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 pigfoot/claude-code-hubs --skill taiwan-mrt-fareastern-empty-traingit clone --depth 1 https://github.com/pigfoot/claude-code-hubsWrote 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/pigfoot/claude-code-hubs/taiwan-mrt-fareastern-empty-train)<a href="https://agentmods.dev/skills/pigfoot/claude-code-hubs/taiwan-mrt-fareastern-empty-train"><img src="https://agentmods.dev/badge/skills/pigfoot/claude-code-hubs/taiwan-mrt-fareastern-empty-train/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/pigfoot/claude-code-hubs/taiwan-mrt-fareastern-empty-train"><img src="https://agentmods.dev/badge/skills/pigfoot/claude-code-hubs/taiwan-mrt-fareastern-empty-train.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 | $0.00060 | $0.01460 |
| Opus 5 | $0.00030 | $0.00730 |
| Sonnet 5 | $0.00012 | $0.00292 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
taiwan-mrt-fareastern-empty-train 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 11d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Taiwan MRT Far Eastern Hospital Empty Train Finder
Identifies trains that originate at 亞東醫院 station (空車) vs those arriving from 海山 station. Empty trains are less crowded because no passengers have boarded yet.
Background
The Bannan line (板南線) terminates at 頂埔 on the west end. Trains departing from 亞東醫院 are "empty trains" (空車) — they originate here with no passengers. Trains coming from 海山 (3 minutes west) already have riders.
Travel time: 海山 → 亞東醫院 ≈ 3 minutes
When to Use
Trigger when user asks about:
- 亞東醫院 空車 / empty trains at Far Eastern Hospital station
- 捷運空車 / which trains are less crowded
- 幾點有空車 / when are the empty trains
- 下一班空車 / next empty train
Workflow
Step 1: Determine Day Type
Always determine the correct day type BEFORE running the script.
Use the taiwan-calendar skill to check if the query date is a holiday or working day.
Run taiwan_calendar.py check <YYYY-MM-DD> from within the taiwan-calendar skill directory.
Map the result to a --day-type value:
| taiwan-calendar output | Weekday | --day-type |
|---|---|---|
| 非工作日 (國定假日 or Sunday) | any | sunday_holiday |
| 非工作日 (Saturday, not 補班) | Sat | saturday |
| 工作日 (including 補班 on Saturday) | Mon–Thu | mon_thu |
| 工作日 | Friday | friday |
If taiwan-calendar skill is unavailable: Omit
--day-typeentirely. The script falls back to weekday-based detection (no holiday awareness).
Step 2: Run the Script
From this skill's directory (skills/taiwan-mrt-fareastern-empty-train/):
# Show next N empty trains (空車 only)
uv run --managed-python ${CLAUDE_SKILL_DIR}/scripts/mrt_empty_train.py query \
--day-type <type> \
--time HH:MM \
--count 5
# Show all trains with 空車/海山發 labels
uv run --managed-python ${CLAUDE_SKILL_DIR}/scripts/mrt_empty_train.py all \
--day-type <type> \
--time HH:MM \
--count 10
Commands
query — Next Empty Trains
Shows the next N trains that originate at 亞東醫院 (空車 only).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 191 lines · 60 tokens per session scan A 6f713211bb89
taiwan-mrt-fareastern-empty-train is a skill published in the GitHub repository pigfoot/claude-code-hubs (5 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,460 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…