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/steipete/tmuxwatch/agents-mdgit clone --depth 1 https://github.com/steipete/tmuxwatchWrote 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/steipete/tmuxwatch/agents-md)<a href="https://agentmods.dev/instructions/steipete/tmuxwatch/agents-md"><img src="https://agentmods.dev/badge/instructions/steipete/tmuxwatch/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 | $0.02085 | $0.02085 |
| Opus 5 | $0.01043 | $0.01043 |
| Sonnet 5 | $0.00417 | $0.00417 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade B, and why
tmuxwatch AGENTS.md scanned grade B with 1 finding 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- Run any command that could hang (tests, servers, log streams, browser automation) inside tmux using the repository’s preferred entry point. How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared guardrails distilled from the various ~/Projects/*/AGENTS.md files (state as of November 15, 2025). This document highlights the rules that show up again and again; still read the repo-local instructions before making changes.
Usage: In repo copies, the shared content lives inside <shared>…</shared> and the tool list inside <tools>…</tools>. Keep those tagged blocks identical across repos; anything outside them is repo-local and can be customized freely.
Codex Global Instructions
- Keep the system-wide Codex guidance at
~/.codex/AGENTS.md(the Codex home; override viaCODEX_HOMEif needed) so every task inherits these rules by default.
General Guardrails
Intake & Scoping
- Open the local agent instructions plus any
docs:listsummaries at the start of every session. Re-run those helpers whenever you suspect the docs may have changed. - Review any referenced tmux panes, CI logs, or failing command transcripts so you understand the most recent context before writing code.
Tooling & Command Wrappers
- Use the command wrappers provided by the workspace (
./runner …,scripts/committer,pnpm mcp:*, etc.). Skip them only for trivial read-only shell commands if that’s explicitly allowed. - Stick to the package manager and runtime mandated by the repo (pnpm-only, bun-only, swift-only, go-only, etc.). Never swap in alternatives without approval.
- When editing shared guardrail scripts (runners, committer helpers, browser tools, etc.), mirror the same change back into the
agent-scriptsfolder so the canonical copy stays current. - Ask the user before adding dependencies, changing build tooling, or altering project-wide configuration.
- When discussing dependencies, always provide a GitHub URL.
- Keep the project’s
AGENTS.md<tools></tools>block in sync with the full tool list fromTOOLS.mdso downstream repos get the latest tool descriptions.
tmux & Long Tasks
- Run any command that could hang (tests, servers, log streams, browser automation) inside tmux using the repository’s preferred entry point.
- Do not wrap tmux commands in infinite polling loops. Run the job, sleep briefly (≤30 s), capture output, and surface status at least once per minute.
- Document which sessions you create and clean them up when they are no longer needed unless the workflow explicitly calls for persistent watchers.
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 · 104 lines · 2,085 tokens per session scan B cad79085ad4c
tmuxwatch AGENTS.md is an instructions file published in the GitHub repository steipete/tmuxwatch (221 stars, last pushed 1mo ago), licensed MIT. It adds 2,085 tokens to every session, about $0.0104 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
zot AGENTS.md
AGENTS.md instructions for patriceckhart/zot, covering working agreement for zot, product intent, starting a task, code ownership map and correctness contracts.
pvetui AGENTS.md
AGENTS.md instructions for devnullvoid/pvetui, covering agent instructions, initial setup, development workflow, quick reference and code quality standards.
waveloom AGENTS.md
AGENTS.md instructions for Menfre01/waveloom, covering waveloom, 项目概要, 编码规范, 代码审查 and 开发流程.
pvetui CLAUDE.md
Claude Code instructions for devnullvoid/pvetui: Canonical instructions live in AGENTS.md.
ssm AGENTS.md
AGENTS.md instructions for lfaoro/ssm, covering ssm — agent working instructions, the prime directive, 2. non-negotiable rules, 3. architecture contracts (must remain true) and ssh config parser (pkg/sshconf).
forestui CLAUDE.md
Instructions for flipbit03/forestui, covering claude.md - ai development guidelines, never touch the user's live tmux, project overview, tech stack and project structure.