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.
npx agentmods add instructions/michalstrnadel/agentbar/claude-mdgit clone --depth 1 https://github.com/michalstrnadel/AgentBarWrote 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/michalstrnadel/agentbar/claude-md)<a href="https://agentmods.dev/instructions/michalstrnadel/agentbar/claude-md"><img src="https://agentmods.dev/badge/instructions/michalstrnadel/agentbar/claude-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 | $0.00506 | $0.00506 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
AgentBar 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentBar — AI Instructions
Context for AI coding assistants working on this repository.
Project
AgentBar is a native macOS status app (Swift, AppKit, SPM) showing live status of
AI coding agents (Claude Code, Codex, Cursor, Gemini, Copilot, Antigravity). Node.js hook scripts in
Scripts/hooks/ write per-session JSON to ~/.agentbar/state.d/; the app watches
that folder. It presents itself as a menu bar item, a Dynamic Island panel under the
notch, or both — the user picks in the welcome window. State file protocol (normative):
docs/protocol.md; original design spec (a 1.0.0 snapshot, read its header note):
docs/specs/2026-07-23-agentbar-design.md; presentation modes:
docs/plans/2026-07-28-presentation-modes-and-island.md.
Build & run
./Scripts/build.sh # builds build/AgentBar.app
open "build/AgentBar.app"
Rules
- One file, one responsibility — keep the unit layout from the spec; don't grow a god-object controller.
- Stay out of the way: no dock icon, no heavy dependencies, nothing that unfolds
over the screen on its own. Two surfaces only — the menu bar item
(
StatusItemController) and the island (IslandController) — both fed from the same stores throughMascotDriver/AgentActions; never render one from the other's code. Windows are the exception, not the pattern: onlyWelcomeWindowandSettingsWindow, both small, both opened by the user. - Hooks must never block the host agent: async, atomic writes, exit fast.
Sole exception:
permission.jsblocks while the session is already waiting on the human, and must always time out silently to the normal terminal prompt. - Adding an agent: entry in
Agents.swift, sprite inSources/AgentBar/Sprites/, optional hook dir inScripts/hooks/<agent>/plus its installer step inHookInstaller.swift, and the agent id in thedocs/protocol.mdlist and the README agent table. Nothing else should need touching. - Third-party marks stay listed in
THIRD_PARTY_NOTICES.md.
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.
- 5d ago First seen · 38 lines · 506 tokens per session scan A 0c05299251ec
AgentBar CLAUDE.md is an instructions file published in the GitHub repository michalstrnadel/AgentBar (4 stars, last pushed 4d ago), licensed MIT. It adds 506 tokens to every session, about $0.0025 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 2026-08-31.
Other instructions, from other repositories
mectrics AGENTS.md
AGENTS.md instructions for farukkamcici/mectrics, covering agents.md — working agreement for mectrics, 0. golden rule: english-only repository, 1. project shape, 2. internationalization (i18n) and 3. menu bar rendering rules.
mectrics CLAUDE.md
Claude Code instructions for farukkamcici/mectrics, covering claude.md, absolute must-knows (see agents.md for detail), fast local loop (no xcode ui), build & run the app and notes.
Sluice CLAUDE.md
Instructions for Franlinozz/Sluice, covering what we're building, non-negotiable rules, canonical sources of truth (fetch these, don't guess), payment flow (the exact 8 steps — memorize) and stack (pinned choices — see "pinned versions").
build-swift-apps AGENTS.md
AGENTS.md instructions for Xopoko/build-swift-apps, covering agent guidance, project shape, scope, skill catalog and rules for editing.
Vesta AGENTS.md
AGENTS.md instructions for vestaterm/Vesta, covering agents.md — rules for ai agents working in vesta, golden rules, build / run / test, architecture (where things live, all under sources/) and config & cli.
browser AGENTS.md
Instructions for lucid-softworks/browser, covering agents.md, pull requests, before you open a pr, guiding constraint and web platform tests (conformance).