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/forgeyclap/claude-forge/forge-electronnpx skills add ForgeyClap/claude-forge --skill forge-electrongit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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/forgeyclap/claude-forge/forge-electron)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-electron"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-electron.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 | $0.00041 | $0.01101 |
| Opus 5 | $0.00020 | $0.00550 |
| Sonnet 5 | $0.00008 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
forge-electron 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Electron / desktop app
The electron-pro specialist (.claude/agents/electron-pro.md) leads the Electron-specific work under Build Boss or Integration Boss. Renderer UI defers to forge-website (real content, responsive, a11y); anything that talks to a gateway/API defers to forge-integration / forge-payments. Forge context: the boekhouder (accounting) desktop app — offline-first, safe IPC, an installer that opens on a clean machine. Modern Electron (v20+) ships these secure defaults; the rule is to never regress them, and to prove they hold.
Hard rules (verify, don't assume — cite the exact config line)
contextIsolation: trueon everyBrowserWindow— no exceptions. Required even with nodeIntegration off; it is what separates preload/renderer JS contexts from Electron internals.nodeIntegration: falsein all renderers. Node reaches the renderer only through a preloadcontextBridge.exposeInMainWorldwith an explicit, minimal API — never a rawipcRendererpassthrough onwindow. (EnablingnodeIntegration:truealso disables the sandbox for that renderer.)sandbox: truewhere feasible;webSecurityleft enabled; remote module disabled;allowRunningInsecureContent: false.- Validated IPC. Every IPC channel validates its payload and (where relevant) sender; the exposed API surface is a small allow-list, not the whole
ipcRenderer. - Strict CSP — no
'unsafe-eval', no wildcard remote script sources. (CSP limits, not cures, XSS — defense in depth on top of context isolation.) - No secrets baked into the bundle. Sensitive data uses OS-appropriate secure storage (Keychain/DPAPI/libsecret), not plain files; secrets in env / secure store, never in the packaged asar.
- A real, signed installer that actually opens. The build produces the intended artifact (e.g. Windows NSIS), the installer installs and launches on a clean machine (verify — don't assume), and auto-update (if in scope) verifies signatures + supports rollback. Never ship an unsigned silent updater.
- No test/demo/mock/placeholder data in the shipped build (Forge desktop rule).
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.
- 4d ago First seen · 42 lines · 41 tokens per session scan A 43f43e989f4b
forge-electron is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,101 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other skills, from other repositories
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.