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/team-modesWrote 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/team-modes)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/team-modes"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/team-modes/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/team-modes"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/team-modes.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 | $0.00094 | $0.02720 |
| Opus 5 | $0.00047 | $0.01360 |
| Sonnet 5 | $0.00019 | $0.00544 |
| Haiku 4.5 | $0.00009 | $0.00272 |
Grade A, and why
team-modes 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
team-modes — what the current mode means, in thirty seconds
The team has one persistent mode at a time. It lives in
$JHT_HOME/profile/capitano-maintenance.json (historical filename — do NOT
expect a renamed file) under the key "mode", a closed enum of five
values. The hourly [MODALITÀ CORRENTE] banner carries the compact spec;
this skill is the full card. If the banner and your context disagree, the
file on disk wins — your context may have been wiped by a refresh.
| value | meaning |
|---|---|
search |
default: accumulate (scout → analysis → score) |
harvest |
stop sourcing, convert the best already-found positions into CVs |
care |
keep the found portfolio fresh: cadenced recheck, discard expired (C-18) |
calibration |
read the user's feedback and re-aim the search priority |
saving |
bare survival minimum, no autonomous enrichment |
- No file →
search. Legacy values:"normal"→ search,"maintenance"→ care (live installs still carry them — honor them, same mode). - File present but unreadable → mode
sconosciuto: treat it as an ACTIVE order (sourcing stays off), open the file yourself before deciding anything. - A value outside the enum is still an order from the user: report it, do not normalize it away.
Every mode declares four things — the same four the banner compresses: (1) which queues are active, (2) what is suspended, (3) where the budget goes, (4) when its work is DONE. Point 4 is the one that was missing historically: no mode ended by itself, and a team once sat 18 days in maintenance with nobody noticing. When the banner says the mode's work is exhausted, tell the user — never switch mode on your own, but silence is not allowed either.
The orders vocabulary (stop_search, discard_expired_rotating,
cv_min_score, pre_check_liveness_for_cv, plus hand-written keys) composes
with EVERY mode: an explicit key in orders always overrides the mode's
default. A live production VPS runs care with those orders active today.
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 · 184 lines · 94 tokens per session scan A 07729f9a2845
team-modes is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 2,720 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
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.
recipe-draft-email-from-doc
Read content from a Google Doc and use it as the body of a Gmail message.