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/vertiso/memory-vscode/handoffnpx skills add Vertiso/memory-vscode --skill handoffgit clone --depth 1 https://github.com/Vertiso/memory-vscodeWhat 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 | $0.00073 | $0.01067 |
| Opus 5 | $0.00036 | $0.00534 |
| Sonnet 5 | $0.00015 | $0.00213 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
handoff 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handoff
Write a structured session handoff so the work can be picked up cleanly — in this tool or another, now or later.
Announce: "Using the handoff skill to save selected session context to Vertiso Memory."
Consent boundary
Invoking this skill at the user's request, or affirmatively accepting an agent's offer to run it, authorizes one capture. That capture may inspect the current conversation and a client-exposed session transcript for exact quotations, then send selected context and attributed verbatim excerpts to Vertiso Memory as a claimable handoff. Once invoked, do not ask a second permission question before performing the transcript-backed handoff write.
One invocation does not grant standing authorization for later handoffs. Omit and do not persist passwords, API keys, authentication tokens, payment information, illegal or illicit materials, or sensitive third-party information the user is not authorized to store.
Secret stripping
Before composing the memory, inspect every selected source, including the conversation, transcript, work artifacts, tool output, title, tags, and metadata, for secrets. Treat passwords, API keys, bearer or refresh tokens, OAuth codes, session cookies, private keys, recovery codes, and credentialed connection strings as secrets.
Strip or redact any detected value before composing the memory. Never send the original value to Vertiso Memory or copy it into a quote, title, tag, metadata, link, or error detail. Do not echo the secret in the report; state only that sensitive content was omitted. If sanitization would make the capture meaningless, stop and ask the user for a sanitized replacement.
When to use
- The user runs
/handoff. - The user asks for a handoff or affirmatively accepts an agent's offer.
- A session ending, a tool or device switch, or approaching compaction is a reason to offer a handoff, not authorization to run it. Wait for the user's approval.
Procedure
- Gather the past context via the checkpoint skill. Follow the
checkpointskill's Procedure steps 1-2 — gather authoritative state from the workstream's own artifacts (checkpoint's gather step has the domain palette: code / writing / product / design / hardware / ops — not git by default) and retrospective-sweep the whole span for the attributed verbatim decisions (who said what). This gathered context FILLS handoff's "What happened" and "Where it stands" slots verbatim — carry checkpoint's attributed quotes and detailed snapshot across intact, do not summarize them. It does not replace handoff's body. Do NOT invoke the checkpoint skill itself (that writes a checkpoint memory) — reuse its gather + sweep. - Compose handoff's own body (below), building the forward slots — Next, Open questions, Verify — ON TOP of that gathered context. Distinguish what was done from what was told or believed; record an approval or decision only if witnessed this session, dated and attributed.
- Call the
handoffverb — thehandoffMCP tool, orvmem handoff— with the composed body and an agent-suppliedscope(a git branch for a coding session, a project name, or none). This is handoff's terminal act: it writes the record AND marks it claimable sohandoff_resumecan pick it up. - Report the new handoff id to the user.
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.
- yesterday First seen · 86 lines · 73 tokens per session scan A 9914d2d4f4b8
handoff is a skill published in the GitHub repository Vertiso/memory-vscode (0 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 1,067 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…