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 cyanheads/openchargemap-mcp-server --skill openchargemap-guidegit clone --depth 1 https://github.com/cyanheads/openchargemap-mcp-serverWrote 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/cyanheads/openchargemap-mcp-server/openchargemap-guide)<a href="https://agentmods.dev/skills/cyanheads/openchargemap-mcp-server/openchargemap-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/openchargemap-mcp-server/openchargemap-guide/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/cyanheads/openchargemap-mcp-server/openchargemap-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/openchargemap-mcp-server/openchargemap-guide.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 | $0.00041 | $0.01001 |
| Opus 5.5 | $0.00016 | $0.00400 |
| Sonnet 5.5 | $0.00008 | $0.00200 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
openchargemap-guide 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 today.
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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
Use Open Charge Map to discover registered charging stations and inspect their equipment, access conditions and community check-ins. It cannot guarantee present operation or an unoccupied stall, plan a driving route, or search a global stream of fault reports. Live station calls require the server's configured Open Charge Map API key.
Place-name resolution composes with an external geocoder such as openstreetmap_search_places; an existing coordinate or bounding box needs no geocoding step.
Identifiers
openchargemap_find_stationsreturns the numeric stationidused byopenchargemap_get_stationandopenchargemap_get_station_comments. A station'suuidcannot be used to fetch it.openchargemap_lookup_referencereturns category-specific reference IDs. Follow itsfilterParamwhen present; country entries instead supplyisoCode. A numeric country ID is not a country search code, and current-type entries have no direct search filter.- Connector families can resolve to multiple entries. Select the variants appropriate to the user's equipment and region rather than treating the first match as universal. An unknown connector entry does not establish vehicle compatibility.
Gates
- Confirm the applied search scope before comparing results. Read the search summary and notices. An unrecognized country code is not applied, so resolve a valid country code and repeat before describing results as country-restricted.
- Check the intended connection before recommending a station. A station can have several connector types and power ratings. Inspect the matching connection's power, status and notes with
openchargemap_get_station, together with station access restrictions and cost. A search match does not establish that the user's connector supplies the station's highest power. Missing power, quantity or access evidence stays unknown; estimated power is not guaranteed delivery. - Separate recent evidence from registry claims. Compare status text, operational flags, verification dates and dated check-in outcomes before calling a charger usable. A station-level operational flag does not override an unavailable or partly operational status, or a fault on the intended connection. No comments and no reliability warning are not confirmations that charging works.
- Establish coverage before claiming absence or completeness. An empty successful response may mean no matches, an offset past the end, or no matching stations in the retrieved candidate pool. Use the notice and counts to distinguish them. Follow
nextOffsetwhen supplied; if the notice says upstream stations remain beyond the pool, narrow the area or add suitable filters. A retrieved count is then a floor, not the area's total. Even an exhausted registry search establishes only what OCM records for that scope. - Resolve reference misses before relaxing the user's requirements. For an empty lookup, check spelling, broaden the term or browse the category. Read
sourcewithsnapshotDate: a bundled snapshot may lack a recently added operator or connector. Do not silently remove an unresolved filter or conclude the network does not exist.
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.
- today First seen · 47 lines · 41 tokens per session scan A 066372c1dfd7
openchargemap-guide is a skill published in the GitHub repository cyanheads/openchargemap-mcp-server (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,001 once invoked, about $0.0002 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 2026-10-27.
Other skills, from other repositories
omh-physical-device-readiness
This is an OMH physical-device-readiness workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
embedded-iot
Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.
wasm
WebAssembly (WASM) integration, WASI, component model, Rust/Go to WASM compilation. Use when implementing WASM modules, browser/edge compute, or polyglot runtime.
asus-router-ops
ASUS router config and hardening: Asuswrt-Merlin, security hardening, encrypted DNS (DoT/DoH), VPN (WireGuard/OpenVPN), guest networks, VLAN/IoT isolation, AiMesh, AiProtection. Triggers on: asus router, asuswrt, merlin, wireguard router, AiProtection, AiMesh, nvram, jffs, IoT isolation.
earllm-build
Build, maintain, and extend the EarLLM One Android project — a Kotlin/Compose app that connects Bluetooth earbuds to an LLM via voice pipeline.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.