Agent Plugins Marketplace
All plugins

trellis

v0.0.3

Local kanban boards and vaults for AI agents: board state at session start, cards with expiring claims, and a linked markdown vault.

CodexClaude Code6 Skills

By mtchenLicense: MIT0 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
6 skill or MCP entries
Source updated
Sep 17, 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 trellis for Codex and 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 trellis-2@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.

Compatibility: the page URL and API slug “trellis-2” remain stable.

  • Codex: Legacy selector trellis-2@agent-plugin-marketplace remains documented for migration; install from source for this runtime.

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.

Codex has another source with the same manifest name. This directory does not invent numbered install aliases; use the publisher's catalog or inspect the source manually for that runtime.

Get the source manually
git clone https://github.com/mtch3n/trellis

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

Plugin files

plugin/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/coordinating/SKILL.md
├── skills/keeping-glossary/SKILL.md
├── skills/trellis/SKILL.md
├── skills/using-glossary/SKILL.md
├── skills/when-to-use-trellis/SKILL.md
└── skills/writing-knowledge/SKILL.md

Included Skills6

coordinatingskills/coordinating/SKILL.md

Use when another actor has claimed a Trellis card, when several agents or sessions work one board at the same time, or when deciding whether a quiet claim may be stolen. Covers reading the claimant's state, when stealing is justified, and keeping parallel workers from overwriting each other. Commands are in trellis:trellis.

keeping-glossaryskills/keeping-glossary/SKILL.md

Use when a Trellis project needs a glossary or its glossary must change - the user says what a word means or that one word replaces another, something new needs a name the glossary lacks, a term is retired, or the user asks for a glossary. Commands are in trellis:trellis.

trellisskills/trellis/SKILL.md

How to operate the Trellis CLI - session identity, the command for every noun, output and exit-code contract, claims, and optimistic-concurrency rules. Use when running any trellis command. Whether work belongs on the board is decided by trellis:when-to-use-trellis.

using-glossaryskills/using-glossary/SKILL.md

Use before naming anything other people or agents will see in a Trellis project - a command, flag, field, table, UI label, help string, card or entry title - including when the user dictates the name, and when the user uses a term you do not recognise or that could mean two things. Commands are in trellis:trellis.

when-to-use-trellisskills/when-to-use-trellis/SKILL.md

Use when deciding whether work belongs on a Trellis board - starting a task with three or more steps, ending a session with work unfinished, about to clear or compact context mid-task, resuming a repository after a gap, or carrying a finding that the next session would otherwise re-derive. Decides whether to reach for Trellis and authorizes writing to the board. How to run the commands is in trellis:trellis.

writing-knowledgeskills/writing-knowledge/SKILL.md

Use when deciding whether a finding is worth recording and where it belongs - after debugging something non-obvious, when a measurement or decision would otherwise be re-derived, when an approach failed and the reason matters, or when the user says to write something down. Covers what each template asks for and when a card comment or project memory is the better home instead.

Plugin manifests2

plugin/.codex-plugin/plugin.json
{
  "name": "trellis",
  "version": "0.0.3",
  "description": "Local kanban boards and vaults for AI agents: board state at session start, cards with expiring claims, and a linked markdown vault.",
  "author": {
    "name": "mtchen"
  },
  "license": "MIT",
  "keywords": [
    "kanban",
    "board",
    "vault",
    "agent",
    "work"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Trellis",
    "shortDescription": "Local kanban boards and vaults for AI agents",
    "longDescription": "Trellis gives AI coding agents a local kanban board and a linked markdown vault. Use it to claim work safely, record progress, preserve what it learns, and recover context across sessions.",
    "developerName": "mtchen",
    "category": "Productivity",
    "capabilities": [
      "Interactive",
      "Write"
    ],
    "defaultPrompt": [
      "Show my Trellis work and blockers.",
      "Claim the next available Trellis card.",
      "Save what this session verified in Trellis."
    ]
  }
}
plugin/.claude-plugin/plugin.json
{
  "name": "trellis",
  "version": "0.0.3",
  "description": "Local kanban boards and vaults for AI agents: board state at session start, cards with expiring claims, and a linked markdown vault.",
  "author": {
    "name": "mtchen"
  },
  "license": "MIT",
  "keywords": [
    "kanban",
    "board",
    "vault",
    "agent",
    "work"
  ]
}

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

[trellis on Agent Plugins Marketplace](https://pluginsmp.com/plugins/trellis-2)