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/wiseaidotdev/autogpt/frontend-gptgit clone --depth 1 https://github.com/wiseaidotdev/autogptWhat 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 | $0.00000 | $0.00450 |
| Opus 5 | $0.00000 | $0.00225 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
frontend-gpt 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FrontendGPT
Feature: gpt CLI: autogpt front
FrontendGPT generates complete frontend user interface code for web applications. It produces HTML, CSS, JavaScript, and framework-specific components, responsive by default and styled appropriately for the described use case.
What FrontendGPT Solves
Translating a feature description into a working, well-structured UI requires decisions about layout, component hierarchy, data binding, and styling. FrontendGPT makes those decisions automatically, generating a complete starting point rather than skeleton files.
Supported Stacks
FrontendGPT accepts the programming language / framework as a string:
| Value | Output |
|---|---|
javascript |
Vanilla HTML/CSS/JS or React/Vue based on context |
react |
React component tree with JSX |
python |
Jinja2 HTML templates (for FastAPI/Flask) |
rust |
Yew WASM components |
CLI Usage
autogpt front
SDK Usage
use autogpt::prelude::*;
#[tokio::main]
async fn main() {
let persona = "UX/UI Designer";
let behavior = "Generate UI for a weather app using React JS.";
let agent = FrontendGPT::new(persona, behavior, "javascript").await;
AutoGPT::default()
.with(agents![agent])
.build()
.expect("Failed to build AutoGPT")
.run()
.await
.unwrap();
}
Output
workspace/frontend/
├── main.py # (Python) Template renderer entry point
├── template.py # (Python) Jinja2 templates
└── ... # HTML/CSS/JS files for JS-based projects
Pairing with BackendGPT
FrontendGPT is aware of the backend API schema when run via ManagerGPT. This means the generated frontend code calls the correct API endpoints defined by BackendGPT, producing a cohesive full-stack result.
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.
- 2d ago First seen · 62 lines · 0 tokens per session scan A 54381d84b61a
frontend-gpt is an agent published in the GitHub repository wiseaidotdev/autogpt (115 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 450 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 2026-08-30.
Other agents, from other repositories
agent_class
The Agent class is the core orchestrator in AgentForge. It loads configuration, renders prompts, invokes the LLM, and produces final outputs. Agents can be subclassed for custom logic.
custom_agents
This is an advanced extension reference.
agent_prompts
AgentForge uses YAML-based prompt templates to drive agent behaviors. All prompt files live under.
agents
Agents are the orchestrators in AgentForge, binding configuration, prompts, models, and storage into end-to-end AI workflows. An agent.
verify
Verifies edits conform to project AGENTS.md and suggests simplifications.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.