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/kkd927/kmux/agents-mdgit clone --depth 1 https://github.com/kkd927/kmuxWrote 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/kkd927/kmux/agents-md)<a href="https://agentmods.dev/instructions/kkd927/kmux/agents-md"><img src="https://agentmods.dev/badge/instructions/kkd927/kmux/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 | $0.00324 | $0.00324 |
| Opus 5 | $0.00162 | $0.00162 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
kmux 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 4d 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.
What it actually says
AGENTS.md
kmux focus
kmux is a terminal app for working with coding AI agents such as Claude Code, Codex CLI, and Gemini CLI.
The product should prioritize reliable multi-surface agent workflows: agent output must stay stable, readable, and unbroken while users switch surfaces, split panes, restore sessions, and keep multiple agent conversations running side by side.
When changing terminal, pane, surface, restore, or rendering behavior, treat coding-agent output continuity as a primary product requirement.
Test discipline
Do not add or expand automated tests merely because code changed. Tests are for behavior important enough that CI should prevent it from regressing.
- Do not add tests for trivial visual or mechanical edits such as pixel-level spacing, alignment, colors, copy changes, simple element moves, or removal of UI that has no meaningful behavioral contract.
- Add tests for significant logic and durable contracts such as state transitions, data transformations, persistence and restore behavior, process or session lifecycle, security boundaries, error handling, and regressions that would materially affect users.
- For minor UI changes, use proportionate visual or manual verification when useful instead of encoding incidental markup, text, or CSS details into CI.
- When removing behavior, remove obsolete tests and fixtures. Do not replace them with negative assertions unless absence is itself a meaningful product requirement or a credible regression risk.
- Test a rule at the layer that owns it. Avoid duplicating the same assertion across normalization, state, and rendering layers.
- Prefer observable outcomes over implementation details. Keep every assertion relevant to the behavior named by the test.
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.
- 4d ago First seen · 21 lines · 324 tokens per session scan A 0eb219fb3fa9
kmux AGENTS.md is an instructions file published in the GitHub repository kkd927/kmux (25 stars, last pushed today), licensed MIT. It adds 324 tokens to every session, about $0.0016 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
corral AGENTS.md
Instructions for x0c/corral, covering corral, 文档导航, 组件一览, 领域地图(doc-init) and 待补充知识库(doc-init backlog).
herd CLAUDE.md
Claude Code instructions for poddubnyoleg/herd, covering claude.md, commands, architecture and key design decisions.
herd GEMINI.md
Gemini CLI instructions for poddubnyoleg/herd, covering gemini.md, architecture overview, core tasks & behaviors, file structure and api endpoints.
corral CLAUDE.md
Instructions for x0c/corral, a project described as: Corral: terminal session handoff for Claude Code, Codex, OpenCode, Kimi, Cursor, and Pi.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.