Borrowing it
Nothing to install: this file belongs to DV1-321/scalpstream-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DV1-321/scalpstream-mcp/main/GEMINI.mdgit clone --depth 1 https://github.com/DV1-321/scalpstream-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/instructions/dv1-321/scalpstream-mcp/gemini-md)<a href="https://agentmods.dev/instructions/dv1-321/scalpstream-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/dv1-321/scalpstream-mcp/gemini-md/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/instructions/dv1-321/scalpstream-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/dv1-321/scalpstream-mcp/gemini-md.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 | $0.01139 | $0.01139 |
| Opus 5.5 | $0.00456 | $0.00456 |
| Sonnet 5.5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
scalpstream-mcp GEMINI.md 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ScalpStream data tools
This extension runs the ScalpStream MCP server in Docker. It buys small, factual datasets per call over the x402 payment protocol: US product recalls, US border crossing wait times, cheapest fuel prices, air quality and a wash-sale check on the user's own trades. There is no account and no API key. The install above has no wallet configured, so it runs preview-only.
What every tool returns
One JSON envelope, for every tool:
| Field | Meaning |
|---|---|
paid |
Whether money moved for this result. false in preview-only mode, always. |
complete |
Whether data is the full dataset the tool describes. false means data is the service's free preview. |
source |
The exact URL the data came from (local for payment_status). |
data |
The dataset or the preview. |
reason, price, howto |
Present when paid is false: why no payment happened, the seller's exact quote (amount_usd, network, asset, pay_to), and how paid calls are enabled. |
complete is the field to branch on. A result with paid: false, complete: false
and a price is the designed outcome in preview-only mode, not an error: it
shows what the data looks like and what one call would cost (about $0.01 in
USDC on Base).
The tools:
product_recalls- active US recalls for a product, brand, ingredient or vehicle (make, model and year together) across FDA, NHTSA and CPSC, with the severity normalised onto one scale, the hazard, the remedy and the lot numbers or UPCs that say whether a specific unit is affected.completeis false when an agency could not be reached; that is never an all-clear.border_crossings- US land ports of entry ranked by all-in time (drive plus the current CBP wait) from a latitude and longitude, per vehicle type and lane eligibility. The nearest crossing is often not the fastest.cheapest_fuel- cheapest stations near a point in Spain, France or Italy for a fuel grade, or the official EIA weekly average for a US state.air_quality- current US AQI and pollutants for any coordinates, an EPA-based outdoor exercise verdict and the cleanest window ahead.wash_sale_check- the US wash-sale rule (IRC 1091) applied to the user's own trades across taxable, IRA and spouse accounts: would buying or selling a ticker on a date wash a loss, by how much, and the first safe rebuy date, or the whole ledger with adjusted basis and the year's totals. A rule calculation, not tax advice; the service keeps nothing. Pass the trades only when the user gave them for this, and relay the statement verbatim.payment_status- whether paid calls are enabled and what this process has spent. Local, free, safe to call first.my_engine_status- for ScalpStream managed-trading subscribers only: their own engine's status (running / paused / halted / crash / unarmed and why, equity, realized all-time and over 24 h, 7 d, 30 d, open positions, the last 20 closes). Free, no payment; needs the subscriber's status token in the server'sSCALPSTREAM_STATUS_TOKEN(never ask for it in chat). The figures are the user's own ledger: a record, never a forecast.
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 Changed · +6 lines · +119 tokens per session faaab5c59917
- 8d ago Changed · +8 lines · +153 tokens per session 28d9948a10bc
- 11d ago First seen · 63 lines · 867 tokens per session scan A 23547d8acfb8
scalpstream-mcp GEMINI.md is an instructions file published in the GitHub repository DV1-321/scalpstream-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 1,139 tokens to every session, about $0.0046 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 2026-10-26.
scalpstream-mcp GEMINI.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scalpstream-mcp GEMINI.mdDV1-321/scalpstream-mcp | Instructions file | 0 | yesterday | MIT | A | 1,139 | Gemini CLI |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |