tmux-send

tmux-send is a skill for Claude Code from leopu00/job-hunter-team. It costs 80 tokens per session (1,672 once invoked), scanned A, original, MIT.

A safe way to send a message to another agent running in a terminal multiplexer, which keeps terminal programs running in separate sessions.

In plain words
What is it for?
It is for reliable communication between named agents such as workers, reviewers, and coordinators.
Why use it?
It confirms that the message was submitted, avoiding a common problem where the text appears in the other agent's input but is never sent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Good fit It is for reliable communication between named agents such as workers, reviewers, and coordinators.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leopu00/job-hunter-team/tmux-send
Install

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.

Any agent
npx skills add leopu00/job-hunter-team --skill tmux-send
Clone the repo
git clone --depth 1 https://github.com/leopu00/job-hunter-team

Made for: Claude Code.

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 tmux-send

README.md
[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/tmux-send/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/tmux-send)
Your own site
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/tmux-send"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/tmux-send/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.

agentmods 80×15 button for tmux-send

Your own site · 80×15
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/tmux-send"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/tmux-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,672 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00080 $0.01672
Opus 5 $0.00040 $0.00836
Sonnet 5 $0.00016 $0.00334
Haiku 4.5 $0.00008 $0.00167

Measured 9d ago against content hash 6602689f521e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tmux-send 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 9d 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.

agents/_skills/tmux-send/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tmux-send — inter-agent messaging

Shell wrapper colocated at /app/agents/_skills/tmux-send/jht-tmux-send (also on PATH via /usr/local/bin symlink, populated at image build).

Why it exists

Ink-based TUIs (Codex, Kimi Code) drop the Enter if it arrives in the same tmux send-keys call as the text body. Text is sent character-by-character; Ink must finish rendering before accepting another keystroke. If you call tmux send-keys "msg" Enter, the message stays in the peer's input buffer without being submitted → silent inter-agent deadlock.

The wrapper handles it atomically: it types the text, re-reads the pane to confirm the text landed, sends Enter, then re-reads the pane again to confirm the turn actually started. Delivery is not "having typed" — it is "having seen the turn start".

⚠️ There is a second, nastier state: the TUI accepts the text and ignores the Enter, leaving the line hanging in the composer while the agent sits idle for hours. Seen 4 times in 3 days on one box, Captain included, when a message arrives while the peer is closing a long turn. The wrapper now retries the Enter and, if the turn still doesn't start, returns 5 instead of falsely reporting success.

Usage

jht-tmux-send <SESSION> "<message>"

Examples (V5)

# Captain → Scout (INFO, generic operational message)
jht-tmux-send SCOUT-1 "[@capitano -> @scout-1] [INFO] Start the main loop. Begin from CIRCLE 1 (Remote EU); ping after each batch of 3-5 positions."

# Captain → Writer (URG, real-time order)
jht-tmux-send SCRITTORE-1 "[@capitano -> @scrittore-1] [URG] FREEZE — finish the current Critic round, then sleep until throttle returns to T0/T1."

# Analyst → Scout (FEEDBACK, rejection-pattern coaching)
jht-tmux-send SCOUT-2 "[@analista-1 -> @scout-2] [FEEDBACK] [SENIORITY] 4 of last 5 inserts from greenhouse.io require senior+ — switch source or query for the next batch."

# Sentinel → Captain (URG, state change)
jht-tmux-send CAPITANO "[@sentinella -> @capitano] [URG] Usage 94%, projection 102% — recommend throttle T2 + freeze Writers."

# Writer → Captain (REPORT, final result)
jht-tmux-send CAPITANO "[@scrittore-1 -> @capitano] [REPORT] Position 42 — verdict PASS, score 7.5/10. PDF: /jht_user/.../CV.pdf"

# Worker → Captain (ACK, confirming URG)
jht-tmux-send CAPITANO "[@scrittore-1 -> @capitano] [ACK] freeze applied, sleeping."

Read the full file on GitHub · 99 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 99 lines · 80 tokens per session scan A 6602689f521e

Subscribe to this mod's changes

tmux-send is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 1,672 once invoked, about $0.0004 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 2026-09-03.