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/rate-budgetWrote 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/rate-budget)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/rate-budget"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/rate-budget/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/rate-budget"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/rate-budget.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 | $0.00077 | $0.01044 |
| Opus 5 | $0.00039 | $0.00522 |
| Sonnet 5 | $0.00015 | $0.00209 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
rate-budget 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 11d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rate-budget — rate-limit budget snapshot
The monitoring bridge (.launcher/sentinel-bridge.py) polls the active provider every 1–10 min (dynamic — more often under pressure) and writes each sample to /jht_home/logs/sentinel-data.jsonl. This skill reads only the latest sample that's already been written — no extra provider call.
Primary: the SAME tick the Sentinella gets
Run with no argument (or tick):
python3 /app/shared/skills/rate_budget.py tick
You get the exact same message the bridge sends to the Sentinella — the
bridge renders it every tick into logs/last-tick.txt and this reads it back
(zero provider calls, zero divergence). Three airy sections + a bridge hint:
── BRIDGE TICK · 12:45:03 · codex · ON ──
⏱ FINESTRA 5H
usage 51% target 92% → chiusura 2026-06-30 16:45 CEST (tra 4h 00m)
velocità 11.5 %/h · target 10.2 %/h [+12% sopra]
→ ATTENZIONE · proj 97%
📅 OGGI (budget giornaliero)
consumato 4.2% / budget 9.0% (cap 14.0%) ✅
velocità 1.1 %/h · target 0.8 %/h [+38% sopra]
📆 SETTIMANA
usato 16% · rimane 84% · reset 2026-07-07 05:00 CEST (tra 6g 16h)
velocità 3.4 %/h · sostenibile 1.1 %/h [+209% sopra] ratio 3.09×
SOPRA-PACE · debito +6pp · lockout ~58h
🧭 CONSIGLIO BRIDGE
Sopra-pace: throttle-to-pace + STOP nuovi spawn finché rientri. ...
src=bridge.
Read it like this — la velocità è IL segnale (proj è solo INFO volatile):
- ogni sezione ha velocità attuale (usage consumato / tempo trascorso) vs target (quanto manca / tempo che resta), stessa unità %/h. Lo scarto
[+X%/-X%]è il giudizio. - 5h = il soffitto del provider (lock a 100% prima del reset). Oggi = il budget del giorno. Settimana = budget + debito.
- velocità sotto target su tutte → c'è margine → spawn graduale (C-02). Velocità sopra target → frena / non spawnare. Segui il
🧭 CONSIGLIO, ma decidi tu (C-01).
If output is NO_DATA: the bridge hasn't written a tick yet (not started, or off-hours). Wait 1–2 min and retry.
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.
- 11d ago First seen · 69 lines · 77 tokens per session scan A c0c2231c0fb5
rate-budget is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 1,044 once invoked, about $0.0004 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
gws-modelarmor
Google Model Armor: Filter user-generated content for safety.
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-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.