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 metrxbots/mcp-server --skill check-vendor-billgit clone --depth 1 https://github.com/metrxbots/mcp-serverWrote 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/metrxbots/mcp-server/check-vendor-bill)<a href="https://agentmods.dev/skills/metrxbots/mcp-server/check-vendor-bill"><img src="https://agentmods.dev/badge/skills/metrxbots/mcp-server/check-vendor-bill/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/metrxbots/mcp-server/check-vendor-bill"><img src="https://agentmods.dev/badge/skills/metrxbots/mcp-server/check-vendor-bill.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 | $0.00059 | $0.00805 |
| Opus 5.5 | $0.00024 | $0.00322 |
| Sonnet 5.5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
check-vendor-bill 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 yesterday.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check a vendor bill
A per-resolution bill lists units the vendor says it resolved. The company's own records (ticket events, resolved and rejected ids) say what actually happened. This skill puts the two side by side.
Steps
- Collect:
period:{ "from": ISO, "to": ISO }, from before to.billed: the bill lines, each{ "external_id", "billed_at", "cost_usd" }, optionallytier_name,adjustment_of(a negative line that refers back to an earlier one), andid. Up to 500 lines per call.- At least one of:
resolved_ids(ids your records show as resolved by the agent),rejected_ids(a person overturned it), orledger(events{ "external_id", "event_type", "occurred_at" }whereevent_typeissolved,closed,reopenedorpublic_comment). covered_spans: the time spans your records cover,{ "from": ISO, "to": ISO | null }. If the person cannot say, leave it out and tell them every unit will be reported as outside coverage.- Optional:
import_rejected_count, the number of ledger rows that failed to import, so the report can say how much it could not see. If the person pastes a CSV, convert it faithfully; ask when a column is ambiguous rather than guessing which id is the vendor's.
- Call
metrx_check_vendor_billwith the input. No key is needed; the tool stores nothing. - Relay the result as a short reconciliation:
- The
summary: their count andtheir_usd, matched, disputed, unmatched, uncounted (rejected), outside coverage, anddisputed_usd,unmatched_usd,outside_coverage_usd.dropped_outside_periodsays how many bill lines fell outside the period and were not judged. Relay thenote. - Each class in one sentence: matched means your records show the resolution; disputed means your records show it reopened; uncounted means a person rejected it (overturned the resolution), so it is not counted either way; unmatched means your records have no trace of it; outside coverage means your records do not cover that time, so nothing can be said either way.
- When
withheldis true, say why: rejected lines are present, or the importer rejectedimport_rejectedrows, so the records are known to be incomplete and no total difference is stated. - The disputed lines, each with its reason.
Every amount is measured from the two inputs and is labelled
measured. The result is a reconciliation, not a refund; say what the person can take to the vendor and leave the next step to them.
- The
- When
delta_usdis null (always so whilewithheldis true) the tool could not form a total difference; say so and do not compute a substitute figure from the per-class amounts.
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.
- yesterday First seen · 60 lines · 59 tokens per session scan A 15a5e91087c7
check-vendor-bill is a skill published in the GitHub repository metrxbots/mcp-server (2 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 805 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 2026-11-10.
check-vendor-bill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| check-vendor-billmetrxbots/mcp-server | Skill | 2 | 2d ago | MIT | A | 59 | Claude Code |
| meter-chargebackSnowflake-Labs/cocoplus | Skill | 728 | 4d ago | MIT | A | 33 | Claude Code |
| meter-statusSnowflake-Labs/cocoplus | Skill | 728 | 4d ago | MIT | A | 16 | Claude Code |
| prediction-marketsBlockRunAI/blockrun-mcp | Skill | 390 | yesterday | MIT | A | 136 | Claude Code, Codex |
| crypto-dataBlockRunAI/blockrun-mcp | Skill | 390 | yesterday | MIT | A | 194 | Claude Code, Codex |
| polymarket-tradingBlockRunAI/blockrun-mcp | Skill | 390 | yesterday | MIT | A | 72 | Claude Code, Codex |
| signal-to-trade-demoBlockRunAI/blockrun-mcp | Skill | 390 | yesterday | MIT | A | 88 | Codex |