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.
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.
[](https://agentmods.dev/instructions/pimpstudios/claude-tmux-bridge/agents-md)<a href="https://agentmods.dev/instructions/pimpstudios/claude-tmux-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/pimpstudios/claude-tmux-bridge/agents-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 | $0.01002 | $0.01002 |
| Opus 5 | $0.00501 | $0.00501 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
claude-tmux-bridge 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 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.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex MCP — tmux Bridge
What This Is
This is an MCP server that connects Codex Desktop to an interactive Codex session running in a named tmux pane. It delivers prompts from Desktop to Code and returns the response — maintaining full conversation history and tool access between calls.
How to Use This Tool (for Codex Desktop)
This server exposes one tool: Codex.
When to use it
Use Codex whenever the user wants Codex to execute a task — writing code, editing files, running commands, working with git, or using any tools Codex has access to (MCP tools, bash, file system, etc.).
Required parameters
prompt— the full task description to send to CodexworkFolder— absolute path to the user's project directory (determines which tmux session to target)
Optional parameters
timeout— max seconds to wait for a response (default: 300)clearContext— send/clearbefore the prompt; wipes conversation history entirely. Fast (< 1s).compact— send/compactbefore the prompt; summarises history via the Codex API, keeping key context while freeing space. Slower (30–60s). Takes precedence overclearContextif both are set.
When to use clearContext
Use clearContext: true when:
- Starting a completely new feature, system, or unrelated task
- Beginning a fresh work session on a project you've worked on before
- Codex warns that the context window is getting large
- The previous task is fully done and the next task has no dependency on it
When to use compact
Use compact: true when:
- Context is growing large but the conversation history is still relevant
- You're mid-task and want to keep continuity without hitting context limits
- Codex's responses are getting slower or less accurate due to context size
How to write a good prompt for Codex
- Be explicit and step-by-step for complex tasks
- Include relevant file names, function names, or error messages
- Reference what was previously done if continuing a task
- Codex retains full conversation history — you don't need to re-explain the whole project each time, just what's new
- Never re-paste the full GDD or project context on every call — Code already has it
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.
- 5d ago First seen · 102 lines · 1,002 tokens per session scan A 5beb4b0259d7
claude-tmux-bridge AGENTS.md is an instructions file published in the GitHub repository PiMPStudios/claude-tmux-bridge (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,002 tokens to every session, about $0.0050 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 2026-09-01.
Other instructions, from other repositories
world-intel-mcp CLAUDE.md
Claude Code instructions for marc-shade/world-intel-mcp, covering claude.md, what this is, commands, install and run mcp server (stdio mode).
sui-mcp CLAUDE.md
Claude Code instructions for 0xfreak0/sui-mcp, covering sui-mcp, stack, architecture, which transport to use and archive fallback.
clawstash CLAUDE.md
Claude Code instructions for fo0/clawstash, covering claude.md -- project guide, session start -- read order, workflow triggers, output languages and performance / modes.
datadog-mcp CLAUDE.md
Claude Code instructions for dreamiurg/datadog-mcp, covering agent instructions, project, stack, commands and releases.
pubmed-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/pubmed-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool.
clawstash AGENTS.md
AGENTS.md instructions for fo0/clawstash, covering agents.md — agent guide and gitnexus — read-only analysis policy (non-negotiable).