vibo-mcp: Instructions file for Claude Code

CLAUDE.md

vibo-mcp CLAUDE.md is an instructions file for Claude Code from chrischall/vibo-mcp. It costs 4,343 tokens per session, scanned A, original, MIT.

Project instructions for the Vibo music-management service, including its commands, tool names, software structure, authentication, and tests.

In plain words
What is it for?
Building, testing, and maintaining the vibo-mcp project, which connects to Vibo's GraphQL API and exposes actions to an assistant.
Why use it?
They give an AI coding assistant the project-specific rules it needs to work on the code consistently.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is chrischall/vibo-mcp's own configuration. It tells Claude Code how to work on vibo-mcp 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 vibo-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/vibo-mcp. 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/chrischall/vibo-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chrischall/vibo-mcp

Made for: Claude Code.

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 vibo-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrischall/vibo-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/vibo-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrischall/vibo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/vibo-mcp/claude-md/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 vibo-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrischall/vibo-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/vibo-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,343 This file is loaded in full into every session.
When invoked 4,343 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04343 $0.04343
Opus 5.5 $0.01737 $0.01737
Sonnet 5.5 $0.00869 $0.00869
Haiku 4.5 $0.00434 $0.00434

Measured 2d ago against content hash 770d79c2b128, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

vibo-mcp CLAUDE.md 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 2d 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.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vibo-mcp

MCP server for Vibo. Wraps the Vibo consumer GraphQL API (https://api.vibodj.com/v2/graphql) and exposes 42 host/couple tools to Claude over stdio (15 reads + 27 writes/actions, confirmation-gated where they mutate). Built on @chrischall/mcp-utils (runMcp, minifiedResult, toolAnnotations, confirmWrite, error classes).

Commands

npm run build          # tsc + esbuild bundle → dist/index.js + dist/bundle.js
npm test               # vitest run
npm run test:watch     # vitest watch
npm run test:coverage  # vitest run --coverage (v8 reporter, no thresholds)

Run locally (requires built dist/ + credentials):

[email protected] VIBO_PASSWORD=… node dist/index.js

Tool naming

All tools are prefixed vibo_ (e.g. vibo_list_sections, vibo_add_song_to_section).

Architecture

src/
  version.ts      # single source of truth for VERSION (x-release-please-version)
  index.ts        # entry — runMcp({ name, version, banner, tools })
  client.ts       # ViboClient — GraphQL POST w/ x-token, deferred config error,
                  #   single-flight login + refresh-on-expiry + replay-once;
                  #   gqlUpload() for multipart (Upload scalar);
                  #   adoptVerifiedTokens() verifies a browser-captured pair on an
                  #   isolated client before adopting it (never the env login,
                  #   never session.json — the tool persists after it succeeds)
  auth.ts         # captureViboSession() — fetchproxy browser-bridge token capture (SSO)
  session-store.ts# persist {accessToken,refreshToken} to ~/.vibo-mcp/session.json (0600)
  gql.ts          # all GraphQL operation documents (selections from introspection)
  reorder.ts      # planMoves() — "move these after X" as single-item reorder
                  #   calls (Vibo: source lands after target; null = first)
  brief.ts        # view: "brief" lines (title — date — status, ≤ 120 chars,
                  #   "-- " note lines) in the untrusted-data envelope
  song-search.ts  # pure search-quality heuristics — parseSearchQuery, assessSong,
                  #   annotateSearchResults; grades each search hit
                  #   likely-original / uncertain / likely-not-original
  tools/
    profile.ts          # vibo_get_me, vibo_healthcheck
    events.ts           # list_events, get_event, join_event, leave_event, create_event_contact
    sections.ts         # vibo_list_sections
    songs.ts            # get_section_songs, search_songs, add_song_to_section, toggle_song_like
    playlists.ts        # get_playlists, get_playlist_songs, export_event_to_{spotify,apple_music}
    notifications.ts    # list_notifications, get_notifications_count, mark_notifications_read
    questions.ts        # list_section_questions, answer_question (incl. image/file uploads)
    song-management.ts  # remove_song_from_section, update_song, move_song, reorder_songs
    comments.ts         # comment_on_song/section, delete_song/section_comment
    ideas.ts            # list_section_song_ideas, list_song_ideas_songs
    imports.ts          # import_playlist_to_section
    collaboration.ts    # list_event_users, invite_users, change_user_role, remove_user
    section-edit.ts     # update_section
    section-manage.ts   # create_section, delete_section, reorder_sections
    lookups.ts          # read-before-write helpers (sections, event perms,
                        #   section song ids, id validation)
    uploads.ts          # set_profile_photo
    session.ts          # capture_session (SSO browser token capture)
    shared.ts           # pagination + confirmWrite (confirmation gate) helpers
    hints.ts            # familyMeta() — context-group `_meta.mint` hints

Read the full file on GitHub · 294 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. 2d ago Changed · +9 lines · +148 tokens per session 770d79c2b128
  2. 20d ago Changed · +14 tokens per session 1fd10b4984b4
  3. 28d ago Changed · +6 lines · +116 tokens per session 3afb407330a1
  4. 1mo ago Changed · +4 lines · -89 tokens per session bf34ba7db897
  5. 1mo ago Changed · +40 lines · +714 tokens per session 370051dc9d42
  6. 1mo ago Changed · +24 lines · +412 tokens per session 7664e05707fc
  7. 2mo ago First seen · 211 lines · 3,028 tokens per session scan A 1485855e392a

Subscribe to this mod's changes

vibo-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/vibo-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 4,343 tokens to every session, about $0.0174 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 2026-08-31.

Related

vibo-mcp CLAUDE.md compared with instructions from other repositories

vibo-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
vibo-mcp CLAUDE.mdchrischall/vibo-mcpInstructions file12d agoMITA4,343Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode