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 agentmods add skills/yonro/memory-os-cli/xmemo-vscodenpx skills add yonro/memory-os-cli --skill xmemo-vscodegit clone --depth 1 https://github.com/yonro/memory-os-cliWhat 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 | $0.00045 | $0.00427 |
| Opus 5 | $0.00023 | $0.00214 |
| Sonnet 5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
xmemo-vscode 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 3d 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
XMemo for VS Code
Use this skill when an editor task should use XMemo memory: restore project context, save durable decisions, record working state, or prepare a clean handoff.
Core positioning
Your editor executes development. XMemo lets it remember the project.
XMemo is a user-owned, identity-aware memory layer for multi-agent workflows. It carries useful project context, decisions, preferences, and progress across ChatGPT, Codex, Claude, Cursor, Copilot, Gemini, IDEs, CLIs, and other agents.
Connection
Hosted MCP endpoint: https://xmemo.dev/mcp
The extension authenticates with a token stored in the OS keychain (VS Code SecretStorage) and attributes activity with:
X-Memory-OS-Agent-ID: vscodeX-Memory-OS-Agent-Instance-ID: <local-instance-id>
OAuth 2.0 (PKCE) in-editor sign-in is the default; token paste is a documented fallback for power users.
Memory workflow
At task start: recall focused context for the current repo/subsystem/task; restore a restart snapshot if continuing prior work; fall back to repository evidence if XMemo is unavailable.
During architecture/integration work: capture pending decisions before major tradeoffs; resolve them after implementation or explicit confirmation; save only durable conclusions, not noisy intermediate reasoning.
At handoff: update working state (what changed, what was verified, what remains); create memory TODOs for concrete follow-ups; create a restart snapshot when work is incomplete.
Safety rules
- Never commit tokens, OAuth codes, cookies, or session secrets.
- Treat
X-Memory-OS-Agent-IDand instance ID as non-secret attribution metadata, not authentication. - Keep recall scoped to the user's request.
- Use synthetic memory data for review demos and screenshots.
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.
- 3d ago First seen · 41 lines · 45 tokens per session scan A 7eb858a888ff
xmemo-vscode is a skill published in the GitHub repository yonro/memory-os-cli (12 stars, last pushed 3d ago), licensed MIT. It adds 45 tokens to every session and 427 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 2026-08-30.
Other skills, from other repositories
stickies
Capture and recall persistent sticky notes — decisions, blockers, todos, preferences, and context — that survive across Claude sessions, kept in a local SQLite store (no account, no API key). Use this skill whenever the user wants to remember something for later, jot a note, park a todo or follow-up, record a decision…
lesson
Store a lesson learned from the current conversation. Triggered by /lesson command. Use when Master signals that the recent conversation contains a pitfall, fix, or key insight that should be persisted to long-term memory.
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
chainstack
Work with the Chainstack MCP server to manage blockchain nodes and projects. Use when deploying nodes, migrating to Chainstack from another RPC provider such as QuickNode or Alchemy, checking platform status, searching Chainstack docs, contacting the Chainstack team, or interacting with the Chainstack platform API via…
freshness-check
Model-aware staleness check before asserting how a PoE mechanic/item/system works, plus a scope filter so league/event mechanics don't bleed into the wrong character. Routes to freshnessindex.md + mechanicsindex.md.