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/accessd/tmux-agent-indicator/agents-mdgit clone --depth 1 https://github.com/accessd/tmux-agent-indicatorWhat 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 | $0.00548 | $0.00548 |
| Opus 5 | $0.00274 | $0.00274 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
tmux-agent-indicator 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 2d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is a tmux plugin written in Bash.
agent-indicator.tmux: plugin entrypoint; injects#{agent_indicator}and registers focus/window hooks.scripts/agent-state.sh: state machine forrunning,needs-input,done,off; applies/restores pane, border, and window-title styles.scripts/pane-focus-in.sh: clears deferreddonestyling when pane/window focus changes.scripts/indicator.sh: status segment renderer (icons + process/state detection).hooks/: Claude and Codex hook templates.docs/: product notes and testing docs (docs/PRD.md,docs/TESTING.md, assets).
Keep runtime logic in scripts/; keep agent-indicator.tmux focused on bootstrap/hook wiring.
Build, Test, and Development Commands
No build step is required.
bash -n agent-indicator.tmux scripts/*.sh install.sh setup.sh: syntax check.shellcheck agent-indicator.tmux scripts/*.sh install.sh setup.sh: lint (if installed).tmux source-file ~/.tmux.conf: reload tmux config../install.sh --target-dir ~/.tmux/plugins/tmux-agent-indicator: local install/update.
For behavior verification, use the step-by-step playbooks in docs/TESTING.md.
Coding Style & Naming Conventions
- Bash with
#!/usr/bin/env bashandset -euo pipefail. - Indentation: 4 spaces, no tabs.
- Script names: lowercase kebab-case (for example
agent-state.sh). - Variables: uppercase for exported/config keys (
TMUX_AGENT_*), lowercase for locals. - Always quote expansions (
"$var"), and keep tmux failures non-fatal where recovery is expected (|| true).
Testing Guidelines
- Prefer automated tmux-socket tests first, then manual UX checks.
- Validate all four states:
running,needs-input,done,off. - Verify empty-value semantics (
'') skip property application. - Verify focus-driven reset behavior for done styling (pane/window focus hooks).
Use docs/TESTING.md as the source of truth for commands and expected results.
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.
- 2d ago First seen · 44 lines · 548 tokens per session scan A f22e7c0c4448
tmux-agent-indicator AGENTS.md is an instructions file published in the GitHub repository accessd/tmux-agent-indicator (91 stars, last pushed 19d ago), licensed MIT. It adds 548 tokens to every session, about $0.0027 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
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.