What is beevibe CLAUDE.md?

A set of project instructions for Beevibe, a monorepo—one repository containing several related applications and packages. It describes the API, web app, scheduler, daemon, and shared core, including how the shared core is compiled before other parts can use changes.

Use it when running the local development stack, changing shared core code, working on the API, daemon, scheduler, or web app, or diagnosing why a source change is not being picked up.

It explains the project's package layout and a common source of confusing stale-code problems. Changes in the shared core are not visible to the API or daemon until that package is compiled into its distribution folder.

How beevibe-ai/beevibe configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to beevibe-ai/beevibe. 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/beevibe-ai/beevibe/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/beevibe-ai/beevibe

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/beevibe-ai/beevibe/claude-md/github.svg)](https://agentmods.dev/instructions/beevibe-ai/beevibe/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/beevibe-ai/beevibe/claude-md"><img src="https://agentmods.dev/badge/instructions/beevibe-ai/beevibe/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/beevibe-ai/beevibe/claude-md"><img src="https://agentmods.dev/badge/instructions/beevibe-ai/beevibe/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,886 This file is loaded in full into every session.

When invoked 2,886 The same file — it is already loaded in full.

Security scan A 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.

Model	Per session	Once invoked
Fable 5.1	$0.02886	$0.02886
Opus 5.5	$0.01154	$0.01154
Sonnet 5.5	$0.00577	$0.00577
Haiku 4.5	$0.00289	$0.00289

Measured 1mo ago against content hash 297b141c72b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

beevibe CLAUDE.md scanned grade A 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -sS -o /dev/null -w '%{http_code}\n' https://fonts.googleapis.com/css2?family=Inter`.

CLAUDE.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beevibe — Claude Code Guide

Monorepo structure

packages/
  core/       shared domain, ports, services, adapters — compiled to dist/
  api/        Express API + MCP server (tsx watch src/main.ts)
  daemon/     Local agent runner (tsx watch src/main.ts start)
  scheduler/  Cron + background jobs
  web/        Next.js frontend
scripts/
  dev.sh      One-command local stack (postgres + core watch + api + scheduler)

Running locally

pnpm dev          # everything: postgres, core watcher, api, scheduler, tunnel
pnpm dev --no-tunnel

pnpm dev now:

Kills any stale beevibe processes from previous runs
Starts tsc --watch for @beevibe/core so source changes compile automatically
Starts API and scheduler (tsx watch, reload on file change)

The daemon is NOT started by pnpm dev — start it separately:

cd packages/daemon && npx tsx watch src/main.ts start

Critical: @beevibe/core compiles to dist/

packages/core/package.json exports point to ./dist/, not ./src/. Changes to packages/core/src/** are invisible to the API and daemon until compiled.

pnpm dev now runs tsc --watch for core automatically. If you're not using pnpm dev (e.g. running the API standalone), rebuild manually first:

pnpm --filter @beevibe/core build

After a core rebuild, touch a file in the consuming package to force tsx reload:

touch packages/api/src/runtime/router.ts   # reload API
touch packages/daemon/src/spawner.ts       # reload daemon

Restarting cleanly

pnpm dev uses trap 'kill 0' EXIT but only kills its own children. If you close the terminal without Ctrl+C, tsx/node processes linger and hold ports.

To fully reset:

pkill -f "beevibe/(packages|scripts)"
pkill -f "daemon/src/main"

Or just run pnpm dev — it does this cleanup at the start now.

Agent runtime (Claude Code CLI)

The CLI binary is claude on PATH
Sessions spawn with --dangerously-skip-permissions --strict-mcp-config
MCP config lives in ~/.beevibe/workspaces/<agent_id>/mcp-config.json
Agent cwd is the workspace path (~/.beevibe/workspaces/<agent_id>)

Read the full file on GitHub · 262 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.

1mo ago First seen · 262 lines · 2,886 tokens per session scan A 297b141c72b6

Subscribe to this mod's changes

beevibe CLAUDE.md is an instructions file published in the GitHub repository beevibe-ai/beevibe (346 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,886 tokens to every session, about $0.0115 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent agent-memory agent-orchestration agent-os agent-runtime future-of-work

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 · 9,649 tokens

beevibe: Instructions file for Claude Code