Borrowing it
Nothing to install: this file belongs to Waybox-AI/roadtrip-skill. 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/Waybox-AI/roadtrip-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/Waybox-AI/roadtrip-skillWrote 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/waybox-ai/roadtrip-skill/agents-md)<a href="https://agentmods.dev/instructions/waybox-ai/roadtrip-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/waybox-ai/roadtrip-skill/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/waybox-ai/roadtrip-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/waybox-ai/roadtrip-skill/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 | $0.04355 | $0.04355 |
| Opus 5 | $0.02178 | $0.02178 |
| Sonnet 5 | $0.00871 | $0.00871 |
| Haiku 4.5 | $0.00436 | $0.00436 |
Grade A, and why
roadtrip-skill AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
third-party pip packages** at runtime (`urllib`, `json`, `re`, `math`, …). Do **not** How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Universal Rulebook
Vendor-agnostic technical rules for working in this repo. Applies to any AI agent or human. For product/domain background see CONTEXT.md.
Branching Rule
- When creating git branches, if current base branch is not default branch (
main), you should prompt user to specify base branch - When submitting pull request (PR), you should set PR base branch as the current local base branch, instead of the browser github's default base branch
Hard constraints
- Python 3.8+ standard library only for
assets/,scripts/, andtools/. No third-party pip packages at runtime (urllib,json,re,math, …). Do not add runtime dependencies. Sole exception:mcp_server/depends on themcpSDK (declared inpyproject.toml) — never let it leak into the other dirs. Dev dependencies arepytestplusmcpfortests/test_mcp_server.py, which auto-skips whenmcpis absent so the stdlib+pytest baseline stays green. - Zero required API keys. Everything must run and test with no keys and no network.
Keys (
NPS_API_KEY,OCM_API_KEY,OPENWEATHER_API_KEY) are read from env vars only and are strictly optional upgrades. - Use
python3(there is nopythonon the standard dev machine).
Commands
# One-time: venv + test dependency (only pytest is needed)
python3 -m venv .venv && . .venv/bin/activate && pip install pytest
# Run the full test suite (CI runs exactly this)
python3 -m pytest tests/ -v
# Run a single test file / test
python3 -m pytest tests/test_generate.py -v
python3 -m pytest tests/test_helper.py -k drive_intensity -v
# Render a tripData JSON into the single-file HTML (the core output step)
python3 assets/generate.py assets/tripData.example.json -o trip.html
# Exercise helpers / clients standalone (each has a __main__ demo)
python3 scripts/helper.py "from Las Vegas, 7 days, 2 adults, gas, southwest loop"
python3 scripts/helper.py --compare
python3 tools/charging_client.py --corridor
python3 tools/routing_client.py 36.17,-115.14 37.30,-113.03
# Render the other bundled demo trips
python3 assets/generate.py assets/tripData.tahoe.json -o assets/preview-tahoe.html
python3 assets/generate.py assets/tripData.pnw.json -o assets/preview-pnw.html
# Probe other data sources directly
python3 tools/border_client.py US MX --rental
python3 tools/parks_client.py --countdown 2026-09-12
python3 tools/charging_client.py --leg 165 280
python3 tools/places_client.py "Zzyzx, CA" # place-name existence gate ("ABC" → no-match)
# MCP server: serve over stdio / run its tests (the one part that needs the mcp SDK)
pip install -e ".[dev]" # mcp SDK + pytest
python3 -m mcp_server.server
python3 -m pytest tests/test_mcp_server.py -v
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 · 290 lines · 4,355 tokens per session scan A d5f7c39b79b5
roadtrip-skill AGENTS.md is an instructions file published in the GitHub repository Waybox-AI/roadtrip-skill (98 stars, last pushed 12d ago), licensed MIT. It adds 4,355 tokens to every session, about $0.0218 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.