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/emergency-handlingWrote 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/emergency-handling)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/emergency-handling"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/emergency-handling/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/emergency-handling"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/emergency-handling.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 | $0.00056 | $0.01281 |
| Opus 5 | $0.00028 | $0.00641 |
| Sonnet 5 | $0.00011 | $0.00256 |
| Haiku 4.5 | $0.00006 | $0.00128 |
Grade A, and why
emergency-handling 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Gestione emergenze e cascata FATAL
🚨 Bypass cooldown emergenza (manda subito)
Una di queste condizioni → manda ordine immediato senza aspettare cooldown:
proj > 200%(catastrophic) andreset_edge_guard != truevelocità_smussata > velocità_ideale × 5(esplosione)usage ≥ 90%assoluto (limite hard)
In questi casi, PRIMA della notifica esegui freeze_team.py:
python3 /app/shared/skills/freeze_team.py
Manda Esc x2 a tutti gli operativi (esclude CAPITANO/ASSISTENTE/SENTINELLA/SENTINELLA-WORKER). Il consumo si ferma anche se il messaggio al Capitano si perde.
Imposta freeze_active = True.
Reset-edge guard (last 30 minutes)
When the tick has reset_edge_guard=true, projection is diagnostic only: do
not freeze, throttle, kill, or update emergency_proj_history because of
proj, including persistent proj > 150%. Keep suggested_throttle_s=0.
Independent hard signals (usage >= 90%, bridge FATAL) remain active.
📊 Trigger during the emergency zone (proj > 100%, guard inactive)
Mantieni emergency_proj_history (ultimi 5) e emergency_proj_min. Tre trigger:
RECOVERY TRACKING (info ogni 3 tick)
SE recovery_tracking_cooldown == 0 AND len(history) >= 3:
delta_3 = history[-3] - history[-1]
SE delta_3 > 0: manda RECOVERY TRACKING (calo)
SE delta_3 ≈ 0: → vedi STAGNAZIONE
SE delta_3 < -5: → vedi PEGGIORAMENTO
recovery_tracking_cooldown = 3
STAGNAZIONE CRITICA
SE len(history) >= 5 AND proj > 150% AND (max(history) - min(history)) < 10:
manda STAGNAZIONE CRITICA → "kill altri agenti, throttle non basta"
cooldown 5 tick prima di rimandarla
PEGGIORAMENTO POST-FREEZE
SE proj > emergency_proj_min + 10:
manda PEGGIORAMENTO POST-FREEZE → "secondo freeze + kill totale"
no cooldown: scatta subito
🛡️ Cascata FATAL (bridge totalmente cieco)
Quando il bridge non riesce a leggere usage e ricevi [BRIDGE FAILURE]:
L1 — fetch HTTP rapido (vedi skill `check-usage-http`)
• OK → continua normalmente
• FAIL → ↓
L2 — TUI worker manuale (vedi skill `check-usage-tui`)
• OK → continua normalmente
• FAIL → ↓
L3 — FATAL: niente dato dal bridge per N cicli consecutivi
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 · 122 lines · 56 tokens per session scan A 8374dcbacaed
emergency-handling is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,281 once invoked, about $0.0003 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
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-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.
recipe-draft-email-from-doc
Read content from a Google Doc and use it as the body of a Gmail message.