om
v0.1.0Operational Memory skills for Claude Code — propose-only fact capture, read-only readiness / staff-answer, and client handover. Requires a Knowledge Layer MCP backend (contract schemas live in <your-om-contracts-repo>/contracts/operational-memory/).
By Manolii0 GitHub starsUpdated 1 hour ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Oct 1, 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 om for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install om@agent-plugin-marketplacePaste 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/Manolii-org/ai-starter-packClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is registry/platform/om/.
Plugin files
├── .claude-plugin/plugin.json├── skills/om-fact-capture/SKILL.md├── skills/om-handover/SKILL.md├── skills/om-readiness/SKILL.md└── skills/om-staff-answer/SKILL.md
Included Skills4
Reviewed fact capture for Operational Memory: extract candidate knowledge items from a source packet or approved evidence bundle, preserve citations, classify sensitivity, detect duplicates/conflicts, and produce a PROPOSED change set. Never publishes directly.
Compile a client handover pack for an Operational Memory deployment: module manifest, source registry export, object schemas, capability profile, evaluation results, deployment assumptions, export manifest, recovery instructions, ownership boundaries, known limitations, unresolved decisions.
Read-only Operational Memory readiness report for a deployment: source-registry coverage, review/sensitivity gaps, available reviewed knowledge, conflicts, freshness risks, blockers to safe staff use, and the recommended next change set. Includes the stale/conflicting-knowledge review queue.
Cited internal staff answer from reviewed Operational Memory only. States when it does not know, cites reviewed sources, distinguishes evidence from inference, follows escalation rules, refuses restricted content, never sends messages, never changes operational systems. Also compiles per-subject property fact packs.
Plugin manifests1
{
"name": "om",
"description": "Operational Memory skills for Claude Code — propose-only fact capture, read-only readiness / staff-answer, and client handover. Requires a Knowledge Layer MCP backend (contract schemas live in <your-om-contracts-repo>/contracts/operational-memory/).",
"version": "0.1.0",
"author": {
"name": "Manolii",
"url": "https://github.com/manolii-org"
}
}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.
[om on Agent Plugins Marketplace](https://pluginsmp.com/plugins/om)