vibe-learn: Instructions file for Claude Code

CLAUDE.md

vibe-learn CLAUDE.md is an instructions file for Claude Code from gkaria/vibe-learn. It costs 11,927 tokens per session, scanned B, original, MIT.

Project instructions for vibe-learn, a coding-assistant plugin that records development actions and explains what was built. It supports several coding assistants and uses session logs rather than external API calls.

In plain words
What is it for?
Understanding file edits, tool use, and commands through learning prompts, summaries, digests, and quizzes.
Why use it?
It helps users understand AI-assisted changes instead of accepting code they cannot explain.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is gkaria/vibe-learn's own configuration. It tells Claude Code how to work on vibe-learn 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 vibe-learn configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to gkaria/vibe-learn. 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/gkaria/vibe-learn/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/gkaria/vibe-learn

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 vibe-learn CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gkaria/vibe-learn/claude-md"><img src="https://agentmods.dev/badge/instructions/gkaria/vibe-learn/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,927 This file is loaded in full into every session.
When invoked 11,927 The same file — it is already loaded in full.
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 $0.11927 $0.11927
Opus 5.5 $0.04771 $0.04771
Sonnet 5.5 $0.02385 $0.02385
Haiku 4.5 $0.01193 $0.01193

Measured 6d ago against content hash a310976a1fdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

vibe-learn CLAUDE.md 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 6d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

install.sh ← hook registration into ~/.claude/settings.json
CLAUDE.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Project Is

vibe-learn is a coding assistant plugin that observes what the AI does during a development session and helps users understand what was built. It works by registering lifecycle hooks that capture tool use events (file writes, edits, bash commands) into an append-only JSONL session log, then surfaces summaries at natural pause points.

Product principle: users can outsource thinking to an assistant, but they cannot outsource understanding. The project should make AI-assisted work easier to learn from, not just easier to accept.

It supports Claude Code, GitHub Copilot CLI, Codex App/CLI, OpenCode, Grok Build, and Cursor, with a generic adapter system for adding new assistants.

It requires no external API calls. Hooks are mechanical (bash + jq). The learning commands/prompts (/learn, /digest, /quiz, and the Copilot/Codex/Grok/Cursor skills) leverage the AI's own context window to generate explanations and reports.

Multi-Assistant Architecture

The project is split into a generic core and per-assistant adapters:

.claude-plugin/   ← Claude Code plugin packaging (the repo root is the plugin root)
  plugin.json     ← manifest; points commands/hooks at adapters/claude-code/
  marketplace.json ← single-plugin marketplace so `/plugin marketplace add gkaria/vibe-learn` works
bin/              ← on the Bash tool PATH while the plugin is enabled
  vibe-learn      ← → scripts/cli.sh
  vibe-learn-knowledge ← → scripts/knowledge.sh

scripts/          ← assistant-agnostic core (host payload translation stays in adapters)
  bootstrap.sh    ← SessionStart hook
  capture-prompt.sh ← UserPromptSubmit hook
  observe.sh      ← PostToolUse hook (<50ms, append-only)
  pause-summary.sh ← Stop hook
  setup.sh        ← global installer
  install.sh      ← per-project installer
  cli.sh          ← `vibe-learn` command dispatcher; `vibe-learn completion bash|zsh` is generated from its dispatch case labels and usage lines
  doctor.sh       ← `vibe-learn doctor`: read-only checks of jq, the install, each host's hooks, config keys, and the last session
  briefing.sh     ← `vibe-learn briefing`: static HTML session briefing + NotebookLM pack
  audio-prep.sh   ← `vibe-learn audio-prep`: finds the pack and walks through the NotebookLM upload
  knowledge.sh    ← knowledge ledger helper (record/touch/forget/list/due)
  recap.sh        ← `vibe-learn recap`: weekly "what I learned" markdown (read-only)
  identity.sh     ← sourced helper: harness, model, effort, version from payloads and host files
  health.sh       ← session log + meta → one assistant-health row per session segment (read-only)
  usage.sh        ← sourced helper: tool families and skills per session from the host's own session record
  health-report.sh ← `vibe-learn health`: before/after-change comparison of health rows (read-only)
  lib/session.jq  ← shared jq module: learning turns (`learning_prompt`, `work_events`) and `session_facts` (goal, files, failures) for the pause summary and briefing
  lib/briefing.jq ← `briefing_facts` (session_facts + timeline, ledger, diff, pause summary) and the page renderers that fill the templates
  lib/pack.jq     ← the NotebookLM pack, rendered from the same facts
  lib/briefing-{session,index,health}.html ← briefing page templates (static HTML with `{{name}}` placeholders)

adapters/
  claude-code/    ← Claude Code adapter
    hooks.json    ← hook registration template
    commands/     ← /learn, /digest, /quiz, and /explain slash command files
    install.sh    ← hook registration into ~/.claude/settings.json
  codex/          ← Codex App/CLI adapter
    hooks.toml    ← hook registration template (TOML)
    prompts/      ← learn, digest, quiz, and explain prompt-file fallbacks
    skills/       ← global Codex vibe-learn skill
    install.sh    ← hook registration into ~/.codex/config.toml
  opencode/       ← OpenCode adapter
    plugins/      ← local plugin for event capture
    commands/     ← /learn, /digest, /quiz, and /explain markdown commands
    install.sh    ← plugin/command install into .opencode or ~/.config/opencode
  grok/           ← Grok Build adapter
    hooks.json    ← hook registration template
    commands/     ← /learn, /digest, /quiz, and /explain slash command files
    skills/       ← /vibe-learn skill
    install.sh    ← hook file + skill/command install into ~/.grok or .grok
  cursor/         ← Cursor adapter
    hooks.json    ← hook registration template (merged into hooks.json)
    hooks/        ← vibe-learn.sh payload shim (Cursor envelope → core scripts)
    skills/       ← learn, digest, quiz, explain (slash-style) and vibe-learn skills
    install.sh    ← shim + hooks.json merge + skill install into ~/.cursor or .cursor
  copilot-cli/     ← GitHub Copilot CLI adapter
    hooks.json    ← native camelCase hook template
    hooks/        ← vibe-learn.sh payload shim (Copilot envelope → core scripts)
    skills/       ← learn, digest, quiz, explain, and vibe-learn skills
    install.sh    ← dedicated hook file + skill install into ~/.copilot or .github

Read the full file on GitHub · 350 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. 6d ago Changed · +20 lines · +2,690 tokens per session a310976a1fdb
  2. 7d ago Changed · +46 tokens per session a816b116a5a9
  3. 21d ago Changed · +151 tokens per session e65c610bb6be
  4. 22d ago Changed · +43 tokens per session 00060bba1b40
  5. 28d ago Changed · +32 lines · +1,810 tokens per session 818642eb4878
  6. 1mo ago Changed · +13 lines · +939 tokens per session aec91a4bc5e7
  7. 1mo ago Changed · +29 lines · +1,711 tokens per session 8ecc997e3fd4
  8. 1mo ago First seen · 256 lines · 4,537 tokens per session scan B 44283bda06c7

Subscribe to this mod's changes

vibe-learn CLAUDE.md is an instructions file published in the GitHub repository gkaria/vibe-learn (57 stars, last pushed 5d ago), licensed MIT. It adds 11,927 tokens to every session, about $0.0477 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens