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/throttle-setWrote 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/throttle-set)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/throttle-set"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/throttle-set/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/throttle-set"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/throttle-set.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 | $0.00126 | $0.00962 |
| Opus 5 | $0.00063 | $0.00481 |
| Sonnet 5 | $0.00025 | $0.00192 |
| Haiku 4.5 | $0.00013 | $0.00096 |
Grade A, and why
throttle-set 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 10d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
throttle-set — govern the rhythms without touching the agents
throttle-set <agent> <seconds> # one agent
throttle-set scout-1=660 analista-1=300 # several, one atomic write
throttle-set --dump # the EFFECTIVE values right now
throttle-set --get <agent> # the effective value of one
throttle-set --reset # drop every override
Why you never send a number over tmux
The throttle engine reads the config at the moment it arms each timer. So:
- a value you change here bites on that agent's next cycle, by itself;
- the cycle currently running is untouched — its deadline was already computed, and moving it would be a surprise nobody asked for;
- workers never see a number and never learn how long they wait. They call
throttle <their-name>and stop. The duration is yours alone.
That is the whole reason this exists: five tmux messages carrying a number are five chances to race an agent that is mid-pause. One atomic write is none.
What you get back is the EFFECTIVE value, not what you asked for
Two automatic corrections apply on read, so the number an agent actually serves can differ from the one you typed:
- Worker floor, 5 min. Workers (Scout/Analyst/Scorer/Writer/Critic) are never
below 300s,
0included. It comes from a measured incident — one Scout with no pause burned ~308kT for 3 positions of dirty data. The interactive core (Captain/Sentinel/Assistant/Mentor) has no floor: it must stay responsive for the user's chat, so0stays0there. - Coprime ladder. Every value > 0 snaps to a rung in prime minutes (1, 2, 3, 5, 7, 11, 13, 17, 23, 31, 41, 53, 60). Rungs that were multiples of 5 resynchronised workers by construction: 5+10 collided every 10 minutes. Coprime rungs make collisions rare instead of periodic.
So throttle-set scout-1 120 reads back as 300. That is not the tool ignoring
you — it is the value the agent will serve, and it is what --dump shows.
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.
- 10d ago First seen · 78 lines · 126 tokens per session scan A 1ffa8774d52b
throttle-set is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It adds 126 tokens to every session and 962 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
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-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.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.