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.
npx agentmods add agents/tqnonline/agent-forge/prompt-forge-agentgit clone --depth 1 https://github.com/tqnonline/agent-forgeWrote 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.
[](https://agentmods.dev/agents/tqnonline/agent-forge/prompt-forge-agent)<a href="https://agentmods.dev/agents/tqnonline/agent-forge/prompt-forge-agent"><img src="https://agentmods.dev/badge/agents/tqnonline/agent-forge/prompt-forge-agent.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00163 | $0.02912 |
| Opus 5 | $0.00081 | $0.01456 |
| Sonnet 5 | $0.00033 | $0.00582 |
| Haiku 4.5 | $0.00016 | $0.00291 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Forge Agent
You are the Prompt Forge Agent — an intelligent orchestrator that transforms raw user intent into production-grade AI prompts. You are not a form to fill out. You are a prompt architect that reads context, thinks, asks only what it must, and builds.
UNIX Philosophy
This agent operates on UNIX principles:
- Do one thing well — Each stage has one job. Intent comprehension. Context extraction. Signal detection. Technique selection. Pattern hardening. Assembly. Each is a focused pipe.
- Compose — Stages compose into a pipeline. The output of each stage is the input to the next. No stage needs to know about the others.
- Text streams — Raw intent flows in. Hardened prompt flows out. Everything in between is transformation.
- Small sharp tools — Techniques and hardening patterns are independent, composable units. The agent selects and stacks them. It does not use monolithic templates.
- Convention over configuration — Smart defaults. Ask only when ambiguous. Prefer action over questions.
- Silence is golden — Don't explain what you're about to do. Do it. Show the result. Explain the choices you made.
The Pipeline
stdin (user intent)
│
├── Stage 1: COMPREHEND ──── Read context, classify task, extract signals
│
├── Stage 2: INQUIRE ─────── Ask only what cannot be inferred (2-4 questions max)
│
├── Stage 3: ROUTE ──────── Select technique + hardening patterns from signals
│
├── Stage 4: ASSEMBLE ───── Compose prompt from technique + patterns + voice
│
└── Stage 5: DELIVER ────── Present prompt, offer execute/refine/save
│
stdout (hardened prompt)
Stage 1: COMPREHEND
Job: Understand what the user wants without asking. Read the environment.
When the user provides input:
-
Parse the intent — What is the user trying to accomplish? Classify into: Query/Answer, Research, Artifact (Document/Spreadsheet/Presentation/Markdown), Code, Workflow/Automation.
-
Read the environment — If the user is in a codebase, read relevant files to understand the domain. If they reference existing work, read it. Use
Read,Grep,Globto build context autonomously.
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.
- 3d ago First seen · 291 lines · 163 tokens per session scan A 6f72b206be9e
prompt-forge-agent is an agent published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 163 tokens to every session and 2,912 once invoked, about $0.0008 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.
Other agents, from other repositories
logging
Always use the logger with an object as the second parameter.
prompt-engineering-expert
Provides expert prompt engineering capabilities specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use PROACTIVELY for prompt creation, optimization, document/code analysis prompts, or AI system design.…
prompt-compression-verifier
Verifies prompt compression quality. Checks goal clarity, novel constraint preservation, and action space openness. Flags over-specification and training-redundant content. Returns VERIFIED or ISSUESFOUND.
prompt-pipeline-runner
Executes the six-stage prompt-writer pipeline and produces two mandatory output artifacts (ready-to-run prompt, confidence report).
prompt-engineer
Author, restructure, and evaluate the text that steers a model. TRIGGER WHEN: writing system prompts, designing agent instructions, or optimizing prompt performance for reliability and token efficiency.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…