vibeframe: Instructions file for Claude Code

CLAUDE.md

vibeframe CLAUDE.md is an instructions file for Claude Code from jubayertalha/vibeframe. It costs 712 tokens per session, scanned A, original, MIT.

A repository guide for VibeFrame, a coding-agent framework that keeps project goals, architecture, and code links in the repository.

In plain words
What is it for?
Use it when working on the VibeFrame codebase and needing to understand its packages, tools, and development rules.
Why use it?
It gives an agent one documented source for the project layout, commands, and coding conventions.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions AGENTS.md.

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

Reuse

Borrowing it

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

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 vibeframe CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jubayertalha/vibeframe/claude-md.svg)](https://agentmods.dev/instructions/jubayertalha/vibeframe/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jubayertalha/vibeframe/claude-md"><img src="https://agentmods.dev/badge/instructions/jubayertalha/vibeframe/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 712 This file is loaded in full into every session.
When invoked 712 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 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 6d ago against content hash 9341da5eb091, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

vibeframe 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 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.

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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

VibeFrame — repository guide

VibeFrame is a control plane for agentic coding: a living, in-repo model of intent, architecture, and code (.vibeframe/), deterministically indexed, bidirectionally linked, continuously checked for drift. The approved Discovery report is the product baseline; docs/ mirrors its decisions. The framework makes zero LLM calls — the coding agent is the only intelligence, connected via MCP.

Layout

  • packages/core — model schemas (zod), .vibeframe/ store, schema versioning + migrations, IDs, errors, logging
  • packages/store — SQLite (better-sqlite3): code plane, link state, events, findings, reconcile queue
  • packages/indexer — tree-sitter (WASM) symbols, import resolution (oxc-resolver + Python resolver), watcher, git catch-up
  • packages/engine — graphology working graph, lenses, impact analysis, reflexion validator, digest builder
  • packages/daemon — hono app: MCP endpoint (Streamable HTTP) + REST + SSE + UI hosting
  • packages/clivibeframe bin: init/start/stop/status/index/validate/mcp/hook; ships built UI in ui-dist/
  • packages/ui — React 19 + React Flow lens UI (private; builds into packages/cli/ui-dist)
  • plugin/ — Claude Code plugin (manifest, hooks, skills, commands, dependency-free launchers)
  • tests/dogfood — end-to-end acceptance scenarios; examples/restaurant-platform is their fixture

Dependency direction (enforced by tsconfig references, never violate): core ← store ← indexer ← engine ← daemon ← cli; ui talks only to daemon HTTP.

Commands

  • npm run build — tsc project references + UI (vite)
  • npm run check — lint (biome) + typecheck + all tests
  • npm run test:unit / npm run test:dogfood — vitest projects (unit aliases vibe-frame-* to sources)
  • npm run version:sync / version:check — root package.json is the only version authority

Conventions

  • TypeScript strict, ESM only, node: import protocol, no default exports.
  • Biome for lint + format; run npm run lint:fix before committing.
  • Conventional commits; one coherent module/phase per commit; docs updated in the same commit as behavior.
  • Determinism is the product: no wall-clock/randomness in library code paths without injection (Clock/IdSource interfaces in core); tests must be seed- and time-stable.
  • Validator precision invariant: every reflexion check has a false-positive corpus under its package tests; a check firing on its corpus is a CI failure.
  • Three version domains, never conflated: product semver (root package.json), .vibeframe schemaVersion (SCHEMA_VERSION in core), SQLite index schema (PRAGMA user_version, rebuild on mismatch).
  • Tool output discipline: MCP responses stay far under the 25k-token cap — compact, paginated, cursor-carrying.

Read the full file on GitHub · 46 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 First seen · 46 lines · 712 tokens per session scan A 9341da5eb091

Subscribe to this mod's changes

vibeframe CLAUDE.md is an instructions file published in the GitHub repository jubayertalha/vibeframe (0 stars, last pushed 10d ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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 · 6,785 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 · 7,296 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens