Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ContoriumLabs/contorium --skill contorium-workspace-memorygit clone --depth 1 https://github.com/ContoriumLabs/contoriumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/contoriumlabs/contorium/contorium-workspace-memory)<a href="https://agentmods.dev/skills/contoriumlabs/contorium/contorium-workspace-memory"><img src="https://agentmods.dev/badge/skills/contoriumlabs/contorium/contorium-workspace-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/contoriumlabs/contorium/contorium-workspace-memory"><img src="https://agentmods.dev/badge/skills/contoriumlabs/contorium/contorium-workspace-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.00447 |
| Opus 5 | $0.00016 | $0.00224 |
| Sonnet 5 | $0.00007 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
contorium-workspace-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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
- Prefer Current focus (optional) for user intent; never block export if empty.
- For clipboard handoff, use Copy AI-ready context — not raw event dumps.
- If focus and active files diverge sharply, suggest Start fresh AI context session.
- When AI intent is stale (low confidence), rely on heuristic operational intent from recent edits.
- 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.jsonstore_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 contextcontora.startFreshAiSession— reset session activity + intent poolcontora.analyzeWorkspaceIntent— BYOK intent snapshotcontora.saveStateNow/contora.restoreSession— persist or restore editors
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 44 lines · 33 tokens per session scan A 409283147293
contorium-workspace-memory is a skill published in the GitHub repository ContoriumLabs/contorium (6 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 447 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
commit
Creates conventional git commits enriched with a Context section that logs AI-layer changes (.wisci/, CLAUDE.md, skills, rules), turning git history into queryable long-term memory. Use to commit changes, optionally pushing afterward.
write
Externalizes knowledge from the conversation into persistent, staleness-tracked markdown files under .wisci/context/. Use when research results, decisions, or findings are worth keeping beyond this session, or when the user wants context saved to disk.
neo4j-agent-memory-skill
Authoritative reference for the neo4j-agent-memory Python package — a graph-native memory system for AI agents built on Neo4j — and for the hosted service (NAMS) at memory.neo4jlabs.com. Use this skill whenever the user mentions neo4j-agent-memory, agent memory with Neo4j, context graphs, the POLE+O model…
context-degradation
Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash.
context-compression
Design and evaluate compression strategies for long-running sessions.
context-optimization
Apply compaction, masking, and caching strategies.