C

Contorium

Runtime continuity layer for AI coding agents, providing persistent workspace state, Git-aware sessions, and MCP-based context retrieval across tools and agent runs

contoriumlabs/contorium · v1.3.1 · Development & Workflow

ContoriumLabssafe
InstallSourceClaim this plugin
81Follow0

Trust Score

81

Security

100

Surfaces

2

What is Contorium?

Contorium is a published development & workflow plugin for AI coding agents in the codex ecosystem, developed by ContoriumLabs and distributed through the HOL AI plugin registry. Runtime continuity layer for AI coding agents, providing persistent workspace state, Git-aware sessions, and MCP-based context retrieval across tools and agent runs

Canonical slug
contoriumlabs/contorium
Version
v1.3.1 · updated Sep 15, 2026

Trust & Reputation

HOL Trust Score
81

Factor Analysis

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100pts
Maintenance
75pts
MCP Posture
100pts

Registry Snapshot

Publisher verification
No
Marketplace source
Unknown
Scanner
Broker fallback
Safety label
safe
Digest verified
Yes
1 bundled skill — copy or download SKILL.mdOpen skills

Trust & reputation

Trust & Reputation

HOL Trust Score
81

Factor Analysis

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100pts
Maintenance
75pts
MCP Posture
100pts
Plugin Security
100pts
Provenance
70pts
Publisher Quality
75pts

Provenance

Plugin root
.
Source repo
https://github.com/ContoriumLabs/contorium
Source commit
d5949d7c91d8…
Publisher verified
No
Owner verified
Not owner verified

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

Verified badge not detected

Add the HOL verified badge to the repository README to score +2% trust. Plugin owners can open that pull request from Guard Plugins.

Security Posture

safe
Safety label
100
Security score
0
High findings
Provider
registry-broker-fallback
Grade
A · safe
Version
Unknown
cisco-skill-scanner: unknown

Findings

infoskill-securityskill-scan.unavailable

Cisco skill scanner exited with code 1: Error loading skill: No SKILL.md and no .md files found in /var/folders/9z/48v7m0s52llddzmskkyjbdl80000gn/T/hol-skill-safety-Keahyp (lenient mode requires at least one markdown file)

Contorium — Frequently asked questions

What is Contorium?
Contorium is an AI plugin in the HOL registry. Runtime continuity layer for AI coding agents, providing persistent workspace state, Git-aware sessions, and MCP-based context retrieval across tools and agent runs
How do I install Contorium?
Install Contorium in your harness: Codex — codex plugin marketplace add ContoriumLabs/contorium; Claude Code — /plugin marketplace add ContoriumLabs/contorium; Cursor — npx skills add ContoriumLabs/contorium. Full step-by-step guidance is on the HOL plugin page.
How do I install Contorium in Codex?
To install Contorium in Codex, start with codex plugin marketplace add ContoriumLabs/contorium. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install Contorium in Claude Code?
To install Contorium in Claude Code, start with /plugin marketplace add ContoriumLabs/contorium. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install Contorium in Cursor?
To install Contorium in Cursor, start with npx skills add ContoriumLabs/contorium. The complete step-by-step install guide for Cursor is on the HOL plugin page.
Is Contorium free?
Pricing for Contorium is published on its HOL plugin page when the maker schedules a launch.
Who publishes Contorium?
Contorium is published by ContoriumLabs and listed on HOL.
Is Contorium available now?
Contorium availability is listed on its HOL plugin page.

Install Guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs
  1. 1

    Add the marketplace

    Run this inside a Claude Code session.

    claude code
  2. 2

    Install the plugin

    Use the plugin name and the marketplace name shown by the previous command.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell

