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/k1low/tcmux/claude-mdgit clone --depth 1 https://github.com/k1LoW/tcmuxWrote 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/k1low/tcmux/claude-md)<a href="https://agentmods.dev/instructions/k1low/tcmux/claude-md"><img src="https://agentmods.dev/badge/instructions/k1low/tcmux/claude-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 5.1 | $0.00695 | $0.00695 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
tcmux CLAUDE.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 6d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Development Commands
# Run all tests with coverage
make test
# Run a single test
go test -v ./agent -run TestClaudeAgent_ParseStatus
# Build the binary
make build
# Install locally
make install
# Lint (requires golangci-lint and gostyle)
make lint
# Install dev dependencies
make depsdev
Architecture
tcmux is a CLI tool that displays coding agent instances (Claude Code, GitHub Copilot CLI) running in tmux windows/sessions along with their status.
Core Components
-
cmd/: CLI commands using cobra
root.go- Root command with--colorflaglsw.go-list-windows(alias:lsw) - Lists windows with coding agent statusls.go-list-sessions(alias:ls) - Lists sessions with coding agent stats
-
agent/: Coding agent detection and status parsing
agent.go-Detectorinterface andDetect()function for agent detectionclaude.go- Claude Code detection (pane title with✳prefix or Braille spinner, processclaudeornode)status_claude.go- Claude Code status parsingcopilot.go- Copilot CLI detection (processcopilot)status_copilot.go- Copilot CLI status parsingstatus.go- Common status utilities
-
tmux/: tmux interaction via shell commands
tmux.go- Wrapstmux list-panes,tmux list-sessions,tmux capture-pane
-
output/: Output formatting and colorization
format.go- Expands format strings with tmux variables and custom#{agent_status}variablecolor.go- Terminal color handling withtermenv
Data Flow
- CLI command parses user format string and extracts tmux variables
tmux.ListPanes()ortmux.ListSessions()fetches data from tmux- For each pane,
agent.Detect()checks if it's a coding agent (Claude Code or Copilot CLI) tmux.CapturePane()gets pane content, agent'sParseStatus()determines stateoutput.ExpandFormat()generates final output with colors
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.
- 6d ago First seen · 72 lines · 695 tokens per session scan A 4ce951f35d5b
tcmux CLAUDE.md is an instructions file published in the GitHub repository k1LoW/tcmux (41 stars, last pushed 6mo ago), licensed MIT. It adds 695 tokens to every session, about $0.0035 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 2026-08-30.
Other instructions, from other repositories
DevoxxGenieIDEAPlugin GEMINI.md
Gemini CLI instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven…
agent-rules child-process.instructions.md
Instructions for lirantal/agent-rules, covering system processes secure coding guidelines, your mission and spawning system processes.
skill.color-expert CLAUDE.md
Claude Code instructions for meodai/skill.color-expert, covering claude.md, project overview, architecture, no build/test/lint and editing guidelines.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.