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-agentWrote 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-agent)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/spawn-agent"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/spawn-agent.svg" alt="Measured on agentmods" 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 Prompt Injection · line 73 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00126 | $0.02564 |
| Opus 5 | $0.00063 | $0.01282 |
| Sonnet 5 | $0.00025 | $0.00513 |
| Haiku 4.5 | $0.00013 | $0.00256 |
Grade A, and why
spawn-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spawn-agent — bring an agent online
Two-phase contract: launch the CLI, then kick-off its loop. Skipping the kick-off leaves the agent at an empty prompt — the Captain thinks it is working, it is not.
Phase 1 — launch via start-agent.sh
bash /app/.launcher/start-agent.sh <role> [instance_number]
Examples:
bash /app/.launcher/start-agent.sh scout 2 # SCOUT-2
bash /app/.launcher/start-agent.sh analista 1 # ANALISTA-1
bash /app/.launcher/start-agent.sh critico # CRITICO (singleton, no number)
Instance number — roll the die (scalable workers, 2026-06-13). For scout / analista / scorer / scrittore, do NOT pick the number sequentially: the work always piled up on -1/-2 while -4 did almost nothing. Roll a free random number first, then pass it:
N=$(python3 /app/shared/skills/roll_worker_number.py scout) && \
bash /app/.launcher/start-agent.sh scout "$N"
roll_worker_number.py rolls a d6 excluding the numbers already in use (existing SCOUT-N sessions) → never a collision, and the workload spreads across instance numbers instead of always hitting -1. Applies to NEW spawns only; singletons (Critico / Sentinella / Dottore / Assistente / Mentor) keep no number, and the Dottore's session-refresh recreates the same number (it does not roll).
The launcher does, atomically:
- creates the tmux session with the canonical name (
SCOUT-2,ANALISTA-1, …) - sets
cwdto$JHT_HOME/agents/<role>[-N]/ - exports
JHT_HOME · JHT_DB · JHT_AGENT_DIR · PATH · JHT_USER_DIR · JHT_CONFIG - detects the active provider from
jht.config.json(claude / kimi / codex) - copies
agents/<role>/<role>.mdinto the workspace asCLAUDE.md/AGENTS.md - starts the CLI with the right flags for that provider + tier
- derives the initial stagger from the throttle rung and pre-arms the new worker's throttle
⚠️ NEVER spawn with
tmux new-session ... ; tmux send-keys "kimi ...". The CLI is not onPATHoutside the launcher's environment →command not found→ the session is just bash. The Captain'sjht-tmux-sendreturnsexit 0writing to that empty bash, the message is silently lost, and the team underperforms with no visible cause.
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.
- 8d ago First seen · 135 lines · 126 tokens per session scan A 8a1be4400735
spawn-agent is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 2,564 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
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
persona-event-coordinator
Plan and manage events — scheduling, invitations, and logistics.
persona-researcher
Organize research — manage references, notes, and collaboration.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
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.