forge-registry

forge-registry is a skill for Claude Code from ForgeyClap/claude-forge. It costs 42 tokens per session (474 once invoked), scanned A, original, MIT.

A read-only, optional index of Forge projects on one computer. It collects each project's location, technology, status, recent run, open tickets, test status, and port in one registry.

In plain words
What is it for?
Use it to list Forge projects, check which have open tickets or failing tests, and review status before a wider project sweep.
Why use it?
It removes the need to inspect projects one by one when you want an overview of their condition.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Install

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.

agentmods
npx agentmods add skills/forgeyclap/claude-forge/forge-registry
Any agent
npx skills add ForgeyClap/claude-forge --skill forge-registry
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code.

Wrote 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.

agentmods badge for forge-registry

README.md
[![agentmods](https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-registry.svg)](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-registry)
Your own site
<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>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 6c4137eb1e03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

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.

.claude/skills/forge-registry/SKILL.md · 36 lines

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.json data only; a missing/malformed file yields honest defaults (unknown), never a fabricated status.
  • Opt-in only: it never runs on require, only via the scan command.
Changes

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.

  1. 5d ago First seen · 36 lines · 42 tokens per session scan A 6c4137eb1e03

Subscribe to this mod's changes

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.