chat-worker

chat-worker is a skill for Claude Code from leopu00/job-hunter-team. It costs 0 tokens per session (1,680 once invoked), scanned A, original, MIT.

A chat-handling procedure for a coding agent working inside the JHT game or desktop chat. It tells the agent how to recognize the user's message and send one short reply through the required command.

In plain words
What is it for?
It helps an agent answer messages such as progress questions from the JHT chat, then continue its earlier task.
Why use it?
It prevents replies from being sent to the wrong place or written in the wrong format. It also keeps chat responses brief because each reply uses part of the agent's work time.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps an agent answer messages such as progress questions from the JHT chat, then continue its earlier task.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/chat-worker"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/chat-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,680 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 $0.00000 $0.01680
Opus 5 $0.00000 $0.00840
Sonnet 5 $0.00000 $0.00336
Haiku 4.5 $0.00000 $0.00168

Measured 10d ago against content hash 578a5b18f4a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

chat-worker 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 10d 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/chat-worker/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chat-worker — the user can talk to you, and it must stay cheap

The user is not in a tmux session. They write from the game / desktop app, one-to-one with you. The app tags the message and drops it into your pane:

[@utente -> @scout-2] [CHAT] Come procede il giro delle board?
  • Same envelope as inter-agent traffic, but the [CHAT] type and the @utente author make it unambiguous: this is the person you work for.
  • There is no tmux session to answer into. jht-tmux-send UTENTE … returns exit 2. [CHAT]jht-send. Always.
  • Reply to the body, not to the envelope. The user did not type the prefix.
  • The delivery tool waits for your current turn to end before typing into your pane, so a [CHAT] never lands mid-thought. When you see one, your turn has just started: answer first, then resume.

How to answer

jht-send 'Sto girando le board EU: sei posizioni nuove stamattina, quattro remote.'

One call. No flags. That closes the turn and the bubble appears in the game.

⏱️ The cost rule — this is the point of this skill

Your reply is one full turn of your model, taken out of the same budget that pays for the work the user is waiting for. A chatty worker is a worker that scouts less, scores less, writes less. So:

  1. Answer from what you already have in context. No new query, no new fetch, no new scrape, no file to open "just to be precise". If you do not already know, say what you know and how you will find out — do not go and find out now.
  2. One to three sentences. Concrete: numbers, state, what you are on. The user is looking at a comic balloon, not a report.
  3. One reply per message, then back to work. Do not close with "anything else?" — an invitation costs another turn, and then another.
  4. Batch. If two or three [CHAT] lines piled up while you were mid-turn, answer them all in one jht-send.
  5. No --partial. The checkpoint flag exists for a coordinator running a long user-facing operation. If answering you properly would need a long operation, that is the signal that this question is not yours (see below) — not the signal to start one.
  6. Never poll. There is no inbox to check. The message is injected into your pane; if there is nothing in your pane, there is nothing to answer. A while true check loop would burn your whole window on "no messages".

Read the full file on GitHub · 128 lines

Files

What ships with it

6 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. 10d ago First seen · 128 lines · 0 tokens per session scan A 578a5b18f4a9

Subscribe to this mod's changes

chat-worker is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,680 tokens. 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.