claude-office: Instructions file for Claude Code

CLAUDE.md

claude-office CLAUDE.md is an instructions file for Claude Code from bpinheiroms/claude-office. It costs 2,420 tokens per session, scanned A, original, MIT.

A Claude Code statusline plugin that displays plan quota, costs, savings, tool activity, agent tracking, and todo progress. Claude Code starts it as a short-lived process about every 300 milliseconds.

In plain words
What is it for?
Use it when changing the statusline display, its cached data, file access, performance behavior, or type-checking and formatting setup.
Why use it?
Its strict runtime and Bun-only rules help keep the statusline responsive and compatible with how Claude Code invokes it.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is bpinheiroms/claude-office's own configuration. It tells Claude Code how to work on claude-office 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 claude-office configures →

Reuse

Borrowing it

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

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 claude-office CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bpinheiroms/claude-office/claude-md"><img src="https://agentmods.dev/badge/instructions/bpinheiroms/claude-office/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,420 This file is loaded in full into every session.
When invoked 2,420 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02420 $0.02420
Opus 5 $0.01210 $0.01210
Sonnet 5 $0.00484 $0.00484
Haiku 4.5 $0.00242 $0.00242

Measured 9d ago against content hash ebaec2e69d85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-office 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 9d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **NEVER use Node.js**: no `fs`, no `readline`, no `stream`, no `http`, no `child_process`
CLAUDE.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Claude Office

What is this?

Claude Office is a statusline plugin for Claude Code that shows plan quota, real-time costs, monthly saving, tool activity, agent tracking, and todo progress. It runs as a stateless single-shot process invoked by Claude Code every ~300ms.

Hard rules

These rules are non-negotiable. Follow them exactly.

Bun only — zero Node.js APIs

  • All file I/O must use Bun APIs: Bun.file(), Bun.write(), Bun.stdin, Bun.file().stream(), Bun.file().slice()
  • NEVER use Node.js: no fs, no readline, no stream, no http, no child_process
  • Exception: path and os from Node.js are fine (Bun provides compatible implementations)
  • TypeScript runs directly via bun run — no build step, no bundler, no transpiler
  • Use bun run typecheck (runs tsc -p tsconfig.json) to validate types

Performance budget: 300ms max

  • Claude Code kills the statusline process after 300ms — every code path must complete within this
  • Cache hit path must be <5ms — this is the common case (~95% of invocations)
  • Cache miss path must be <200ms — network + file I/O + parsing
  • Never block on a single slow operation — use Promise.all() to parallelize independent work
  • Never do synchronous file I/O in the hot path

ANSI colors: 24-bit RGB only

  • Use \x1b[38;2;r;g;bm format — no 16-color ANSI, no 256-color fallback
  • All colors are defined in the C object in render.ts via the c(r, g, b) helper
  • Always reset with \x1b[0m (the RST constant) after colored text

Non-breaking spaces

  • Use \u00A0 (non-breaking space) between statusline elements to prevent terminal whitespace collapsing
  • The S constant in render.ts is \u00A0 — use it instead of regular spaces in output

Project structure

src/
  statusline/               # Statusline plugin (stateless, single-shot)
    index.ts                # Entry: stdin -> config -> [quota, usage, transcript] -> render -> stdout
    stdin.ts                # Parse Claude Code's stdin JSON (model, context window, transcript path)
    config.ts               # Config loader with presets (full/minimal), mtime-cached
    usage-scanner.ts        # Token cost aggregation from JSONL files (30s cache, per-file mtime tracking)
    render.ts               # Modular ANSI renderer with extracted tools/agents/todos functions
    transcript.ts           # Incremental transcript parser (10s cache, byte-offset tracking)
  data/
    types.ts                # QuotaData type definition
    quota-api.ts            # Anthropic OAuth usage API + automatic token refresh (60s cache)
.claude-plugin/
  plugin.json               # Claude Code plugin metadata (name, commands, version)
  marketplace.json          # Plugin marketplace listing
skills/
  setup/
    SKILL.md                # /claude-office:setup — configures statusline in settings.json
  configure/
    SKILL.md                # /claude-office:configure — interactive display configuration

Read the full file on GitHub · 194 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. 9d ago First seen · 194 lines · 2,420 tokens per session scan A ebaec2e69d85

Subscribe to this mod's changes

claude-office CLAUDE.md is an instructions file published in the GitHub repository bpinheiroms/claude-office (7 stars, last pushed 4mo ago), licensed MIT. It adds 2,420 tokens to every session, about $0.0121 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

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 · 5,153 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

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

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

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 · 3,735 tokens