Agent Plugins Marketplace
← All plugins

ai-baton

v0.3.1

Environment-portable Claude Code kit: capability-gated skills and agents, an env fact store, a markdown context DB with a session registry, and a self-audit — one skill set for every machine.

Claude Code7 Skills

By ai-baton maintainers0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
7 skill or MCP entries
Source updated
Sep 27, 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 ai-baton 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 ai-baton@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/MdaaaaO/ai-baton

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

Plugin files

ai-baton/
├── .claude-plugin/plugin.json
├── skills/notion-page-review/SKILL.md
├── skills/pr-event-brief/SKILL.md
├── skills/repo-docs/SKILL.md
├── skills/self-assessment/SKILL.md
├── skills/session-register/SKILL.md
├── skills/ticket-close/SKILL.md
└── skills/ticket-open/SKILL.md

Included Skills7

notion-page-reviewskills/notion-page-review/SKILL.md

Review a Notion page tree (page, sub-pages, every comment thread) against the user's position, walk each proposed comment with them (Comment, Update wording, Skip, batches of 4), and post only the approved ones as thread replies or anchored inline comments. Invoke when the user asks to "go through", "catch up on" or "comment on" a Notion page with comments.

pr-event-briefskills/pr-event-brief/SKILL.md

Sonnet-forked triage of one pr-watch event — reads the PR's reviews, unresolved threads, checks and mergeability and returns a ≤10-line brief with exactly one recommended ACTION. Invoke for every BOT REVIEW / NEW comment / NEW review / CHECK NOT GREEN line a pr-watch Monitor emits; the main session then performs the action.

repo-docsskills/repo-docs/SKILL.md

Write or restructure a repo's README.md and CONTRIBUTING.md in the house style — badges, a short pitch, code on the first screen, tables over prose, detail linked to docs/ — measured by readme-check.py. Use when a README reads as a wall of text or a repo goes public. Not for docs/ pages or CHANGELOGs.

self-assessmentskills/self-assessment/SKILL.md

Compose the user's weekly self-assessment for a PAST ISO week or range, sourced only from `.context/` and the systems of record, never live sessions. Writes the week file plus the report block and ledger card the env config asks for, back-filling from the systems of record when `.context/` has no coverage. Invoke as "self-assessment for last week" or "for W37".

session-registerskills/session-register/SKILL.md

Register this session in the live registry (`.context/SESSION_INDEX.md`) and keep its heartbeat fresh; each heartbeat refreshes the row's stats line from the transcript. Invoke at the start of any session working an epic/feature, whenever responsibilities change, on every flush, and before ending. Read the registry to see which session owns an epic, PR or worktree.

ticket-closeskills/ticket-close/SKILL.md

Checklist for closing a ticket in the environment's tracker (Jira or GitHub issues) cleanly — a final outcome comment (Delivered / Verified / Out-of-scope), the right transition/resolution or close reason (Done / Won't Do / Cancelled), confirmation the delivering PRs are linked, and the context-doc flush. Invoke when a ticket's work is finished, decided-against, or abandoned.

ticket-openskills/ticket-open/SKILL.md

Checklist every session follows when it CREATES a ticket in the environment's tracker (Jira or GitHub issues) — type/placement (active sprint, or labels + milestone), labels, epic/parent link, a lean opening comment (Goal + Plan + Links), and the matching .context/ context doc. The tracker analogue of pr-open. Invoke right before/after creating the ticket.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "ai-baton",
  "displayName": "Claude Code workspace kit",
  "version": "0.3.1",
  "description": "Environment-portable Claude Code kit: capability-gated skills and agents, an env fact store, a markdown context DB with a session registry, and a self-audit — one skill set for every machine.",
  "author": {
    "name": "ai-baton maintainers",
    "url": "https://github.com/MdaaaaO/ai-baton"
  },
  "homepage": "https://github.com/MdaaaaO/ai-baton",
  "repository": "https://github.com/MdaaaaO/ai-baton",
  "keywords": [
    "workspace",
    "skills",
    "env-facts",
    "context-db",
    "session-registry",
    "kit-health"
  ],
  "experimental": {
    "evals": "evals"
  },
  "userConfig": {
    "user_name": {
      "type": "string",
      "title": "Your name",
      "description": "How skills address and stamp you (WORKSPACE_USER): sign-queue --by, the self-assessment ledger eyebrow. Never written into the kit.",
      "required": true
    },
    "github_login": {
      "type": "string",
      "title": "GitHub login",
      "description": "Your GitHub login (WORKSPACE_GITHUB_LOGIN): pr-watch drops your own events, cost-report and self-assessment query author:<login>.",
      "required": true
    },
    "tz": {
      "type": "string",
      "title": "Timezone (IANA)",
      "description": "The zone timestamps render in (WORKSPACE_TZ): an IANA Region/City name, not an abbreviation like EDT. UTC when empty or unknown.",
      "default": "UTC"
    },
    "slack_self_dm": {
      "type": "string",
      "title": "Chat self-DM channel id",
      "description": "Your own chat DM channel id (WORKSPACE_SLACK_SELF_DM), where a draft skill parks text for you. Optional; needs systems.slack in the env store.",
      "sensitive": true
    },
    "slack_lattice_dm": {
      "type": "string",
      "title": "Performance-review bot DM channel id",
      "description": "The chat DM your performance-review tool's bot posts in (WORKSPACE_SLACK_LATTICE_DM), read by the self-assessment skill. Optional; needs systems.slack in the env store.",
      "sensitive": true
    }
  }
}

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.

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