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 decision-throttlegit 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/decision-throttle)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/decision-throttle"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/decision-throttle/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/decision-throttle"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/decision-throttle.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 | $0.00050 | $0.01316 |
| Opus 5 | $0.00025 | $0.00658 |
| Sonnet 5 | $0.00010 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
decision-throttle 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Tabella stati e throttle
Riferimento per decidere lo stato dal proj ricevuto e il livello throttle da imporre al Capitano.
Stati basati su proj
| Stato | Condizione proj |
Ordine al Capitano |
|---|---|---|
| CRITICO | > 100% |
EMERGENZA / RALLENTA forte |
| ATTENZIONE | 95-100% |
RALLENTA leggermente |
| STEADY (G-spot) | 90-95% per 3 tick consecutivi |
MANTIENI |
| SOTTOUTILIZZO vicino | 70-90% per 2+ tick stagnanti |
PUSH G-SPOT |
| SOTTOUTILIZZO grave | < 70% per 2+ tick + vel<ideale×0.7 |
SCALA UP |
| OK | qualunque, primo tick | ACCELERARE |
Tabella throttle — FLOOR 5min, ladder a gradini (2026-06-21)
Niente throttle sotto i 5min. Lo storico mostra che i throttle <5min (78-86% degli
eventi su Kimi/Codex) erano correzioni marginali applicate a raffica = chatter. Ora il
throttle è 0 (off) oppure ≥5min agganciato alla ladder {5,10,15,20,25,30,40,50,60}min
(floor 5min, cap 1h). jht-throttle/throttle-config agganciano da soli qualunque valore
(es. 120s → 300s), quindi ordina pure in minuti "puliti".
rapporto = velocità_smussata / velocità_ideale
| rapporto | sleep tra operazioni | semantica |
|---|---|---|
| ≤ 1.0 | 0s | sotto target, full speed |
| 1.0 – 1.5 | 5 min | leggermente sopra |
| 1.5 – 2.0 | 10 min | moderato |
| 2.0 – 3.0 | 20 min | pesante |
| > 3.0 | 30 min (sali fino a 60) | near-freeze, emergenza |
Se velocità_ideale ≤ 0 (proj > SAFE_TARGET 95%) → sali la ladder (30-60min).
⚠️ Per CONSUMARE di più NON si scende sotto i 5min. Il throttle pace il SINGOLO agente; la PORTATA del team la regola il numero di agenti. Se al floor di 5min il team sotto-utilizza il budget, la leva è il PARALLELISMO: ordina SCALA UP → il Capitano spawna più agenti (più agenti in simultanea = più throughput a parità di floor). Mai inseguire il budget abbassando il throttle sotto i 5min: non esiste più.
Bypass emergenza (manda subito, ignora cooldown)
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 · 79 lines · 50 tokens per session scan A 85250023ea04
decision-throttle is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,316 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.