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/ibrain-bvba/gutt-claude-code-plugin/migrate-memorynpx skills add iBrain-BVBA/gutt-claude-code-plugin --skill migrate-memorygit clone --depth 1 https://github.com/iBrain-BVBA/gutt-claude-code-pluginWrote 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/ibrain-bvba/gutt-claude-code-plugin/migrate-memory)<a href="https://agentmods.dev/skills/ibrain-bvba/gutt-claude-code-plugin/migrate-memory"><img src="https://agentmods.dev/badge/skills/ibrain-bvba/gutt-claude-code-plugin/migrate-memory.svg" alt="Measured on agentmods" 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 | $0.00123 | $0.04229 |
| Opus 5 | $0.00062 | $0.02115 |
| Sonnet 5 | $0.00025 | $0.00846 |
| Haiku 4.5 | $0.00012 | $0.00423 |
Grade A, and why
migrate-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 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate built-in memory into gutt
Claude Code keeps its own file-based memory store per project. Where it is non-empty, that is organizational knowledge sitting outside the graph — invisible to teammates, to every other project on the machine, and to gutt search. This skill moves it across exactly once, and is the only place in the plugin that deletes a user's memory files.
It builds on memory-capture (how to write), memory-search (how to dedup and
verify) and conflict-adjudication (what to do when a local note and the graph
disagree) rather than restating them. Migration does not get its own dedup or
conflict rules — it is a bulk caller of those skills, and a store is the largest
batch of writes the plugin ever makes. Read this file's rules first; they are
stricter than the general ones because the local copy is destroyed at the end.
Hard rules (non-negotiable — read first)
- Ask before anything. Use AskUserQuestion for consent and for scope before the first write. The session-start offer also asks with AskUserQuestion, so arriving here usually means consent to run is already given — that answer covers starting the skill, not the writes. Scope is still unasked, and so is anything you only discovered by reading the files. Where you got here some other way (the user named the skill, or the offer was answered in prose), treat consent as unasked: an offer is not an answer.
- Back up before you write, verify before you delete. The order is
fixed: back up → write episodes → search to confirm they landed → record the
confirmations → delete.
memory-capturerule 6: a write is queued, not confirmed, so a success response is not evidence. Never delete on a 200. - Deletion is the script's job, not yours. Do not
rmanything and do not use Write/Edit on the store.store-cli.cjs deleteremoves only files with a recorded verification, which is what makes an unlanded write cost nothing. - Record the answer, including "no". Every terminal answer is persisted per project. A decline must never be re-asked; a completed migration must never be re-offered.
- Degrade by stopping. No write tool visible, or MCP unreachable → write nothing, delete nothing, say so in one line, and leave the decision unset so the offer returns next session. A partial migration is worse than none.
- Default to the org group; screen for what must stay personal. Visibility to teammates is the whole point of migrating, so the group is the default. But publishing is the one failure here that restoring a file cannot undo, so read every fact before it goes: anything sensitive — a credential, PII, a note about a named person, or personal preference data — goes to personal scope regardless of what the user picked for the batch.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 294 lines · 123 tokens per session scan A 6690c1b763fc
migrate-memory is a skill published in the GitHub repository iBrain-BVBA/gutt-claude-code-plugin (4 stars, last pushed 13d ago), licensed MIT. It adds 123 tokens to every session and 4,229 once invoked, about $0.0006 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…