claude-code-tmux AGENTS.md

claude-code-tmux AGENTS.md is an instructions file for Claude Code, Codex, OpenCode from Mahir-Isikli/claude-code-tmux. It costs 1,520 tokens per session, scanned C, original, MIT.

Repository instructions for claude-code-tmux, a package that lets people and agents control interactive Claude Code sessions through tmux, a terminal session manager. It documents its command-line, tool, and provider integrations.

In plain words
What is it for?
Use them when developing or operating the ccmux command, its integration tools, Claude Code provider modes, session hooks, or tmux-based automation.
Why use it?
They explain supported releases, session behaviour, and fixes needed to start sessions, send prompts, capture output, and handle completion results reliably.

Instructions file for Claude CodeCodexOpenCode

Written for Claude Code and Codex and OpenCode: PostToolUse hook event, but also the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/mahirisikli/Git/Personal/claude-code-tmux.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, 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 claude-code-tmux AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mahir-isikli/claude-code-tmux/agents-md.svg)](https://agentmods.dev/instructions/mahir-isikli/claude-code-tmux/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mahir-isikli/claude-code-tmux/agents-md"><img src="https://agentmods.dev/badge/instructions/mahir-isikli/claude-code-tmux/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,520 This file is loaded in full into every session.
When invoked 1,520 The same file — it is already loaded in full.
Security scan C 1 finding. 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 5.1 $0.01520 $0.01520
Opus 5 $0.00760 $0.00760
Sonnet 5 $0.00304 $0.00304
Haiku 4.5 $0.00152 $0.00152

Measured 5d ago against content hash e3b839c7a8e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

claude-code-tmux AGENTS.md scanned grade C 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 5d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /tmp/ccmux-provider-smoke
AGENTS.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claude-code-tmux agent notes

What this repo is

claude-code-tmux provides durable tmux control for interactive Claude Code sessions.

It ships three integration surfaces:

  1. ccmux CLI for humans and agents.
  2. Pi extension tools: ccmux_start, ccmux_send, ccmux_steer, ccmux_status, ccmux_capture.
  3. Native Pi provider: claude-code-tmux/opus and claude-code-tmux/sonnet.

The package is published on npm and GitHub:

  • npm: claude-code-tmux
  • GitHub: https://github.com/Mahir-Isikli/claude-code-tmux

Current working release

As of the native Pi tool bridge work, the working npm release is 0.5.0.

Important fixes in 0.2.1:

  • Auto-detect and accept Claude Code workspace trust prompts in provider mode.
  • Wait for Claude Code to be ready before sending the first provider prompt.
  • Verify the pasted job id is visible in the tmux pane before submitting.
  • Retry paste if tmux drops it.
  • Submit with C-m instead of literal Enter.
  • Provider mode requires a done JSON with final_response and returns that to Pi.

Important additions in 0.3.0:

  • Generated Claude Code hook settings per ccmux session.
  • bin/ccmux-hook.mjs command hook recorder.
  • Hook events stored under ~/.pi/ccmux/events/<job-id>.jsonl.
  • ccmux events --job <job-id> and ccmux events --session <name> for inspection.
  • Provider mode starts Claude Code with hooks enabled.
  • Provider streams hook lifecycle/tool progress as thinking/progress deltas while preserving the final response text.
  • Provider matrix script under scripts/provider-matrix.mjs.

Important additions in 0.4.0:

  • ccmux_replay_tool_result shadow replay tool.
  • Claude Code PostToolUse and PostToolUseFailure events are replayed into Pi as tool calls/results without re-running the underlying operation.
  • Matrix asserts PiReplayToolResult events.

Important additions in 0.5.0:

  • bin/ccmux-pi-tool.mjs bridge command for Claude Code to request native Pi tools.
  • Provider prompt includes a pi_native_tool_bridge command pattern with available Pi tools.
  • Provider intercepts pending Pi tool requests and emits the requested native Pi tool call.
  • Provider writes the real Pi tool result back for the blocking Claude Code bridge command.
  • Matrix asserts PiNativeToolRequest and PiNativeToolResult events.

Read the full file on GitHub · 174 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. 5d ago First seen · 174 lines · 1,520 tokens per session scan C e3b839c7a8e5

Subscribe to this mod's changes

claude-code-tmux AGENTS.md is an instructions file published in the GitHub repository Mahir-Isikli/claude-code-tmux (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,520 tokens to every session, about $0.0076 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

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

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

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 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