Plugin Manifest

{
  "name": "contorium",
  "version": "1.3.1",
  "description": "Contorium: AI Project Intelligence Layer — preserve and retrieve project cognition across Codex sessions via MCP.",
  "author": {
    "name": "ContoriumLabs",
    "url": "https://github.com/ContoriumLabs"
  },
  "homepage": "https://github.com/ContoriumLabs/contorium#readme",
  "repository": "https://github.com/ContoriumLabs/contorium",
  "license": "MIT",
  "keywords": [
    "workspace",
    "memory",
    "context",
    "mcp",
    "codex",
    "ai-coding"
  ],
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "interface": {
    "displayName": "Contorium",
    "developerName": "ContoriumLabs",
    "shortDescription": "AI Project Intelligence Layer for Codex",
    "longDescription": "Contorium captures, structures, and preserves project intelligence (STATE, INTENT, DECISION, WHY) locally. Query via MCP inspect tools — Contorium records intelligence; it does not decide for the project.",
    "category": "Developer Tools",
    "capabilities": [
      "Read",
      "Write"
    ],
    "websiteURL": "https://github.com/ContoriumLabs/contorium",
    "privacyPolicyURL": "https://github.com/ContoriumLabs/contorium#readme",
    "termsOfServiceURL": "https://github.com/ContoriumLabs/contorium/blob/main/LICENSE",
    "defaultPrompt": [
      "Recall my workspace focus and active files.",
      "Store a design decision in Contorium memory.",
      "Summarize Git and session context before we continue."
    ],
    "brandColor": "#2563EB",
    "composerIcon": "./assets/logo.png",
    "logo": "./assets/logo.png"
  },
  "registryIndexVersion": 5
}

Marketplace Source

Repo URL
https://github.com/ContoriumLabs/contorium
Marketplace path
Unknown
Source path
.
Install policy
Unspecified

Skills

Copy or download the SKILL.md files this plugin ships, then install them with the Skills CLI.

Share
skills-cli

contorium-workspace-memory

skills/contorium-workspace-memory/SKILL.md

Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.

Raw SKILL.md
---
name: contorium-workspace-memory
description: Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.
---

# Contorium workspace memory

## When to use

- Starting a new chat or switching models mid-task
- User asks to continue where they left off
- Exporting compact, AI-ready project context
- Detecting session pollution after a task change

## Memory layers

| Layer | Source | Lifetime |
|-------|--------|----------|
| Workspace | `.contora/state.json` (focus, files, Git, notes) | Long |
| Session | in-memory events + optional JSONL per `sessionId` | Short |
| Cognitive | `.contora/last-intent.json` (BYOK intent + lifecycle) | Medium |

## Instructions

1. Prefer **Current focus** (optional) for user intent; never block export if empty.
2. For clipboard handoff, use **Copy AI-ready context** — not raw event dumps.
3. If focus and active files diverge sharply, suggest **Start fresh AI context session**.
4. When AI intent is stale (low confidence), rely on heuristic operational intent from recent edits.
5. Respect ignore rules (`.contoraignore`, `contora.extraIgnoreSubstrings`) when reasoning about ranked files.

## MCP tools (Codex / Claude Code / Cursor Agent)

When the Contorium MCP server is connected (`npm run build:mcp`, see `docs/MCP.md`):

- `get_workspace_context` — read extension snapshot from `.contora/state.json`
- `store_memory` / `search_memory` / `get_memory` — agent-persisted notes under `.contora/mcp/memories.json`

Use MCP for agent-driven recall; use extension commands for sidebar UI and clipboard export.

- `contora.exportAIContext` — copy AI-ready context
- `contora.startFreshAiSession` — reset session activity + intent pool
- `contora.analyzeWorkspaceIntent` — BYOK intent snapshot
- `contora.saveStateNow` / `contora.restoreSession` — persist or restore editors

File Inventory

.codex-plugin/plugin.json

plugin-manifest

1,412 bytes

04c531f4d0313fca…

.claude-plugin/plugin.json

file

595 bytes

6936bcda03438171…

README.md

file

12,103 bytes

7056253119e7f21a…

package-lock.json

file

5,645 bytes

91a08407e1fcd696…

package.json

file

9,374 bytes

b43ed8c0f2b2a529…

.cursor-plugin/plugin.json

file

839 bytes

ee943ff78dce1fe0…

tsconfig.json

file

529 bytes

51b57f249d76c1a4…

.mcp.json

file

208 bytes

6c0f90af218eb247…

skills/contorium-workspace-memory/SKILL.md

skill

1,914 bytes

4092831472931804…

commands/copy-ai-context.md

file

1,376 bytes

7b6f07328b38e196…

commands/setup-mcp-claude-code.md

file

676 bytes

f6fd2382b88c53af…

commands/start-fresh-session.md

file

680 bytes

5c57d57c4062eb34…

commands/learn-workspace-intent.md

file

582 bytes

686a00ca30a1bf86…

commands/setup-mcp-codex.md

file

1,186 bytes

a7891947fce466d2…

.registry/mcp.json

mcp-config

147 bytes

adde593533d3b536…

assets/logo.png

asset

6,108 bytes

cb742bf2d1ababd4…