claude-forge: Skill for Claude Code

.claude/skills/forge-doctor/SKILL.md

forge-doctor is a skill for Claude Code from ForgeyClap/claude-forge. It costs 40 tokens per session (495 once invoked), scanned A, original, MIT.

A project self-test and secret-leak scanner for Forge installations. It checks JavaScript files, tests, dashboard files, event validation, and tracked files for exposed secrets.

In plain words
What is it for?
Checking a Forge project before shipping, handing it off, or investigating whether everything runs safely.
Why use it?
It finds broken code, failed tests, invalid events, missing dashboard files, and credentials or other secrets that could be committed.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ForgeyClap/claude-forge's own configuration. It tells Claude Code how to work on claude-forge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-forge configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/forge-bin/forge-doctor.cjs # print a green/red summary, exit 0/1.

Reuse

Borrowing it

Nothing to install: this file belongs to ForgeyClap/claude-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ForgeyClap/claude-forge/main/.claude/skills/forge-doctor/SKILL.md
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-doctor

README.md
[![agentmods](https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-doctor.svg)](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-doctor)
Your own site
<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-doctor"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-doctor.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 495 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00040 $0.00495
Opus 5 $0.00020 $0.00247
Sonnet 5 $0.00008 $0.00099
Haiku 4.5 $0.00004 $0.00049

Measured 7d ago against content hash 7ed858345cb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

forge-doctor 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 7d 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-doctor/SKILL.md · 37 lines

What it actually says

forge-doctor — self-test + leak scan

One command that proves the Forge install in this project actually works and leaks nothing.

When to use

  • The owner asks to "test everything", "check it all executes", or "find leaks".
  • Before a sync/handoff, or after a batch of tooling changes.
  • As the Security Boss's evidence step (the leak scan is a real security check).

How to run

node .claude/forge-bin/forge-doctor.cjs                 # print a green/red summary, exit 0/1
node .claude/forge-bin/forge-doctor.cjs --run <run_id>  # also write <run>/doctor.json + log doctor_run
node .claude/forge-bin/forge-doctor.cjs --json          # full machine-readable report

What it checks (all real — no fabrication)

  1. node --check on every .cjs/.js under forge-bin/ + forge-dashboard/.
  2. tests — runs every forge-bin/*.test.cjs and tallies passed/failed.
  3. honesty gate — feeds log-event.cjs a known type (expect accept) and an unknown type (expect hard-reject / exit 2), then deletes the throwaway run. Proves strict events still reject junk.
  4. dashboard SPA — the render files are all present.
  5. leak scan — scans git-tracked files with the hardened SECRET_PATTERNS; reports only {file, pattern}, never the matched secret. .env.example + binaries are skipped.

Writes <run>/doctor.json (read by the dashboard Doctor panel + the Project Registry's test_status). Exit code 0 = all green, 1 = a check failed — safe to gate a hook/CI on it.

Honesty

Real command output only. A failing check is reported as failing; the leak scan never prints a secret, only the file + which pattern matched. test_status in the registry mirrors this doctor.json.

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. 7d ago First seen · 37 lines · 40 tokens per session scan A 7ed858345cb4

Subscribe to this mod's changes

forge-doctor is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 495 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.

Related

Other skills, from other repositories

flame-harness-evaluator

Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.

tjdrhs90/flutter-flame-harness · 41 tokens

fabrik-validate

Use when operating as the Fabrik Validate stage agent. This skill guides final validation of an implementation, verifying requirements are met, tests pass, and the PR is ready to merge.

handarbeit/fabrik · 36 tokens

verify-implementation

A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.

sangrokjung/claude-forge · 37 tokens

agent-qa-testing

Agent davranis testi ve protokol uyumluluk dogrulamasi. Agent'larin tanimli rollerine uygun davranip davranmadigini assertion-based test'lerle olcer. Personality drift, role violation ve output kalite regresyonu tespit eder.

vibeeval/vibecosystem · 58 tokens

accessibility-a11y

WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.

travisjneuman/.claude · 26 tokens

vitest

Set up Vitest testing in any project — detects type (Cloudflare Workers, React, Node, library), generates vitest.config.ts, test setup, utilities, and a sample test. Covers mocking patterns, coverage config, workspace setup, Jest migration. Use whenever the user mentions adding tests, setting up Vitest, configuring…

jezweb/claude-skills · 87 tokens