claude-statusline-burnrate: Instructions file for Codex

AGENTS.md

claude-statusline-burnrate AGENTS.md is an instructions file for Codex, OpenCode from Gui-Gou/claude-statusline-burnrate. It costs 648 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining a Bash status line that reads JSON and prints terminal status text. They describe the files, compatibility rules, optional dependencies, caching, rendering limits, and release process.

In plain words
What is it for?
Use them when editing the status-line scripts, demos, image-generation tools, changelog, tests, or release-related files.
Why use it?
They give an AI coding agent the project's constraints so changes stay compatible with macOS Bash and do not block status rendering.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions AGENTS.md.

This is Gui-Gou/claude-statusline-burnrate's own configuration. It tells Codex and OpenCode how to work on claude-statusline-burnrate 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-statusline-burnrate configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Gui-Gou/claude-statusline-burnrate. 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/Gui-Gou/claude-statusline-burnrate/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Gui-Gou/claude-statusline-burnrate

Made for: Codex, OpenCode.

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-statusline-burnrate AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/gui-gou/claude-statusline-burnrate/agents-md/github.svg)](https://agentmods.dev/instructions/gui-gou/claude-statusline-burnrate/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/gui-gou/claude-statusline-burnrate/agents-md"><img src="https://agentmods.dev/badge/instructions/gui-gou/claude-statusline-burnrate/agents-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-statusline-burnrate AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gui-gou/claude-statusline-burnrate/agents-md"><img src="https://agentmods.dev/badge/instructions/gui-gou/claude-statusline-burnrate/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 648 This file is loaded in full into every session.
When invoked 648 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 $0.00648 $0.00648
Opus 5.5 $0.00259 $0.00259
Sonnet 5.5 $0.00130 $0.00130
Haiku 4.5 $0.00065 $0.00065

Measured 1mo ago against content hash 4b67e32454b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-statusline-burnrate AGENTS.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.

- **jq is the only hard dependency.** Anything else (`curl`, `git`, `python3`, `agy`) must be optional: check it with `command -v` and skip quietly if it is missing.
AGENTS.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

A Claude Code status line: bash that reads the JSON payload on stdin and prints ANSI text. No build step and no tests beyond the checks below.

Files

  • statusline.sh — the default: a two-row card (v2).
  • statusline-classic.sh — the one-line v1. Same math. Keep fixes to the shared math in sync across both files.
  • demo.sh — renders fake payloads with an isolated $HOME. --classic and --live also work.
  • tools/make-images.sh — rebuilds every README image from real script output (ansi2html.py --grid → headless Chrome → autocrop.py). tools/infographic.py lays out the annotated card.
  • CHANGELOG.md — one entry per release.

Rules

  • bash 3.2 (the macOS default): no ${var^^}, no associative arrays, no mapfile. Use tr for case changes.
  • jq is the only hard dependency. Anything else (curl, git, python3, agy) must be optional: check it with command -v and skip quietly if it is missing.
  • Never block a render. Network or other slow calls run in the background and write a cache under ~/.claude/.cache/; the render only reads that cache.
  • Widths are hand-tracked. ANSI codes take no columns, an emoji takes 2, and ▰ ╳ ↻ ⌂ take 1. When you add or change a glyph, update the matching …l / …len counter, or the card's right border goes crooked.
  • Portability: macOS (BSD) and Linux (GNU) both have to work. date -v… first, then date -d …. But stat is the other way round, stat -c %Y || stat -f %m: on GNU, stat -f %m fails after writing filesystem info to stdout, which ends up inside $(…).
  • No personal data: no home paths, hostnames or personal schedules. Put anything user-specific behind an SL_* variable with a sensible default, and document it in the README's Tweak table.

Before you commit

bash -n statusline.sh && bash -n statusline-classic.sh
./demo.sh && ./demo.sh --classic      # check the card's right border lines up
bash tools/make-images.sh             # only when the look changed (needs Chrome + Pillow)

Read the full file on GitHub · 35 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. 1mo ago First seen · 35 lines · 648 tokens per session scan A 4b67e32454b5

Subscribe to this mod's changes

claude-statusline-burnrate AGENTS.md is an instructions file published in the GitHub repository Gui-Gou/claude-statusline-burnrate (21 stars, last pushed 12d ago), licensed MIT. It adds 648 tokens to every session, about $0.0026 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 2026-09-26.

Related

Other instructions, from other repositories