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/logo-extractionWrote 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/logo-extraction)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/logo-extraction"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/logo-extraction/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/logo-extraction"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/logo-extraction.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 | $0.00112 | $0.01455 |
| Opus 5 | $0.00056 | $0.00727 |
| Sonnet 5 | $0.00022 | $0.00291 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
logo-extraction 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
logo-extraction — the company logo for the position page
The web shows the company logo on the position detail page. The logo
lives on the companies row (ONE per company: 1000 Wizz Air positions
= 1 logo) as a small base64 data-URI, and travels with the existing
companies sync. No upload, no external storage.
3 columns to fill in (logo_fetch.py writes them, NEVER by hand)
logo text base64 data-URI (png/jpeg/webp/ico), <= ~35KB raw
logo_source text URL the logo was extracted from (audit/refresh)
logo_fetched bool true = extraction ATTEMPTED (even if it failed) —
office_geocoded pattern: the company leaves the
next-for-logo-missing queue, no retry every round
GOLDEN RULE: right company, right site
The wrong logo is worse than no logo. Before launching the fetch,
verify that companies.website REALLY belongs to the company of the
position (not a namesake, not the aggregator that published the ad, not
the wrong parent group). When in doubt: web search
"<Company> official site" and compare with the sector/country on the row.
- Ad published by an agency/recruiter (Manpower, Randstad, ...) BUT on
behalf of a named hotel/company → the logo is that of the company on the
companiesrow linked to the position, whichever it is. - Chain vs property (e.g. "CARDO ROMA, Autograph Collection"): use the
logo of the brand that appears as
companies.name.
Workflow
Step 0 — The queue
python3 /app/shared/skills/db_query.py next-for-logo-missing
Lists companies with live positions and a logo never attempted, ordered by
number of positions (most visible first). NO WEBSITE (cercalo prima) = do Step 1 first.
Step 1 — Website missing? Find it and save it
# after a web search "<Company> official website":
python3 /app/shared/skills/db_update.py company "<Company>" \
--website https://www.wizzair.com
Step 2 — Automatic fetch (the normal path)
python3 /app/shared/skills/logo_fetch.py "<Company>"
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 · 130 lines · 112 tokens per session scan A 8e510938d69a
logo-extraction is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,455 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
cli-anything-photoshop
A command-line tool that controls Adobe Photoshop through Windows automation. It can work with Photoshop documents, layers, selections, text, image adjustments, and exports.
extract-design-system
Extract design primitives from a public website and generate starter token files for your project.
double-diamond
A four-stage design method for understanding a problem, defining it clearly, exploring possible solutions, and choosing one to deliver.
figma-use
Control Figma via CLI — create shapes, frames, text, components, set styles, layout, variables, export images. Use when asked to create/modify Figma designs or automate design tasks.
awesome-design-md
Create a DESIGN.md style baseline BEFORE building UI. Use FIRST when no design draft exists — installs a proven visual style, then invoke frontend-design to implement. For borrowing a known product style, getting consistent typography/colors/spacing, or needing a fast visual starting point.
make-interfaces-feel-better
Use when building or reviewing UI polish: typography, hit areas, nested radius, optical alignment, shadows, media outlines, micro-interactions, and animation performance.