prompt-forge-agent

prompt-forge-agent is a command for coding agents from tqnonline/agent-forge. It costs 86 tokens per session (232 once invoked), scanned A, original, BSD-3-Clause.

An agent for turning a user's intent and available context into a carefully structured prompt for another AI system.

In plain words
What is it for?
It can gather missing details, choose among prompting approaches, add safeguards, and return a prompt to run, revise, or save.
Why use it?
It helps when a request needs clearer instructions, selected prompting methods, and checks for assumptions or uncertainty.

Command

Part of the prompts plugin — 1 skill, 1 command, 1 agent shipped together

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/tqnonline/agent-forge/prompt-forge-agent
Clone the repo
git clone --depth 1 https://github.com/tqnonline/agent-forge

Or install prompts, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 agent.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/tqnonline/agent-forge/prompt-forge-agent.svg)](https://agentmods.dev/commands/tqnonline/agent-forge/prompt-forge-agent)
Your own site
<a href="https://agentmods.dev/commands/tqnonline/agent-forge/prompt-forge-agent"><img src="https://agentmods.dev/badge/commands/tqnonline/agent-forge/prompt-forge-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 232 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 $0.00086 $0.00232
Opus 5 $0.00043 $0.00116
Sonnet 5 $0.00017 $0.00046
Haiku 4.5 $0.00009 $0.00023

Measured 4d ago against content hash 8e428e28618f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prompt-forge-agent 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 4d 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.

plugins/prompts/commands/prompt-forge-agent.md · 25 lines

What it actually says

Prompt Forge Agent

Launch the prompt-forge-agent to intelligently build a high-quality prompt.

The agent will:

  1. Comprehend your intent and read relevant context from your environment
  2. Ask only the questions it cannot infer (2-4 max)
  3. Select the optimal technique and hardening patterns automatically
  4. Assemble a production-grade prompt with all layers composed
  5. Deliver the prompt with options to execute, refine, or save

Invoke the prompt-forge-agent agent with the user's full input.

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. 4d ago First seen · 25 lines · 86 tokens per session scan A 8e428e28618f

Subscribe to this mod's changes

prompt-forge-agent is a command published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 86 tokens to every session and 232 once invoked, about $0.0004 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.