decision-throttle

decision-throttle is a skill for Claude Code, Codex from leopu00/job-hunter-team. It costs 50 tokens per session (1,316 once invoked), scanned A, original, MIT.

A decision table that turns projected provider usage into an operating state and a throttle level, meaning how long agents should wait between operations.

In plain words
What is it for?
It is for selecting actions such as accelerating, maintaining pace, slowing down, or entering an emergency state based on usage projections.
Why use it?
It gives the monitoring agent consistent rules for responding to underuse, normal usage, warnings, and projected overuse.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit It is for selecting actions such as accelerating, maintaining pace, slowing down, or entering an emergency state based on usage projections.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leopu00/job-hunter-team/decision-throttle
Install

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.

Any agent
npx skills add leopu00/job-hunter-team --skill decision-throttle
Clone the repo
git clone --depth 1 https://github.com/leopu00/job-hunter-team

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for decision-throttle

README.md
[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/decision-throttle/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/decision-throttle)
Your own site
<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.

agentmods 80×15 button for decision-throttle

Your own site · 80×15
<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>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 85250023ea04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

agents/sentinella/_skills/decision-throttle/SKILL.md · 79 lines

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)

Read the full file on GitHub · 79 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 79 lines · 50 tokens per session scan A 85250023ea04

Subscribe to this mod's changes

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.