generate

generate is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (578 once invoked), scanned A, original, MIT.

A local command for creating security-related values and development artifacts, including JWTs, API keys, passwords, key pairs, hashes, and environment files. JWTs are signed tokens often used to identify or authorize users and services.

In plain words
What is it for?
Use it to create or decode JWTs, generate keys and secrets, hash values, create webhook or two-factor-authentication data, and fill empty secret fields in environment files.
Why use it?
It provides these values without sending secrets to an external service, helping developers fill local configuration and test authentication-related code.

Command for Claude Code

Written for Claude Code: installed under .claude/.

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 commands/samibs/skillfoundry/generate
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

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 generate

README.md
[![agentmods](https://agentmods.dev/badge/commands/samibs/skillfoundry/generate.svg)](https://agentmods.dev/commands/samibs/skillfoundry/generate)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/generate"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 578 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 $0.00000 $0.00578
Opus 5 $0.00000 $0.00289
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 2d ago against content hash 51df948fb56c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

generate 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 2d 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/commands/generate.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/generate — Local Secret & Artifact Generator

Generate JWT tokens, API keys, passwords, key pairs, .env files, and more — locally, no external services. No secrets leave your machine.


Usage

/generate jwt --sub user123 --role admin --exp 24h
/generate jwt --alg RS256 --sub api-client --exp 7d
/generate jwt --decode eyJhbGciOi...
/generate keypair --alg RS256
/generate apikey --prefix sk
/generate uuid --count 10
/generate password --length 32
/generate secret --length 64 --encoding base64
/generate hash mypassword --algo scrypt
/generate hmac --data payload --secret key
/generate webhook-secret
/generate totp
/generate env api
/generate env fullstack
/generate auto                    (auto-fill empty secrets in .env)

Instructions

You are the Secret Generator — a local-only tool that generates cryptographic artifacts without any network calls. When /generate is invoked, produce the requested artifact using Node.js crypto module.

When invoked during /forge or /go pipeline:

AUTOMATICALLY run /generate auto at the start of every project implementation to:

  1. Check for .env or .env.example files
  2. Find empty secret-like variables (JWT_SECRET=, API_KEY=, SESSION_SECRET=, etc.)
  3. Auto-fill them with cryptographically secure random values
  4. Generate RS256 key pairs if the project uses JWT
  5. Report what was generated

Auto-Integration Rules

When implementing any project that has authentication:

  • JWT_SECRET: Generate 64-char hex secret → insert in .env
  • JWT key pair: Generate RS256 keys → save to .keys/ → add .keys/ to .gitignore
  • API_KEY: Generate sk_ prefixed key → insert in .env
  • SESSION_SECRET: Generate 48-char hex → insert in .env
  • COOKIE_SECRET: Generate 48-char hex → insert in .env
  • WEBHOOK_SECRET: Generate whsec_ prefixed secret → insert in .env

Hard Rules

  • NEVER send secrets to any external service or API
  • ALWAYS use crypto.randomBytes() for randomness (not Math.random)
  • DO add .keys/ and .env to .gitignore when generating key files
  • CHECK for existing secrets before overwriting — never destroy user-set values
  • ENSURE generated passwords meet complexity requirements (upper, lower, digit, special)
  • IMPLEMENT RS256 or ES256 for JWT in production — HS256 only for development/testing

Read the full file on GitHub · 60 lines

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. 2d ago First seen · 60 lines · 0 tokens per session scan A 51df948fb56c

Subscribe to this mod's changes

generate is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 578 tokens. 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 2026-09-03.