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 agentmods add skills/ellmos-ai/bach/routingnpx skills add ellmos-ai/bach --skill routinggit clone --depth 1 https://github.com/ellmos-ai/bachWrote 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/ellmos-ai/bach/routing)<a href="https://agentmods.dev/skills/ellmos-ai/bach/routing"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/routing.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00568 |
| Opus 5 | $0.00000 | $0.00284 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
routing 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 5d 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.
What it actually says
BACH Routing Service
Version: 1.0 Autor: BACH System Datum: 2026-02-18 API-Key: Nicht erforderlich (OSRM public, Nominatim)
Beschreibung
Berechnet Routen zwischen GPS-Koordinaten (Auto, Fahrrad, zu Fuss). Datenquelle: OSRM oeffentliche Instanz (router.project-osrm.org). Geocoding: Nominatim / OpenStreetMap.
Nutzung (Library)
import sys
sys.path.insert(0, str(BACH_DIR))
from hub._services.routing.routing_service import get_route, get_route_text, geocode_place
# Lesbarer String
text = get_route_text(
start=(53.551, 9.994),
end=(52.520, 13.405),
mode="car",
start_name="Hamburg",
end_name="Berlin"
)
# Strukturiertes Dict
result = get_route(start=(53.551, 9.994), end=(52.520, 13.405), mode="car")
# -> {"distance_km": 64.2, "duration_str": "1h 1min", ...}
# Ortsname -> Koordinaten
coords = geocode_place("Freiburg im Breisgau")
# -> (47.9957839, 7.8493949)
Nutzung (CLI)
python routing_service.py <start_lat> <start_lon> <end_lat> <end_lon> [mode]
python routing_service.py 47.761 8.079 47.994 7.849 car
python routing_service.py 47.761 8.079 47.994 7.849 bike
Routing-Modi
| Modus | Bedeutung |
|---|---|
car |
Auto (Standard) |
bike |
Fahrrad |
foot |
Zu Fuss |
Rueckgabefelder (get_route)
distance_km– Distanz in kmduration_min– Fahrzeit in Minutenduration_str– Lesbare Fahrzeit (z.B. "1h 5min")mode_label– Modus auf Deutsch ("Auto", "Fahrrad", ...)mode_icon– Emoji (🚗, 🚲, 🚶)
Integration
- Telegram Bridge: Nutzer sendet GPS-Pin, dann z.B. "Route nach Freiburg"
- Claude ermittelt Ziel-Koordinaten via
geocode_place()und ruft routing_service.py auf - Empfohlene Nutzung in Claude: via Bash-Tool als Subprocess
What ships with it
2 files 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.
- 5d ago First seen · 62 lines · 0 tokens per session scan A 5394d15e9a51
routing is a skill published in the GitHub repository ellmos-ai/bach (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 568 tokens. 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
django-patterns
Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
fastapi-patterns
FastAPI patterns for async APIs, dependency injection, Pydantic request and response models, OpenAPI docs, tests, security, and production readiness.
jupyter-notebook
Iterative Python via live Jupyter kernel (hamelnb).
mem0-tour
Browses all stored memories grouped by category with full content display. Use when reviewing all project memories, exploring stored knowledge, onboarding to a project, or getting an overview of captured decisions, conventions, and learnings.