throttle-distribution

throttle-distribution is a skill for Claude Code from leopu00/job-hunter-team. It costs 0 tokens per session (5,039 once invoked), scanned A, original, MIT.

A procedure for distributing a team-wide slowdown across individual research roles. It converts one pacing signal into separate throttle values, where a throttle controls how quickly an agent works.

In plain words
What is it for?
Use it after a pacing warning to decide which agents should slow down and write their individual values to throttle.json.
Why use it?
It prevents every agent from slowing by the same amount when their workloads and contributions differ.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is decidi tu e applica: python3 /app/shared/skills/throttle-config.py bulk-set <a1>=<R> <a2>=<R>.

Good fit Use it after a pacing warning to decide which agents should slow down and write their individual values to throttle.json.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/leopu00/job-hunter-team
agentmods
npx agentmods add skills/leopu00/job-hunter-team/throttle-distribution

Made for: Claude Code.

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 throttle-distribution

README.md
[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/throttle-distribution/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/throttle-distribution)
Your own site
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/throttle-distribution"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/throttle-distribution/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 throttle-distribution

Your own site · 80×15
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/throttle-distribution"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/throttle-distribution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,039 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 warn 7 Sept 2026
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 analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 $0.00000 $0.05039
Opus 5 $0.00000 $0.02520
Sonnet 5 $0.00000 $0.01008
Haiku 4.5 $0.00000 $0.00504

Measured 12d ago against content hash 4cbb1a808157, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

throttle-distribution 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 12d 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/_skills/throttle-distribution/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

throttle-distribution — who slows down, and by how much

Every pacing signal you get is one number for the whole team: "35% too fast", "Throttle: 2", "advised 780s". The actuator is not one number — it is one value per agent in throttle.json, and you are the only one who writes it. No script moves the worker throttle on its own.

So the job this skill does is the conversion, and it has exactly one hard rule: a team-level number does not mean everyone gets the same value. One Scout can be 52% of the burn while an idle Writer is 2%; the Analista and the Scorer are the two roles that turn a backlog into the only thing the user actually sees — a position with a score. Levelling spends your brake where there is nothing to gain and takes throughput where it costs the most.

When to open this skill

Trigger Where it comes from Go to
[PACE-GUARD] … NON APPLICATO in your pane the bridge: it checks consumption against the window curve at every usage sample, and writes to you only when there is something to act on §1
[SENTINELLA] [URG] RALLENTARE — Throttle: N, or any pacing signal she forwards she receives the 15-min [BRIDGE PACING] tick (it lands in her pane, not yours), reads it, and decides whether it is worth waking you §3 — the "how much" is decided, the split is not. bridge-pacing decodes her numbers
[HEARTBEAT] mentioning weekly/burn, or your own rate-budget / agent-speed-table pull you, on your own initiative §2

⚠️ You are not pinged every 15 minutes, and you should not wait to be. Being kept quiet is deliberate: if every bridge in the office reported to you directly, you would spend the budget reading instead of deciding, and you would burn it while the user is asleep. The 15-min tick goes to the Sentinella, who filters and only then disturbs you. So drive on the conditions you observe — do not sit waiting for a tick that is not addressed to you. If a pacing line does reach you directly it is either a [PACE-GUARD] or an escalation saying the Sentinella has gone unreceptive (that is a liveness problem, not a pacing verdict — agent-emergency).

Read the full file on GitHub · 248 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. 12d ago First seen · 248 lines · 0 tokens per session scan A 4cbb1a808157

Subscribe to this mod's changes

throttle-distribution is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,039 tokens. 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.