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 user-reply-checkgit 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/user-reply-check)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/user-reply-check"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/user-reply-check/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/user-reply-check"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/user-reply-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.01485 |
| Opus 5 | $0.00040 | $0.00743 |
| Sonnet 5 | $0.00016 | $0.00297 |
| Haiku 4.5 | $0.00008 | $0.00148 |
Grade A, and why
user-reply-check 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
user-reply-check — pick up user replies sent via the web dashboard
The user can answer your notify-user messages from two places:
- Telegram — they reply on their phone; the
tg-bridgeinjects the message into your tmux as[@utente -> @<agente>] [TG] <body>. You see it inline. Nothing to do here. - Web dashboard — when
delivered_via='web'(Telegram was down/unconfigured), the user types the reply in the dashboard card. The text lands inpending_user_messages.user_reply. Telegram does NOT see it. This is where this skill kicks in.
Without user-reply-check, replies from the dashboard would sit silently in the DB forever.
When to use it
- ✅ At the top of every loop iteration (Capitano: once per tick; Mentor: once per session wake-up; Assistente: between user-input cycles).
- ✅ Right after running
notify-userif you posed akind=question— likely the user already replied if some time has passed. - ✅ When the user mentions "ti ho risposto sulla dashboard" but you didn't see anything via Telegram.
When NOT to use it
- ❌ For Telegram inbound —
tg-bridgehandles it; you see[TG] …directly. - ❌ As a polling loop with no work in between — it's a check, not a watcher. Each call is a cheap DB query, but you'll waste tokens reading "no replies" 100 times.
Usage
# Standard call at top of loop (marks all returned replies as seen)
jht-check-user-replies --agent <your_agent_id>
# Without consuming (debug / before you're sure you want to ack them)
jht-check-user-replies --agent <your_agent_id> --peek
# Structured output for piping into your reasoning
jht-check-user-replies --agent <your_agent_id> --json
<your_agent_id> must match the --agent you used in jht-notify-user. Each agent has its own queue — replies for the Capitano never appear for the Mentor.
Output
Empty output = nothing new for you. Process it as a silent no-op and continue your loop.
Non-empty output (human format):
[USER REPLY via WEB — id=42] Usa la versione breve del CV, grazie.
↳ in risposta a: "Per la candidatura gia' richiesta per Acme Senior FE, quale versione del CV preferisci?"
↳ kind=question created=2026-05-13 12:00:00 reply_at=2026-05-13 14:30:00
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.
- 9d ago First seen · 104 lines · 80 tokens per session scan A 8b072ca4cee6
user-reply-check 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 1,485 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.
Other skills, from other repositories
gws-drive
Google Drive: Manage files, folders, and shared drives.
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-gmail
Gmail: Send, read, and manage email.
gws-calendar-insert
Google Calendar: Create a new event.