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.
git clone --depth 1 https://github.com/rohingosling/claude-skillsWrote 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/plugins/rohingosling/claude-skills/g-render-ascii-memory-map)<a href="https://agentmods.dev/plugins/rohingosling/claude-skills/g-render-ascii-memory-map"><img src="https://agentmods.dev/badge/plugins/rohingosling/claude-skills/g-render-ascii-memory-map/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/plugins/rohingosling/claude-skills/g-render-ascii-memory-map"><img src="https://agentmods.dev/badge/plugins/rohingosling/claude-skills/g-render-ascii-memory-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
g-render-ascii-memory-map 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.
What it actually says
{
"name": "g-render-ascii-memory-map",
"description": "Render an ASCII box-drawing memory map (an address-space layout diagram) from a JSON description, for any architecture — Commodore VIC-20/C64, x86 real-mode/segmented, ARM/MCU flash+SRAM, or flat 32/64-bit. Separates the map's data from its rendering and offloads all box drawing, column alignment, address formatting, and size-proportional block heights to the renderer, so the caller only authors compact JSON. Dependency-free Python.",
"version": "1.0.0",
"author": {
"name": "Rohin Gosling"
},
"homepage": "https://github.com/rohingosling/claude-skills",
"repository": "https://github.com/rohingosling/claude-skills",
"license": "MIT",
"keywords": [ "ascii", "memory-map", "address-space", "diagram", "render", "documentation", "markdown" ]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 127 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 13 lines scan A effa7330baae
g-render-ascii-memory-map is a plugin published in the GitHub repository rohingosling/claude-skills (7 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
unifi
Agent skills for administering a UniFi network over its local API: API-key auth and the endpoint map, the zone-based firewall, Wi-Fi channel planning, client and switch-port operations, and the site inventory file. Verified against UniFi OS 5.1.19 / Network 10.4.57, and written for the traps: config the controller…
dm42
dm42 — write, review and debug HP-42S-family RPN programs, the SwissMicros DM42n first (also DM42, Free42, Plus42). /dm42:rpn (model-invoked) is the workflow and the verified reference: program-text rules, stack lift, flags, locals, menus, GETKEY vs GETKEY1, PIXEL/AGRAPH, the DM42 virtual variables and graphics modes.
cardputer
Hardware reference and firmware-development helper for the M5Stack Cardputer family. Covers pinout, I2C peripherals (TCA8418 keyboard, BMI270 IMU, ES8311 codec), display, Grove/EXT ports, battery behavior, and setup for Arduino IDE, PlatformIO, ESP-IDF, and UIFlow2. Includes cap accessories that snap onto the…
esp32-chips
Chip-level ESP-IDF capability references for the Espressif SoCs behind M5Stack boards: classic ESP32 (Xtensa LX6), ESP32-S3 (Xtensa LX7), ESP32-C6 (RISC-V, WiFi 6 + Thread/Zigbee), and ESP32-P4 (RISC-V, MIPI-DSI/CSI, no radio). Covers peripherals, sleep modes and ULP/LP coprocessors, memory and PSRAM config, USB…
batocera
Agent skills for operating a Batocera retro-gaming cabinet over SSH: connection and safety doctrine, ROM and gamelist curation, shaders and bezels, performance tuning, and maintenance. Distilled from twelve months of running a real arcade cabinet with coding agents.
garmin-dev
Build, run, package, and ship a Garmin Connect IQ app (watch face, data field, widget, device app) on Windows, macOS, or Linux. Auto-detects SDK + JDK + project name + target device from manifest.xml — no per-machine config.