prompt-forge

prompt-forge is a plugin for Claude Code from mturac/hermes-supercode-skills. Its manifest loads nothing; the 13 skills it bundles cost 1,828 tokens per session together, scanned A, original, MIT.

A prompt-design add-on for writing system instructions, creating few-shot examples, and evaluating how prompts perform. Few-shot design means guiding an AI with a small set of examples.

In plain words
What is it for?
Use it to draft system prompts, design example-based instructions, and evaluate prompt behavior.
Why use it?
It helps make AI instructions more consistent and makes it easier to compare whether a prompt produces the intended results.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add mturac/hermes-supercode-skills
agentmods
npx agentmods add plugins/mturac/hermes-supercode-skills/prompt-forge
Clone the repo
git clone --depth 1 https://github.com/mturac/hermes-supercode-skills

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 prompt-forge

README.md
[![agentmods](https://agentmods.dev/badge/plugins/mturac/hermes-supercode-skills/prompt-forge.svg)](https://agentmods.dev/plugins/mturac/hermes-supercode-skills/prompt-forge)
Your own site
<a href="https://agentmods.dev/plugins/mturac/hermes-supercode-skills/prompt-forge"><img src="https://agentmods.dev/badge/plugins/mturac/hermes-supercode-skills/prompt-forge.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 13 skills cost 1,828 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

prompt-forge 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 yesterday.

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-plugin/marketplace.json#prompt-forge · 6 lines

What it actually says

{
  "name": "prompt-forge",
  "type": "skill",
  "path": "skills/prompt-forge",
  "description": "System prompt engineering, few-shot design, evaluation"
}
Files

What ships with it

1 file beside marketplace.json#prompt-forge in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 6 lines scan A 93ff1114a704

Subscribe to this mod's changes

prompt-forge is a plugin published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.