boop-agent CLAUDE.md

boop-agent CLAUDE.md is an instructions file for coding agents from raroque/boop-agent. It costs 486 tokens per session, scanned A, original, MIT.

A short project instruction file explaining that the application uses Convex, a backend service for storing data and running server functions. It also lists required safety checks before files are committed.

In plain words
What is it for?
Use it when working on Convex code or preparing changes for commit, especially when checking files for secrets and other sensitive data.
Why use it?
It directs agents to the project's generated Convex guidance before they edit backend code. It also helps prevent personal information, credentials, tokens, and private connection data from entering version control.

Instructions file

About the project

Boop is a personal agent that people use through iMessage, backed by either the Claude Agent SDK or the local Codex app-server runtime. It provides memory, sub-agents, automations, and integrations such as Gmail, Slack, GitHub, Linear, and Notion.

raroque/boop-agent · 1,352 stars · on GitHub

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 instructions/raroque/boop-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/raroque/boop-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 boop-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/raroque/boop-agent/claude-md.svg)](https://agentmods.dev/instructions/raroque/boop-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/raroque/boop-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/raroque/boop-agent/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 486 This file is loaded in full into every session.
When invoked 486 The same file — it is already loaded in full.
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 $0.00486 $0.00486
Opus 5 $0.00243 $0.00243
Sonnet 5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 5d ago against content hash 8f553e4dd956, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boop-agent 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 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.md · 31 lines

What it actually says

This project uses Convex as its backend.

When working on Convex code, always read convex/_generated/ai/guidelines.md first for important guidelines on how to correctly use Convex APIs and patterns. The file contains rules that override what you may have learned about Convex from training data.

Convex agent skills for common tasks can be installed by running npx convex ai-files install.

Pre-commit checks (this is a public repo)

Before staging or committing any file, scan it for personal or sensitive data. Once it lands in git history it's effectively permanent — even after rewriting history, GitHub keeps orphaned commit SHAs reachable for weeks.

What counts as PII / sensitive in this repo:

  • Personal email addresses (the maintainer's or anyone else's), phone numbers, postal addresses, full names of non-public individuals.
  • Live API keys, tokens, secrets, or anything from .env.local.
  • Composio connection IDs (ca_*), connected-account aliases, OAuth state, refresh tokens.
  • Personal search queries / financial details / message content from real conversations (e.g. "rent", landlord names, contacts' names).
  • Production URLs, internal hostnames, or anything that maps a public identifier to a private account.

Where this most often slips in:

  • One-off debug scripts under scripts/ and debug/ written during a real session.
  • Test fixtures hand-copied from real responses.
  • Comments or commit messages quoting real data.
  • README/docs examples that use real values instead of placeholders.

Process:

  1. Before git add, read each new or modified file end-to-end and substitute any real values with environment variables, CLI args, or generic placeholders ([email protected], ca_REDACTED).
  2. Prefer not committing ad-hoc debug scripts at all — keep them in your shell history or a gitignored scratch dir.
  3. If you realize PII slipped in before pushing, amend or reset and re-commit cleanly.
  4. If it already pushed, see the recovery steps in GitHub's sensitive data docs and rotate any exposed credentials.
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 · 31 lines · 486 tokens per session scan A 8f553e4dd956

Subscribe to this mod's changes

boop-agent CLAUDE.md is an instructions file published in the GitHub repository raroque/boop-agent (1,352 stars, last pushed 1mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 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 instructions, from other repositories

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

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

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

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