing a bug back to its origin, when the answer is a path rather than a spot

Not for single-symbol questions ("where is X defined") — use the nvim-lsp-navigation skill for those.

Workflow

1. Find the route

Establish the path with the LSP tools (see nvim-lsp-navigation for which tool answers which question), falling back to Grep/Glob where LSP has nothing to say. nvim_load_buffer loads a file in the background so you can analyze it without disturbing what the user is looking at.

Build an ordered list of stops as you go: { filename, lnum, col, text }, where text is a short label — it is what shows in the quickfix window, so make it say what happens at that line, not what the file is called.

2. Publish the route, once

One nvim_set_qflist call with every stop in visiting order, a title naming the tour, and open: true.

Call it exactly once per tour. Each call pushes a new quickfix list, so a second call leaves :cnext walking a different list than the one you are narrating. (The same property is why this is safe to call at all: whatever the user had in quickfix before is still there under :colder.)

Note col is 1-based here, matching native quickfix — unlike the 0-based col that nvim_set_cursor and the nvim_lsp_* tools use. Add 1 when you carry a position over from an LSP result.

Read the full file on GitHub · 85 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. 5d ago First seen · 85 lines · 84 tokens per session scan A 6c40b9206068

Subscribe to this mod's changes

vibing-code-tour is a skill published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,136 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

add-sponsor

Add, move or remove a sponsor logo in the README and on the install page. Use when a GitHub sponsor reaches the Team or Company tier, when a sponsorship lapses, or when a sponsor sends a new logo asset.

agarwalvishal/claude-chat-exporter · 50 tokens

code-review

Pre-commit code review using code-reviewer agent for bug detection, security analysis, and quality assurance. Manual invocation only. Use before git commits to catch issues early. Blocks commits on REQUESTCHANGES verdict.

arpitnath/claude-capsule-kit · 45 tokens

debug

Systematic debugging using error-detective and debugger agents instead of manual investigation. Triggers automatically on: error, bug, broken, failing, exception, stack trace, test failure. Orchestrates RCA-first approach with parallel agent investigation.

arpitnath/claude-capsule-kit · 50 tokens

deep-context

Build deep codebase understanding using Capsule context, progressive-reader, and specialist agents instead of overwhelming main context. Triggers on: don't have context, understand codebase, learn about, need background. Implements progressive context building.

arpitnath/claude-capsule-kit · 47 tokens

task-router

Decision matrix for choosing optimal approach to any task. Helps Claude decide when to delegate to sub-agents vs. working directly. Use when starting a new task or unsure of best approach.

arpitnath/claude-capsule-kit · 43 tokens

workflow

Systematic task orchestration for complex multi-step tasks. Triggers automatically when detecting: complex task, multi-step work, coordinate, orchestrate, break down. Guides through Understand → Strategy → Plan → Execute → Verify phases for comprehensive systematic approach.

arpitnath/claude-capsule-kit · 51 tokens