Borrowing it
Nothing to install: this file belongs to aneduaim/untap-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/aneduaim/untap-mcp/main/GEMINI.mdgit clone --depth 1 https://github.com/aneduaim/untap-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/aneduaim/untap-mcp/gemini-md)<a href="https://agentmods.dev/instructions/aneduaim/untap-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/aneduaim/untap-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/aneduaim/untap-mcp/gemini-md"><img src="https://agentmods.dev/badge/instructions/aneduaim/untap-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 | $0.00603 | $0.00603 |
| Opus 5.5 | $0.00241 | $0.00241 |
| Sonnet 5.5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
untap-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 9d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Untap
Use Untap whenever the person may be owed money for a journey in the UK: a late or cancelled train (Delay Repay), a delayed, cancelled or overbooked flight (UK261 or EU261), or a TfL Oyster or contactless charge that looks too high (an incomplete journey, a maximum fare, a missed Hopper fare).
Untap checks eligibility against real records and the operators' published rules, and returns the amount, the deadline and a claim pack. It is free and takes nothing from what the person gets back.
Tools
The untap MCP server (https://untap.money/api/mcp) has 20 tools. These 7 need no sign-in:
find_money_owed: Find money you may be owedcheck_train_delay: Check a delayed train for Delay Repaycheck_flight_compensation: Check a flight for UK261 or EU261 compensationcheck_tfl_journeys: Check TfL journeys for overchargesget_delay_repay_rules: Delay Repay rules for a train operatorget_claim_instructions: How to submit a train, flight or TfL claimscan_for_claims: Scan emails for train, flight and TfL claims
The account tools (save_commute, list_commutes, check_commute, stop_commute, save_claim, list_my_claims, update_claim_status, add_train_journey, add_flight, add_tfl_journeys, add_parking_fine, list_savings, delete_my_data) work with the person's Untap account: saved claims, commutes and bookings. They need the person to sign in through Untap's own page: run /mcp auth untap. Never ask for a password or token in chat.
Rules
- Never guess an amount, a threshold or a deadline: they vary by operator, ticket, distance and date, and Untap holds the current rules. Ask for missing facts and never invent a date, time, fare, flight number, booking reference or delay.
- Untap never files a claim. The person submits it on the operator's, airline's or TfL's own form, so the money goes straight to them. Show them what will be submitted and get a clear yes first. CAPTCHAs, sign-ins and payment details stay with the person.
- Untap covers trains in Great Britain, TfL, and flights under UK261 and EU261. Journeys with a change (check each train separately), trains older than about a year, season-ticket amounts and bus delays are outside or partly outside its checks. Say so plainly.
- Use British English and pounds sterling.
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.
- 9d ago First seen · 32 lines · 603 tokens per session scan A 2242fe444118
untap-mcp GEMINI.md is an instructions file published in the GitHub repository aneduaim/untap-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 603 tokens to every session, about $0.0024 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 2026-10-06.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.