Agent Plugins Marketplace
← All plugins

until-loop

v0.7.0

Interpret natural-language work and evidence-based exit conditions with a private callback state file and LLM judgment.

CodexClaude Code1 Skill

By whichguyLicense: MIT0 GitHub starsUpdated 3 weeks ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 26, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install until-loop for Codex and Claude Code

Installs for the current user
codex plugin marketplace add IchenDEV/agent-plugin-mkt
codex plugin marketplace upgrade agent-plugin-marketplace
codex plugin add until-loop@agent-plugin-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/whichguy/until-loop

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/until-loop/.

Plugin files

plugins/until-loop/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/until-loop/SKILL.md

Included Skills1

until-loopskills/until-loop/SKILL.md

Interpret a natural-language request as work to pursue, a continuation condition, and an evidence-based exit condition. Adapt each next action until the outcome is established or a real blocker requires attention. User slash: /until-loop. Parent skills load this card. Same-turn execution with one temporary state file per run; does not invoke /goal.

Plugin manifests2

plugins/until-loop/.codex-plugin/plugin.json
{
  "name": "until-loop",
  "version": "0.7.0",
  "description": "Interpret natural-language work and evidence-based exit conditions with a private callback state file and LLM judgment.",
  "author": {
    "name": "whichguy",
    "url": "https://github.com/whichguy"
  },
  "homepage": "https://github.com/whichguy/until-loop",
  "repository": "https://github.com/whichguy/until-loop",
  "license": "MIT",
  "keywords": [
    "until-loop",
    "ephemeral-callback",
    "evidence-based"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Until Loop",
    "shortDescription": "Pursue work until its evidence-based exit condition holds",
    "longDescription": "Interpret natural-language work and evidence-based exit conditions with a private callback state file and LLM judgment.",
    "developerName": "whichguy",
    "category": "Productivity",
    "capabilities": [
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Use $until-loop to finish this task and verify its exit condition."
    ]
  }
}
plugins/until-loop/.claude-plugin/plugin.json
{
  "name": "until-loop",
  "version": "0.7.0",
  "description": "Interpret natural-language work and evidence-based exit conditions with a private callback state file and LLM judgment.",
  "author": {
    "name": "whichguy",
    "url": "https://github.com/whichguy"
  },
  "homepage": "https://github.com/whichguy/until-loop",
  "repository": "https://github.com/whichguy/until-loop",
  "license": "MIT",
  "keywords": [
    "until-loop",
    "ephemeral-callback",
    "evidence-based"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[until-loop on Agent Plugins Marketplace](https://pluginsmp.com/plugins/until-loop)