Borrowing it
Nothing to install: this file belongs to aaryan-gulia/uktrains. 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/aaryan-gulia/uktrains/main/AGENTS.mdgit clone --depth 1 https://github.com/aaryan-gulia/uktrainsWrote 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/aaryan-gulia/uktrains/agents-md)<a href="https://agentmods.dev/instructions/aaryan-gulia/uktrains/agents-md"><img src="https://agentmods.dev/badge/instructions/aaryan-gulia/uktrains/agents-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/aaryan-gulia/uktrains/agents-md"><img src="https://agentmods.dev/badge/instructions/aaryan-gulia/uktrains/agents-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 | $0.04650 | $0.04650 |
| Opus 5.5 | $0.01860 | $0.01860 |
| Sonnet 5.5 | $0.00930 | $0.00930 |
| Haiku 4.5 | $0.00465 | $0.00465 |
Grade A, and why
uktrains AGENTS.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 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.
How it starts
The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.
uktrains — agent guide
You are probably an LLM agent whose human asked for something like "book me a train for my next meeting." This file tells you how to install uktrains, what it can and cannot do, and how to give your human the best experience.
What this tool is (and is not)
uktrains searches UK rail journeys, quotes fares (once keyed), and produces pre-filled booking links. It never takes payment and never books. The human always makes two final taps on the retail page: pick the specific train, then pay. Do not tell your human a booking was made — say you prepared a link.
Context is your job, not the tool's. uktrains deliberately stores no
home station, no calendar, no location. You already know those from your
other tools. You translate "my next meeting" into --to, --arrive-by,
and a buffer; uktrains translates that into trains and links.
Install (once)
Requires Node 22.12+ (commander@15's own floor).
git clone https://github.com/aaryan-gulia/uktrains.git
cd uktrains
npm install
npm run build
npm link # puts the `uktrains` binary on PATH — every command below and
# every setup `paste`/`recovery` string assumes this ran
uktrains stations york # smoke test — expect JSON with "crs": "YRK"
Everything works immediately at Tier 0 (no signups): station resolution, journey intents, booking links. Do not block your human's first request on setup — deliver the Tier 0 link first, offer the upgrades after.
If npm link isn't available in your environment (no write access to the
global npm prefix, a sandboxed install, etc.), every uktrains ... command
below and every paste/recovery string that names one is equally the
invocation node dist/cli/index.js ... from the repo root — the binary and
the built entry point are the same code either way.
Use it as a CLI or as an MCP server — your choice
CLI (zero configuration, JSON to stdout, non-zero exit + JSON error envelope on failure):
node dist/cli/index.js search --from "london euston" --to manchester \
--arrive-by 2031-08-01T14:30:00+01:00
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 · 309 lines · 4,650 tokens per session scan A 75b686fe611e
uktrains AGENTS.md is an instructions file published in the GitHub repository aaryan-gulia/uktrains (0 stars, last pushed 3mo ago), licensed MIT. It adds 4,650 tokens to every session, about $0.0186 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.
uktrains AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| uktrains AGENTS.mdaaryan-gulia/uktrains | Instructions file | 0 | 3mo ago | MIT | A | 4,650 | Codex, OpenCode |
| 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 |