frane-agented

A plugin package that provides agented, a text editor designed for language models. It includes a branching undo history, multi-file edits, and memory across sessions, and requires the `ae` program to be installed.

In plain words
What is it for?
Use it for language-model-driven editing, especially multi-file changes, undoing through alternative edit branches, and continuing work across sessions.
Why use it?
It gives an AI coding agent a way to edit text and files while retaining alternative edit histories and information between sessions.

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 frane/agented
agentmods
npx agentmods add plugins/frane/agented/marketplace
Clone the repo
git clone --depth 1 https://github.com/frane/agented

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

frane-agented scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"description": "A text editor for LLMs, not humans. Branching undo tree, atomic multi-file edits, cross-session memory. Requires the `ae` binary on PATH (install via `brew tap frane/tap && brew install agented` or the cu
.claude-plugin/marketplace.json · 18 lines

What it actually says

{
  "name": "frane-agented",
  "owner": {
    "name": "Frane Bandov",
    "email": "[email protected]"
  },
  "description": "agented (ae) — a text editor for LLMs, not humans.",
  "plugins": [
    {
      "name": "agented",
      "source": "./plugin",
      "description": "A text editor for LLMs, not humans. Branching undo tree, atomic multi-file edits, cross-session memory. Requires the `ae` binary on PATH (install via `brew tap frane/tap && brew install agented` or the curl one-liner from the README).",
      "category": "editor",
      "tags": ["editor", "stateful", "undo-tree", "lsp", "mcp"]
    }
  ]
}
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 · 18 lines scan A e03f8fa9bca1

Subscribe to this mod's changes

frane-agented is a plugin published in the GitHub repository frane/agented (5 stars, last pushed 1mo ago), licensed Apache-2.0. 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 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.