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 jmolinasoler/vbl_mcp --skill vblgit clone --depth 1 https://github.com/jmolinasoler/vbl_mcpWrote 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/jmolinasoler/vbl_mcp/vbl)<a href="https://agentmods.dev/skills/jmolinasoler/vbl_mcp/vbl"><img src="https://agentmods.dev/badge/skills/jmolinasoler/vbl_mcp/vbl/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/jmolinasoler/vbl_mcp/vbl"><img src="https://agentmods.dev/badge/skills/jmolinasoler/vbl_mcp/vbl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00045 | $0.00544 |
| Opus 5.5 | $0.00018 | $0.00218 |
| Sonnet 5.5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
vbl 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 2mo 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.
What it actually says
/vbl — Basketball Vlaanderen
Answer this question using the vbl MCP tools, then reply in the user's language:
$ARGUMENTS
If no question was given, ask what they want to know (a club, a team, standings, calendar, a match…).
Resolving a query
Everything is addressed by GUIDs, discovered top-down — never retype or trim a GUID; pass it exactly as a previous tool returned it (team GUIDs contain internal spaces, e.g. BVBL1004HSE 2).
- Club named? →
list_clubswithsearch(name, city, region or stam number). Several matches → ask which one, mentioning the city. - Need teams or poule GUIDs? →
get_club(club_guid)lists teams and the poules (series) each plays in. - Then pick the tool that answers the question:
- Standings/klassement →
get_poule_standings(poule_guid)— ifsourceis"computed"(not"official"), say the table is an estimate. - Calendar/results →
get_team_matches,get_poule_matchesorget_club_matches. - One match →
get_match(match_guid); lineups →get_match_lineup(returnsnulluntil the digital match form exists — normal for future matches). - People →
get_team(roster + coaches) orget_club_members(usesearch; the full list is huge).
- Standings/klassement →
Reading the data
Fields are Dutch: naam name · plaats city · uitslag result · gespeeld played (J/N) · tT* home / tU* away team · accNaam sports hall · datumString date DD-MM-YYYY · beginTijd time HH.MM · wedPunt competition points · wedAant games played · ptVoor/ptTegen points for/against · rangNr rank.
Only the current season exists — for past seasons, say the data is purged rather than guessing. For upcoming matches (gespeeld: "N"), mention date, time and sports hall.
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.
- 2mo ago First seen · 31 lines · 45 tokens per session scan A 6996a2df04aa
vbl is a skill published in the GitHub repository jmolinasoler/vbl_mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 544 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
vbl compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vbljmolinasoler/vbl_mcp | Skill | 0 | 2mo ago | MIT | A | 45 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | 2d ago | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |