Borrowing it
Nothing to install: this file belongs to ergarcade/www-ergarcade. 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/ergarcade/www-ergarcade/master/.claude/skills/add-tool-card/SKILL.mdgit clone --depth 1 https://github.com/ergarcade/www-ergarcadeWrote 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/ergarcade/www-ergarcade/add-tool-card)<a href="https://agentmods.dev/skills/ergarcade/www-ergarcade/add-tool-card"><img src="https://agentmods.dev/badge/skills/ergarcade/www-ergarcade/add-tool-card/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/ergarcade/www-ergarcade/add-tool-card"><img src="https://agentmods.dev/badge/skills/ergarcade/www-ergarcade/add-tool-card.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 | $0.00103 | $0.01754 |
| Opus 5 | $0.00051 | $0.00877 |
| Sonnet 5 | $0.00021 | $0.00351 |
| Haiku 4.5 | $0.00010 | $0.00175 |
Grade C, and why
add-tool-card scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf public resources .hugo_build.lock Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl` every asset path the HTML references) — confirms nothing 404s before How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding a new tool card to www-ergarcade
This is a cross-repo, mechanical process: most of it happens in the
tool's own repo (a sibling directory, e.g. ../virtual-monitor), and the
last step happens here in www-ergarcade. First worked through end-to-end
for virtual-monitor — see that repo's git history and this repo's
content/tools/virtual-monitor.md for a worked example.
Read CLAUDE.md's "Adding a new tool card" section first for the front
matter schema and card conventions. This file is the detailed how-to.
0. Figure out the category
Tools vs Visualisations are different content/ sections with different
front matter conventions (see CLAUDE.md). A PM5-connected utility or app is
a Tool. A generative/visual thing driven by pace data with no real
"utility" purpose is a Visualisation. If it's genuinely unclear which,
ask the user rather than guessing — don't invent a third category.
1. Verify the app works, in its own repo
cd ../<tool-repo>
git status --short # clean tree, expected branch
node --test # or whatever its test command is
Also do a quick local-serve smoke test (e.g. python3 -m http.server +
curl every asset path the HTML references) — confirms nothing 404s before
you build a whole deploy pipeline around it.
2. Add a GitHub Pages deploy workflow, in its own repo
Check whether .github/workflows/deploy-pages.yml (or similar) already
exists — if the tool already deploys, skip to step 3. Otherwise, copy the
pattern from an existing sibling repo (pm5-base or virtual-monitor) and
adapt only the build step's file list to that repo's own layout:
pm5-basedeploysexample/(a subfolder) +lib/, and has to rewrite../lib/path references since flattening the subfolder into the site root changes relative paths.virtual-monitordeploys straight from the repo root (index.html,app.js, etc.) plus thepm5-basesubmodule'slib/— no path rewriting needed sinceindex.htmlalready referencespm5-base/lib/...directly.- If the tool vendors
pm5-baseas a submodule, the checkout steps needwith: { submodules: true }, and the build step'scp -roflib/must be recursive solib/mock-data/(including the sample CSV) comes along — it's a normal tracked file, not LFS, so a plain recursive copy is enough.
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 · 149 lines · 103 tokens per session scan C 3ae313b662ed
add-tool-card is a skill published in the GitHub repository ergarcade/www-ergarcade (2 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,754 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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…