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/binsarjr/termul/agents-mdgit clone --depth 1 https://github.com/binsarjr/termulWrote 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/binsarjr/termul/agents-md)<a href="https://agentmods.dev/instructions/binsarjr/termul/agents-md"><img src="https://agentmods.dev/badge/instructions/binsarjr/termul/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 | $0.05397 | $0.05397 |
| Opus 5 | $0.02698 | $0.02698 |
| Sonnet 5 | $0.01079 | $0.01079 |
| Haiku 4.5 | $0.00540 | $0.00540 |
Grade A, and why
termul 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 3d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Termul loads AGENTS.md from the workspace root as agent memory (similar to AGENTS.md / CLAUDE.md). This file is also the project's living architecture doc — read it before making changes.
Project
Termul (TERminal mULtiplexer) — open-source AI-native terminal & dev workspace. Tauri 2 + Rust (portable-pty) backend, React 19 + TypeScript + xterm.js (webgl) client, BYOK AI via Vercel AI SDK v6.
- Bundle id:
app.binsarjr.termul - Package manager: pnpm
- Platforms: macOS, Linux, Windows
- Frontend checks:
pnpm exec tsc --noEmit,pnpm test - Rust checks:
cd src-tauri && cargo clippy && cargo test --locked
Quality bar
Production-grade or it does not ship. Every change is judged against all of these, not just "it works":
- Correctness: edge cases, failure modes, concurrent access. No "works for now".
- Performance: ultra-lightweight is the product. ~7-8 MB bundle, high-performance terminal. For every change ask: how much RAM it costs, whether it adds IPC round-trips or redundant requests, whether it triggers extra re-renders or wasted work, whether it pulls a heavy dependency. Unused features consume zero resources. Lightweight-first is non-negotiable: if a requirement or proposed change risks added latency or lag (input-to-render, scrolling, large/streamed output, extra re-renders or IPC round-trips, a heavy dependency), STOP and raise it with the user before implementing. Do not silently absorb the cost — speak up first and discuss the trade-off.
- Security: no critical security holes. Validate at every boundary (IPC, fs, network, AI tool surface). The secret-path deny-list applies on both read and write and is never bypassed.
- UI/UX: polished, professional, premium. Every state and detail considered.
- Architecture: new or changed logic lives in pure, dependency-light functions (functional core); tauri commands and React components stay thin (imperative shell). Keeps it testable without a later rewrite.
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.
- 3d ago First seen · 158 lines · 5,397 tokens per session scan A 02b1dac8397e
termul AGENTS.md is an instructions file published in the GitHub repository binsarjr/termul (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,397 tokens to every session, about $0.0270 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
pisper AGENTS.md
Instructions for ling-kong-ran/pisper, covering agents.md, project, architecture, commands and setup.
tmuxy CLAUDE.md
Claude Code instructions for flplima/tmuxy, covering tmuxy, project structure, cli usage, pane operations and tab operations.
terminal-use CLAUDE.md
Instructions for flipbit03/terminal-use, covering terminal-use (tu), build & test, architecture, conventions and git commits.
mars AGENTS.md
Instructions for Yazelix/mars, covering mars agent guide, workflow, source boundaries, validation and release workflow.
zashiki CLAUDE.md
Instructions for kounetsuman/zashiki, covering zashiki development conventions, comment conventions, testing, documentation (where design, specs, and context live) and issues vs. discussions.
agent-of-empires AGENTS.md
AGENTS.md instructions for agent-of-empires/agent-of-empires, covering repository guidelines, where to look, commands, code rules and tests.