Borrowing it
Nothing to install: this file belongs to ilia-pluzhnikov/claude-code-statusline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ilia-pluzhnikov/claude-code-statusline/main/AGENTS.mdgit clone --depth 1 https://github.com/ilia-pluzhnikov/claude-code-statuslineWrote 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.
[](https://agentmods.dev/instructions/ilia-pluzhnikov/claude-code-statusline/agents-md)<a href="https://agentmods.dev/instructions/ilia-pluzhnikov/claude-code-statusline/agents-md"><img src="https://agentmods.dev/badge/instructions/ilia-pluzhnikov/claude-code-statusline/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01089 | $0.01089 |
| Opus 5 | $0.00544 | $0.00544 |
| Sonnet 5 | $0.00218 | $0.00218 |
| Haiku 4.5 | $0.00109 | $0.00109 |
Grade A, and why
claude-code-statusline 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 8d 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.
- **No dependencies.** Everything is built-in Node.js (`fs`, `path`, `os`, `child_process`). Don't add a `package.json` with deps. If a feature needs an npm package, the answer is probably "the feature doesn't belong her Copies of this mod
2 near-identical copies found in the catalogue:
- claude-code-statusline CLAUDE.md — 100% identical, 2 lines differ
- claude-code-statusline GEMINI.md — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-statusline
Sync: Any changes to this file must also be applied to
CLAUDE.mdandGEMINI.md.
A single-file Node.js statusline for Claude Code, plus three optional companion hooks that keep CLAUDE.md / AGENTS.md / GEMINI.md in sync and surface git state at session start.
Project shape
statusline.js— entry point. Reads JSON from stdin (model, workspace, session_id, context_window, rate_limits) and writes one ANSI-coloured line to stdout.optional-hooks/md-sync-check.js— SessionStart drift detector for the CLAUDE/AGENTS/GEMINI trio.optional-hooks/sync-md.js— PostToolUse mirror: writes CLAUDE.md → AGENTS.md + GEMINI.md, swapping theSync:line per file.optional-hooks/github-sync-check.js— SessionStart git status + cachedorigindivergence + background fetch for next session.
Rules for contributors (and AI agents)
- No dependencies. Everything is built-in Node.js (
fs,path,os,child_process). Don't add apackage.jsonwith deps. If a feature needs an npm package, the answer is probably "the feature doesn't belong here". - Single-file per concern.
statusline.jsis one file. Each hook is one file. No build step, no transpiler. - Exit 0 on any error. A broken hook must never block the user's tool call. Wrap risky logic in
try/catchandprocess.exit(0)on failure. Same forstatusline.js— empty output is acceptable, a thrown error that breaks Claude Code's UI is not. - Hot-path budget.
statusline.jsis invoked on every status refresh. No network, nogit fetchon the hot path. Use bridge files inos.tmpdir()and backgroundspawn(detached: true).unref()for anything that takes >100ms. - Hide on happy path. Segments only appear when they have something to say.
0 uncommittedis invisible.↑0 pushis invisible. Add new segments with the same discipline. - Cross-platform. Use
path.join,os.homedir(),windowsHide: trueon everyexecSync. No hard-coded/or\. No assumptions about which shell. - Avoid TUI-incompatible ANSI attributes. Blink (
\x1b[5m), strikethrough, and underline-color extensions are silently dropped by Ink-based TUIs (Claude Code) and disabled by default in modern terminals. For attention without animation, use bold + bright color, inverse video (\x1b[7m), or a background-color badge. Stick to widely-supported codes: 30-37 (fg), 40-47 (bg), 1 (bold), 2 (dim), 7 (inverse), 38;2;R;G;B (truecolor).
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.
- 8d ago First seen · 56 lines · 1,089 tokens per session scan A 4cbe4d598356
claude-code-statusline AGENTS.md is an instructions file published in the GitHub repository ilia-pluzhnikov/claude-code-statusline (112 stars, last pushed 18d ago), licensed MIT. It adds 1,089 tokens to every session, about $0.0054 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 2026-08-30.
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.
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).
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.
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.
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).
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.