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 skills add leopu00/job-hunter-team --skill chat-webgit clone --depth 1 https://github.com/leopu00/job-hunter-teamWrote 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/skills/leopu00/job-hunter-team/chat-web)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/chat-web"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/chat-web/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.
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/chat-web"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/chat-web.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 60 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00112 | $0.02107 |
| Opus 5 | $0.00056 | $0.01053 |
| Sonnet 5 | $0.00022 | $0.00421 |
| Haiku 4.5 | $0.00011 | $0.00211 |
Grade A, and why
chat-web 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chat-web — user ↔ Captain protocol
The user does not sit in a tmux session. They write from the web UI. The frontend tags the message and drops it into your tmux pane. To reply, you write a single JSON line into $JHT_AGENT_DIR/chat.jsonl; the frontend tails that file and renders bubbles in the chat panel.
You don't write the JSON. The wrapper jht-send does it for you, with timestamp + done flag + post-write validation. Use it. Always.
How to recognize an incoming [CHAT]
[@utente -> @capitano] [CHAT] <whatever the user typed>
- The envelope is identical to inter-agent messages (same
[@from -> @to]shape) but the[CHAT]type and the@utenteauthor make it unambiguous. - The user is a human, the profile owner — not an agent. There is no
tmux send-keysyou can use to reply: their session does not exist. - Reply to the body, not to the envelope. The user did not type the prefix; the frontend added it.
⚠️ Common failure mode the first time you see this: you read the prefix and think "let me reply via
jht-tmux-sendto the user".jht-tmux-send UTENTE ...returnsexit 2(no such session). Do not start debugging — just remember that[CHAT]⇒jht-send. Always.
⚠️ The user is NON-TECHNICAL — no terminal, no CLI, no slash commands
A [CHAT] message comes from the desktop app (or Telegram). The user does
not have a terminal, the Claude Code CLI, /mcp, slash commands, or file
access. They are not a developer. NEVER tell them to:
- run
/mcp,/config, or any slash command, - open a terminal / run a CLI command / edit a file / "authorize a tool",
- do anything you could do yourself.
Telling a desktop user "type /mcp in the terminal" is a dead end — they can't.
If a task needs a capability you don't have wired up, solve it yourself with
code instead of bouncing the work back to the user. You are the team; the user
is the client. Figure it out.
Example: sending an email — you do NOT need an MCP/Gmail tool
The team already has email credentials at
$JHT_HOME/credentials/email_monitor.json (a Gmail app-password — valid for SMTP
too). Write a tiny Python script and send it:
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.
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.
- 10d ago First seen · 141 lines · 112 tokens per session scan A aa4197a69c36
chat-web is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 2,107 once invoked, about $0.0006 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 skills, from other repositories
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
persona-researcher
Organize research — manage references, notes, and collaboration.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
recipe-draft-email-from-doc
Read content from a Google Doc and use it as the body of a Gmail message.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.