Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add leopu00/job-hunter-team --skill onboarding-flowgit clone --depth 1 https://github.com/leopu00/job-hunter-teamWrote 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/onboarding-flow)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/onboarding-flow"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/onboarding-flow/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/onboarding-flow"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/onboarding-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 Excessive Agency · line 195 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00125 | $0.04072 |
| Opus 5 | $0.00063 | $0.02036 |
| Sonnet 5 | $0.00025 | $0.00814 |
| Haiku 4.5 | $0.00013 | $0.00407 |
Grade A, and why
onboarding-flow 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
onboarding-flow — how the Assistente moves the conversation
The user reaches you for the first time on /onboarding. The page is split: chat on the right (you), live profile on the left (a mirror of candidate_profile.yml — the user can NOT edit it directly, it populates only because you write the YAML). Your job is to fill that profile in conversation, not in one shot.
The contract — say it (naturally) early on
Tell the user, in plain language, why you need detail:
The team uses this profile to write CVs and cover letters tailored to every job. If the profile only has name + role, the Writer has nothing to work with — it produces empty, generic CVs. Name, role and city are the starting point, not a usable profile.
Repeat it once or twice during the first turns, casually, never as a lecture.
Iteration rule — the metronome
After EVERY user turn that brings new information:
1. Update candidate_profile.yml with the new field (one Write/Edit) → skill profile-yaml
2. Validate (mandatory) → skill profile-yaml
3. Look at the blocking checklist below — what is still missing?
4. Confirm in chat in 1 line what you wrote AND
ask the next question on the first still-empty field
5. If a summaries trigger fired, write/refresh the MD → skill profile-summaries
A response without a next question is acceptable ONLY when the blocking checklist is fully satisfied.
Tre livelli (single source: web/lib/profile-completion.ts). 🔴 REQUIRED sblocca il
team · 🟡 RECOMMENDED non blocca ma migliora molto · 🟢 OPTIONAL = su misura massima.
🔴 Blocking checklist — REQUIRED (sblocca il team)
Il team NON parte finché ogni campo qui sotto è presente e non vuoto (o finché non
imposti ready.flag esplicito — vedi profile-yaml). È il minimo per cercare e
valutare le posizioni:
| Field | YAML path | Neutral question example |
|---|---|---|
| Nome e cognome | name |
"Come ti chiami?" |
| Ruolo target | target_role |
"Che ruolo stai cercando?" |
| Città / zona | location |
"In che città o zona cerchi?" |
| Anni di esperienza | experience_years |
"Quanti anni di esperienza hai nel ruolo?" |
| Seniority target | seniority_target |
"Che livello cerchi? (junior / mid / senior)" |
| Email contatto | candidate.contacts.email |
"Che email vuoi usare per le candidature?" |
| ≥2 skill primarie | skills.primary (≥2 voci) |
"Quali sono le tue 3 competenze più forti?" |
| ≥1 lingua | languages (≥1 con level) |
"Che lingue parli e a che livello?" (A1..C2/native) |
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 · 226 lines · 125 tokens per session scan A 3b0653861430
onboarding-flow is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 4,072 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
gws-drive
Google Drive: Manage files, folders, and shared drives.
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-calendar-insert
Google Calendar: Create a new event.
gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.