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-registrynpx skills add ForgeyClap/claude-forge --skill forge-registrygit 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-registry)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-registry"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-registry.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 5.1 | $0.00042 | $0.00474 |
| Opus 5 | $0.00021 | $0.00237 |
| Sonnet 5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
forge-registry 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 5d 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
forge-registry — global project registry (opt-in, read-only)
An opt-in aggregate across every Forge project on this machine. It never runs automatically and never changes any project — it only reads and writes one global index.
When to use
- The owner asks "show me all my Forge projects" / "which projects have open tickets / failing tests".
- Before a portfolio-wide sweep, to see status/ports/last-run at a glance.
How to run
node .claude/forge-bin/forge-registry.cjs scan # scan ~/Documents, write the registry
node .claude/forge-bin/forge-registry.cjs scan --json # also print the aggregate to stdout
node .claude/forge-bin/forge-registry.cjs scan --root <dir> --run <run_id>
Outputs (global):
~/.claude/forge/registry/projects.json— machine-readable index.~/.claude/forge/registry/index.html— a self-contained home-view (open it directly in a browser; data is inlined, no server needed).
Each record: project_id, name, path, stack, status, last_run_id, last_run_status, last_run_at, open_tickets, test_status, port. test_status reads a run's doctor.json (from Forge Doctor) when present.
Hard rules (isolation + honesty)
- Reads other projects'
.claude/read-only (that is the opt-in aggregation job); it NEVER writes into any scanned project. The only thing written is the global registry dir. - Every record is secret-redacted before writing (defense in depth) — never persists a raw key.
- Real
DASHBOARD_STATE.json/run.jsondata only; a missing/malformed file yields honest defaults (unknown), never a fabricated status. - Opt-in only: it never runs on
require, only via thescancommand.
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.
- 5d ago First seen · 36 lines · 42 tokens per session scan A 6c4137eb1e03
forge-registry is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 474 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.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
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.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.