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.
curl -O https://raw.githubusercontent.com/crevissepartners/projmux/main/AGENTS.mdgit clone --depth 1 https://github.com/crevissepartners/projmuxWrote 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/crevissepartners/projmux/agents-md)<a href="https://agentmods.dev/instructions/crevissepartners/projmux/agents-md"><img src="https://agentmods.dev/badge/instructions/crevissepartners/projmux/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/crevissepartners/projmux/agents-md"><img src="https://agentmods.dev/badge/instructions/crevissepartners/projmux/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03118 | $0.03118 |
| Opus 5.5 | $0.01247 | $0.01247 |
| Sonnet 5.5 | $0.00624 | $0.00624 |
| Haiku 4.5 | $0.00312 | $0.00312 |
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 12d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
Pull requests are accepted from maintainers only. Everyone else, please open an issue.
Commands
Run these in order for every change. ## Workflow explains the rules behind the order.
# start: confirm the checkout and its state
pwd
git status --short
# base check (on failure: rebase onto origin/main first)
git fetch origin main
git merge-base --is-ancestor origin/main HEAD
# Local checks
make fmt
make fix
make test
# publish: re-run the base check right before pushing
git fetch origin main
git merge-base --is-ancestor origin/main HEAD
git push -u origin <branch> # after a rebase: git push --force-with-lease
gh pr create --title '<type>(<scope>): <summary>' --body-file <body.md> # body: docs/pr-guideline.md
# CI checks on the same head: the five required checks (`Format`, `Unit Tests`, `NPM Packages`,
# `Integration Tests`, `E2E Tests`) and the aggregate `Test`. Integration and e2e are judged here, not run locally.
gh pr checks <num> --watch
# merge only when the Local checks passed and the CI checks are green on the same head
gh pr merge <num> --squash --delete-branch # primary checkout; add --auto to queue it
# from a linked worktree, merge without --delete-branch (it checks out `main`, which another worktree holds)
# and delete the remote branch separately
gh pr merge <num> --squash
git push origin --delete <branch>
# after merge only (never before the merge and pull)
git pull --ff-only
make install
Scope
projmuxis a standalone tmux session-management application.- Keep portable session-management behavior in
projmux. - Keep machine-local policy outside the application.
- This file is the shareable, tool-agnostic repo contract. Personal agent recipes, reverse-engineering notes, and machine-local operating memos belong in your own untracked notes, not this tracked file.
- Local-only agent overlays may live in an untracked
AGENTS.local.md.
Repo map
| Path | Purpose |
|---|---|
cmd/projmux |
Binary entrypoint; CLI wiring only. |
internal/app |
Command implementations and app wiring. |
internal/cli |
Canonical command catalog, help, output, and receipts. |
pkg/projmux |
Experimental v0 public Go SDK; instructions and resource reads, public core types and typed refusals. |
internal/services |
Transport-independent execution shared by CLI and SDK. |
internal/core |
Product rules and state that are testable without tmux. |
internal/config |
Config files and saved settings. |
internal/integrations |
Adapters: tmux, AI agents, hooks, metadata, session state. |
internal/integrations/processhost |
Owned provider process lifetime, supervisors, bounded streams, and control admission. |
internal/integrations/agents/codexappserver |
Codex JSON-RPC framing, handshake, sessions, and turns. |
internal/ui |
Native picker and rendering. |
internal/state |
Simple file-backed state helpers. |
internal/i18n, internal/theme |
Message catalog and locales; built-in palette and theme resolution. |
internal/aiprovider |
AI provider registry: IDs, names, binaries, and capability flags. |
internal/diagnostics |
Bounded operational event journal read by projmux diagnostics. |
internal/platformkeys |
Physical key-chord capture for native keybindings; macOS only, a stub elsewhere. |
internal/systemstatus |
Host CPU and memory sampling for the status bar. |
internal/version |
Release version string that release-please bumps. |
internal/testutil |
Test-only support packages; product code never imports them. |
internal/tools/gendocs |
Build-time generator for docs/cli.md (make docs). |
internal/tools/gennotices |
Build-time generator for THIRD_PARTY_NOTICES (make notices). |
test/ |
integration/, e2e/, and install/ suites, Docker images, fixtures, and workflow contract tests. |
scripts/ |
Development, CI, and security tooling only; no product logic. |
npm/ |
npm launcher and per-platform packages. |
docs/ |
User and contributor docs. |
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.
- 12d ago Changed · -8 lines · -751 tokens per session 569a4154b667
- 15d ago Changed · +101 tokens per session 2992cf907e72
- 16d ago Changed · +359 tokens per session e5ffd3eecd02
- 17d ago Changed · +2 lines · +45 tokens per session dc1d99e0c0a6
- 24d ago Changed · +10 lines · +517 tokens per session 9d4a5775c632
- 27d ago Changed · +6 lines · +124 tokens per session 8f1daec9c4c8
- 28d ago Changed · +2 lines · +102 tokens per session c9ccee42e4e6
- 1mo ago Changed · +1 lines · +115 tokens per session f14105545ff4
- 1mo ago Changed · +2 lines · +154 tokens per session c2212f2dab33
- 1mo ago First seen · 152 lines · 2,352 tokens per session scan A 9fc70fe6e1e9
projmux AGENTS.md is an instructions file published in the GitHub repository crevissepartners/projmux (11 stars, last pushed today), licensed MIT. It adds 3,118 tokens to every session, about $0.0125 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.