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/liveness-checkWrote 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/liveness-check)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/liveness-check"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/liveness-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/liveness-check"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/liveness-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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.
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 | $0.00122 | $0.02529 |
| Opus 5 | $0.00061 | $0.01264 |
| Sonnet 5 | $0.00024 | $0.00506 |
| Haiku 4.5 | $0.00012 | $0.00253 |
Grade A, and why
liveness-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 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
liveness-check — keep the team honest
A tmux session can survive its CLI. When the Codex / Kimi TUI crashes, tmux falls back to a bare bash prompt; messages keep being written into it (exit 0 from jht-tmux-send), nobody reads them, the agent is a zombie. This skill detects the state and recovers.
When to run a check
- 👨⚕️ Routine round — every Dottore wake-up (~30 min) walks every team session in sequence (see
agents/dottore/dottore.mdfor the full one-shot lifecycle). - 🚨 Captain handoff — when the Captain reports an agent silent > 10 min while it should be working (no Scout REPORT, no Writer ACK to the Critic).
- 🔁 Post-URG — 10-30s after a Captain
[URG]/[MSG]to confirm ACK + the CLI is still alive. - ⚖️ Pre-scaling — before a spawn/kill that depends on an existing agent's state (do not spawn the Analyst if the Scout it relies on is dead).
Priority order — user-facing FIRST
Before any walking, sort targets so the user-facing long-lived agents get checked first. They're at the top of the chain — if they die, nobody respawns them (the Captain spawns workers, not himself / the Assistant / the Mentor / the Sentinel). The post-mortem of the 2026-05-18 zombie night had 6-8h of dead Capitano because Dottori walked workers first, never reached the Capitano, and self-destructed.
PRIORITY 1 (always check first):
ASSISTENTE, CAPITANO, MENTOR, SENTINELLA
PRIORITY 2 (workers, the Captain can respawn them):
SCOUT-N, SCRITTORE-N, CRITICO-S*, ANALISTA-N, SCORER-N
If you only have 10 min budget for the round, always finish PRIORITY 1 before touching PRIORITY 2. A worker dead 30 min is recoverable; a Capitano dead 30 min means the whole pipeline is silent.
Step 0 — pane_current_command (cheap pre-check)
Before the capture-pane, do the cheap check:
cmd=$(tmux list-panes -t <SESSION> -F '#{pane_current_command}' | head -1)
If $cmd is not Kimi / kimi / claude / codex / node / python*
→ the LLM CLI is already dead, the pane is bare bash residua.
Skip the ping (it'd be lost into the bash and jht-tmux-send would
return exit 0 deceivingly), go directly to Step 3 RESPAWN.
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 · 156 lines · 122 tokens per session scan A 0025ff4c3c99
liveness-check is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 122 tokens to every session and 2,529 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-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
persona-researcher
Organize research — manage references, notes, and collaboration.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.