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/first-run-burstWrote 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/first-run-burst)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/first-run-burst"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/first-run-burst/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/first-run-burst"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/first-run-burst.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 | $0.00092 | $0.01439 |
| Opus 5 | $0.00046 | $0.00720 |
| Sonnet 5 | $0.00018 | $0.00288 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
first-run-burst 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.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
first-run-burst — the demo that decides whether the user stays
A new user finishes the setup, switches the team on, and watches. Ten minutes later they have seen one raw position appear. Nothing tells them apart a team pacing itself from an application that is broken — so they conclude it is broken, and they are not being unreasonable.
Your normal calibration (C-02: one worker, observe 30 min, add a rung) is the right rule at steady state, where a wrong guess costs a budget window. On the very first run it costs the user. This skill is the documented exception, and it applies to the first window only.
Trigger
[@assistente -> @capitano] [PROFILO-PRONTO]— the profile just became usable- at wake, when
python3 /app/shared/skills/first_run.py statusreportsphase: awaiting_profileorphase: burst
What success means here
Positions with a score on screen. Not positions found. A run that sources 50 offers and scores 3 of them (measured, 2026-07-26) has produced almost nothing the user can see — the shortlist is the product, the scraping is plumbing. Everything below follows from that one sentence.
The routine
1. Open the burst and read the roster.
python3 /app/shared/skills/first_run.py begin-burst
It returns the roster (how many Scout / Analista / Scorer), the
scout_cap_first_pass and the target_scored, all derived from the
subscription the user declared during setup. If it answers piano non dichiarato, the setup step is incomplete: tell the user in chat and stop —
do not guess a roster, an over-estimate burns their window on day one.
2. Spawn the whole roster, staggered by ~60 seconds.
Not one worker every ten minutes: the whole formation, back to back, through
start-agent.sh as always (C-03). This is the deliberate C-02 exception.
3. Do not wait for full queues to start the downstream.
Spawn the Analista as soon as one position exists, the Scorer as soon as one position is checked. The habit of "first collect, then evaluate" is what leaves the user staring at a pile of unscored rows.
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.
- 12d ago First seen · 118 lines · 92 tokens per session scan A de31d95784fa
first-run-burst is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,439 once invoked, about $0.0005 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.