Borrowing it
Nothing to install: this file belongs to KiryuuLight/zellij-attention. 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/KiryuuLight/zellij-attention/main/AGENTS.mdgit clone --depth 1 https://github.com/KiryuuLight/zellij-attentionWrote 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/kiryuulight/zellij-attention/agents-md)<a href="https://agentmods.dev/instructions/kiryuulight/zellij-attention/agents-md"><img src="https://agentmods.dev/badge/instructions/kiryuulight/zellij-attention/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.
<a href="https://agentmods.dev/instructions/kiryuulight/zellij-attention/agents-md"><img src="https://agentmods.dev/badge/instructions/kiryuulight/zellij-attention/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00612 | $0.00612 |
| Opus 5 | $0.00306 | $0.00306 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
zellij-attention AGENTS.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 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.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Project Overview
Zellij WASM plugin that adds notification icons to tab names when panes need attention. Designed for Claude Code users running multiple sessions across tabs.
Flow: External process → zellij pipe --name "zellij-attention::EVENT::PANE_ID" → plugin updates tab name → focus clears notification.
Architecture
src/main.rs— Core plugin logic: event handling, tab renaming, pipe parsing, focus clearingsrc/config.rs— User configuration parsing (enabled, waiting_icon, completed_icon)- Build target:
wasm32-wasip1(Zellij WASM plugin)
Key Design Decisions
- Single global plugin instance via
load_pluginsinconfig.kdl(no visible pane) - Notification state:
HashMap<u32, HashSet<NotificationType>>— pane_id → notification set. Latest event replaces (no stacking per pane) - Tab-level priority: If any pane in a tab has Waiting, tab shows ⏳. Only shows ✓ if no Waiting exists.
- No position-keyed caches — original tab names derived via
strip_icons()at rename time, making tab reordering safe rename_tab()is 1-indexed — Zellij API quirk, always passposition + 1updating_tabsflag prevents re-entrancy fromrename_tab()→TabUpdate→update_tab_names()loop
Zellij Plugin Gotchas
- Use broadcast pipes (
zellij pipe --name) NOT targeted pipes (--plugin) — targeted pipes create new instances due to config mismatch - Plugin state must use
/host/path (shared), NOT/data/(sandboxed per-instance) load_pluginsin config.kdl supports configuration via plugin aliases or inline config blocks- Plugin pane IDs overlap with terminal pane IDs — always filter
is_pluginwhen mapping panes rename_tab()triggers a synchronousTabUpdateevent — beware of race conditions between rename and the resulting eventload_pluginsplugins may be lost after session resurrection (zellij attach) — see #4156- After rebuilding WASM, clear Zellij cache:
find ~/.cache/zellij -path "*zellij-attention*" -exec rm -f {} \;
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.
- 9d ago First seen · 47 lines · 612 tokens per session scan A 117a2a22ef3b
zellij-attention AGENTS.md is an instructions file published in the GitHub repository KiryuuLight/zellij-attention (61 stars, last pushed 5mo ago), licensed MIT. It adds 612 tokens to every session, about $0.0031 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.
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.
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).
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).
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.
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.