projmux: Instructions file for Codex

AGENTS.md

projmux AGENTS.md is an instructions file for Codex, OpenCode from crevissepartners/projmux. It costs 3,432 tokens per session, scanned A, original, MIT.

Repository-specific instructions for projmux, a standalone application for managing tmux terminal sessions. They describe supported systems, project boundaries, startup checks, branches, and pull requests.

In plain words
What is it for?
Use them when changing, building, reviewing, or releasing projmux on Linux or macOS.
Why use it?
They give coding agents the project rules needed to avoid unsupported platforms, misplaced changes, and incorrect contribution workflows.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is crevissepartners/projmux's own configuration. It tells Codex and OpenCode how to work on projmux itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything projmux configures →

Reuse

Borrowing it

Nothing to install: this file belongs to crevissepartners/projmux. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/crevissepartners/projmux/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/crevissepartners/projmux

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 projmux AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/crevissepartners/projmux/agents-md.svg)](https://agentmods.dev/instructions/crevissepartners/projmux/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/crevissepartners/projmux/agents-md"><img src="https://agentmods.dev/badge/instructions/crevissepartners/projmux/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,432 This file is loaded in full into every session.
When invoked 3,432 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.03432 $0.03432
Opus 5 $0.01716 $0.01716
Sonnet 5 $0.00686 $0.00686
Haiku 4.5 $0.00343 $0.00343

Measured yesterday against content hash efad1eaf1c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

projmux 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 yesterday.

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 · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

Scope

  • projmux is a standalone tmux session-management application.
  • Supported build targets are Linux and macOS on amd64 and arm64. That matrix is the whole contract: the release workflow builds only those four, no CI job builds any other GOOS, and GOOS=windows compilation is not supported or guaranteed. The repository carries no _windows.go files and no //go:build windows or //go:build !windows constraints; do not add them. WSL is not a separate target — it runs the Linux build under the Linux contract, and WSL-specific behavior such as PROJMUX_WSL_TOAST_ICON_DIR stays inside that build.
  • Keep portable session-management behavior in projmux.
  • Keep machine-local policy outside the application unless the migration plan explicitly calls for it.
  • Keep AGENTS.md focused on repo contract. Personal agent recipes, reverse-engineering notes, and machine-local operating memos belong in external local docs (Obsidian/dotfiles anchors), not this tracked file.
  • Local-only agent overlays may live in an untracked AGENTS.local.md anchored via dotfiles. This tracked file stays shareable and tool-agnostic.

Startup Checks

  • Confirm you are in the intended checkout/worktree with pwd.
  • Check local state with git status --short.

Branch And Checkout Rules

  • Use one branch per task. Preferred names: feat/<topic>, fix/<topic>, docs/<topic>, refactor/<topic>, chore/<topic>.
  • Use a dedicated checkout/worktree per task when parallel work would otherwise collide.
  • Keep one agent per checkout/worktree. Do not share a dirty checkout across agents.
  • If another agent owns a file, do not overwrite their changes. Adjust around them or coordinate a handoff.
  • Keep changes narrow. Split docs, bootstrap, migration, and feature work into separate branches unless they are inseparable.

Branch Protection And PR Flow

  • main is protected by the repository ruleset main-protect. Direct pushes to main are blocked even for repository admins.
  • Every change ships through a pull request. The required status checks are five CI job names: Format, Unit Tests, NPM Packages, Integration Tests, E2E Tests. The aggregate Test job is not required; it fans in every child, including the security and Darwin jobs the ruleset does not require.
  • A required check is a job name. Renaming or splitting one of those five stops that context from ever being reported, and GitHub holds the PR at expected forever — every check green, merge blocked. Keep a thin aggregate job under the original name with needs: [<new jobs>] and if: always(); without if: always() the job skips on child failure, which is neither green nor red. test/e2e/shard-contract.sh fails when the E2E Tests aggregate is missing.
  • Admin bypass mode is pull_request: the admin can self-merge a PR without approvals, but the PR itself is mandatory.
  • Default merge method is squash. The PR title becomes the squash commit subject and is what release-please parses, so write it as a Conventional Commit. Follow docs/pr-guideline.md for full conventions.
  • make install cannot run before the PR is merged into main. The full team-lead loop is: push branch → open PR → wait for CI → merge → git pull --ff-onlymake install.

Read the full file on GitHub · 131 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. yesterday Changed · +4 lines · +387 tokens per session efad1eaf1c19
  2. 7d ago First seen · 127 lines · 3,045 tokens per session scan A e022e06f9155

Subscribe to this mod's changes

projmux AGENTS.md is an instructions file published in the GitHub repository crevissepartners/projmux (11 stars, last pushed today), licensed MIT. It adds 3,432 tokens to every session, about $0.0172 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

github/spec-kit · 7,104 tokens