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/office-geocodingWrote 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/office-geocoding)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/office-geocoding"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/office-geocoding/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/office-geocoding"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/office-geocoding.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 50 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 | $0.00091 | $0.02481 |
| Opus 5 | $0.00046 | $0.01241 |
| Sonnet 5 | $0.00018 | $0.00496 |
| Haiku 4.5 | $0.00009 | $0.00248 |
Grade A, and why
office-geocoding 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
office-geocoding — coordinate precise dell'ufficio
Run dopo location-enrichment. Prerequisiti: loc_city e/o
loc_country popolati (da R12-15). Se la position è full-remote senza
city, skip immediato (no office da geocodare).
5 colonne da popolare
office_lat numeric latitudine WGS84 (es. 41.8933203)
office_lon numeric longitudine WGS84 (es. 12.4829321)
office_address text indirizzo completo dell'ufficio
office_geocoded bool true se hai eseguito geocoding
office_verified bool true se SEI SICURO sia l'ufficio giusto;
false se city-level fallback / multi-ambiguo
REGOLA d'oro: web verification obbligatoria
NON salvare mai un indirizzo street-level senza prima averlo verificato via web come ufficio reale della company. La sequenza corretta è web search PRIMA, geocoding DOPO — non l'inverso.
Sequenza canonica (sempre in quest'ordine)
-
Tentativo 1 — Web search HQ company nella city
- Query:
"<Company> headquarters <city> address","<Company> sede <city>","<Company> office <city>","<Company> contact" - Sorgenti accettabili come prova: sito company ufficiale, LinkedIn "About", Crunchbase, registri d'impresa (partitaiva.it, cerved.com per IT), Google Maps result della company.
- Estrai l'indirizzo dalla sorgente trovata.
- Query:
-
Tentativo 2 — Estrazione da JD
- Cerca pattern "Visit us at...", "Sede operativa:", "Our office", indirizzo nel piè di pagina dello JD.
-
Tentativo 3 — Webfetch di una sorgente sospetta
- Se la web search mostra titolo ma non snippet con indirizzo,
WebFetchdella pagina ufficiale per estrarre.
- Se la web search mostra titolo ma non snippet con indirizzo,
-
Geocoding via Nominatim/Photon SOLO dopo aver trovato l'indirizzo. Nominatim/Photon convertono testo→coordinate, non sono verification. Niente address da web → niente
office_verified=true. -
Fallback city-level quando tutti i tentativi sopra falliscono: geocoda il nome city (es.
"Roma, Italy"), salva conoffice_verified=falseeoffice_address = <city>, <country>. MAI lasciare NULL se la position ha city/country dal location- enrichment — usa il fallback city.
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 · 239 lines · 91 tokens per session scan A 5f215c91cfc5
office-geocoding is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 2,481 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-researcher
Organize research — manage references, notes, and collaboration.
persona-team-lead
Lead a team — run standups, coordinate tasks, and communicate.
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.