tmux-rc AGENTS.md

tmux-rc AGENTS.md is an instructions file for Codex, OpenCode from querystory/tmux-rc. It costs 949 tokens per session, scanned A, original, MIT.

Working instructions for tmux-rc, a project that uses tmux to run a live development service and test changes on a phone instance.

In plain words
What is it for?
Running a branch in the live development daemon, testing Python and web changes, managing worktrees, and following the project’s review and interface conventions.
Why use it?
They explain how branches, worktrees, the service’s working directory, and reloads interact, preventing broken live tests and stranded processes.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/querystory/tmux-rc/agents-md
Clone the repo
git clone --depth 1 https://github.com/querystory/tmux-rc

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for tmux-rc AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/querystory/tmux-rc/agents-md.svg)](https://agentmods.dev/instructions/querystory/tmux-rc/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/querystory/tmux-rc/agents-md"><img src="https://agentmods.dev/badge/instructions/querystory/tmux-rc/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 949 This file is loaded in full into every session.
When invoked 949 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00949 $0.00949
Opus 5 $0.00475 $0.00475
Sonnet 5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured 4d ago against content hash 462151da9b01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tmux-rc 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.

AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — working conventions for tmux-rc

Conventions for AI agents (and humans) working in this repo. The philosophy notes in the harness/session prompt still apply (minimize LOC, DRY, KISS, why-focused docs); this file captures repo-specific workflow that isn't obvious from the code.

Testing changes on the live dev instance

The dev daemon always runs make dev from the REPO ROOT, in a dedicated tmux pane. To test a branch on the live phone instance, git checkout <branch> in the root and restart the daemon — never cd the daemon into a worktree.

  • The daemon loads web/, prompts, etc. relative to its cwd. Running from the stable root means a later git worktree remove can never delete the cwd out from under it (that strands the process → FileNotFoundError on parser_prompt.txt, site returns {"detail":"Not Found"}, and even cd/make fail with "getcwd: No such file").
  • To make branch X live: from root, git checkout X, then in that pane: C-c, then make dev > out.log 2>&1. StatReload restarts on .py edits; for web/ changes just reload the page (assets are served no-store).
  • A branch checked out in a .claude/worktrees/* worktree can't also be checked out in root — git worktree remove it first (after pushing), then checkout in root.
  • The live instance is at <slug>.<your-tunnel-domain> (via the tunnel client, run in its own window). A momentary "no tunnel connected" is the relay's ~1h connection cap; the client auto-reconnects within ~1min.

Develop in worktrees, off main

Each change gets a clean worktree cut from origin/main (git worktree add -b <branch> .claude/worktrees/<name> origin/main). Stacking PRs on a non-main base has repeatedly caused merge pain (features silently reverted when the base squash-merges) — prefer branching off main and merging main in, over stacking.

Review before merge

No PR merges with unaddressed review comments. Drive Copilot review to clean (resolve every thread, re-request, repeat) before merging. Merge only on the user's explicit word.

Read the full file on GitHub · 69 lines

Changes

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.

  1. 4d ago First seen · 69 lines · 949 tokens per session scan A 462151da9b01

Subscribe to this mod's changes

tmux-rc AGENTS.md is an instructions file published in the GitHub repository querystory/tmux-rc (2 stars, last pushed 5d ago), licensed MIT. It adds 949 tokens to every session, about $0.0047 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.