Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/spawn-doctorWrote 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/spawn-doctor)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/spawn-doctor"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/spawn-doctor/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/spawn-doctor"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/spawn-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium Agent Snooping · line 115 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00109 | $0.01602 |
| Opus 5 | $0.00055 | $0.00801 |
| Sonnet 5 | $0.00022 | $0.00320 |
| Haiku 4.5 | $0.00011 | $0.00160 |
Grade A, and why
spawn-doctor 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 11d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spawn-doctor — chiamata di emergenza al Dottore
Perché esiste
Il doctor-watchdog spawna automaticamente un DOTTORE ogni 2 ore
(cadenza scelta 2026-05-18 per ridurre token waste: 12 spawn/day
invece di 48). Tra uno spawn e il successivo la sessione tmux
DOTTORE esiste ma è "bash residua" (il Dottore precedente si è
auto-distrutto a fine giro). Mandare un [URG] o [HEALTH] a quella
sessione è inutile: il messaggio finisce nella bash e nessuno lo
legge.
Caso classico (post-mortem 2026-05-18-capitano-zombie-night):
l'Assistente ha mandato 2 URG al Dottore alle 06:08/06:09 perché
l'utente l'aveva chiesto, ma il Dottore precedente si era
auto-distrutto alle 05:48 → 2 URG persi nel vuoto, Capitano è rimasto
zombie altri ~20 min finché l'Assistente non ha capito di dover
agire direttamente.
Questa skill chiude il loop: invece di "parlare a un Dottore morto", ne spawno uno nuovo subito.
Chi può usarla
I 4 agenti coordinatori long-lived:
- 👨✈️ Capitano — quando rileva worker zombie e vuole un secondo paio di occhi prima di respawnare lui stesso.
- 💬 Assistente — quando l'utente chiede "fai partire il dottore" o "controlla il team" via Telegram/chat.
- 🧙♂️ Mentor — quando in un digest settimanale rileva pattern anomali e vuole una verifica salute infrastruttura.
- 💂 Sentinella — quando un agente smette di consumare token inaspettatamente in piena finestra produttiva.
Gli altri agenti (Scout, Analista, Scorer, Scrittore, Critico) NON
hanno questa skill: se vedono un problema, lo riportano al Capitano
via [REPORT] e lasciano a lui la decisione.
Come usarla
# Spawn one-shot. Lo script è idempotente: killa ogni DOTTORE* esistente
# prima di crearne uno nuovo, quindi puoi chiamarlo senza paura di
# duplicati.
bash /app/.launcher/spawn-doctor.sh
Output atteso:
[spawn-doctor] killing old session: DOTTORE (se presente)
[spawn-doctor] DOTTORE avviato — workdir=/jht_home/agents/dottore — round=YYYYMMDDTHHMMSSZ-spawn
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.
- 11d ago First seen · 119 lines · 109 tokens per session scan A b6c2cd889e1a
spawn-doctor is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,602 once invoked, about $0.0005 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
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
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.