Agent Plugins Marketplace
← All plugins

agent-factory

v1.32.0

Agent roles, house rules, and repo provisioning commands for turning objectives into shipped code.

Claude Code7 Skills

By chamaya00License: MIT0 GitHub starsUpdated 4 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
7 skill or MCP entries
Source updated
Sep 20, 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 agent-factory for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install agent-factory@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. 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/chamaya00/agent-factory

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

Plugin files

plugins/agent-factory/
├── .claude-plugin/plugin.json
├── skills/acceptance-criteria/SKILL.md
├── skills/briefing/SKILL.md
├── skills/design-craft/SKILL.md
├── skills/driving-an-objective/SKILL.md
├── skills/house-rules/SKILL.md
├── skills/instrumentation/SKILL.md
└── skills/memory-protocol/SKILL.md

Included Skills7

acceptance-criteriaskills/acceptance-criteria/SKILL.md

The format for writing acceptance criteria that are observable and checkable, used when creating child issues, judging whether an issue is ready to start, or deciding whether a pull request actually satisfies its issue.

briefingskills/briefing/SKILL.md

The contract between the orchestrator's report on a parent issue and the session driving the objective - what has to reach the driver intact, what has to be compressed, what order it is ranked in, and what a driver may send back. Use when writing the status picture on an objective, reading one, or deciding whether a report was good enough to act on.

design-craftskills/design-craft/SKILL.md

How to act like a designer rather than a transcriber - refining the request before answering it, exploring more than one direction, what "modern" is allowed to mean in checkable terms, and the critique pass against the rendered mock. Use on any issue that changes how something looks, before writing the spec.

driving-an-objectiveskills/driving-an-objective/SKILL.md

How an interactive session drives an objective it filed or was pointed at - the technical judgment it owns, what it may reject and how, what to read and what not to, adopting the merge policy, and surfacing what only the person can decide. Use whenever an objective is in play, a child reaches review, a pull request is waiting, or a session is catching up on what happened while nobody was watching.

house-rulesskills/house-rules/SKILL.md

The non-negotiable process rules for any repo built by the factory - acceptance criteria before work, tests before merge, an ADR for schema and dependency changes, and the three-strike rule. Use at the start of any agent run and whenever deciding whether a piece of work is ready to start or ready to merge.

instrumentationskills/instrumentation/SKILL.md

How an event is chosen, emitted, verified, and stored - the implementation half of a measurement contract. Use when deciding what is worth logging, building or reviewing event logging, wiring the exposure point of an experiment, or judging where events should be kept.

memory-protocolskills/memory-protocol/SKILL.md

How repository-specific lessons are stored, proposed, capped, and retired in .claude/memory/<role>.md. Use when writing a retro, proposing a lesson learned, reading prior lessons at the start of a run, or deciding whether a lesson still earns its place.

Plugin manifests1

plugins/agent-factory/.claude-plugin/plugin.json
{
  "name": "agent-factory",
  "displayName": "Agent Factory",
  "version": "1.32.0",
  "description": "Agent roles, house rules, and repo provisioning commands for turning objectives into shipped code.",
  "author": {
    "name": "chamaya00",
    "url": "https://github.com/chamaya00"
  },
  "homepage": "https://github.com/chamaya00/agent-factory",
  "repository": "https://github.com/chamaya00/agent-factory",
  "license": "MIT",
  "keywords": [
    "agents",
    "orchestration",
    "github",
    "process"
  ]
}

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.

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