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/memsprout/agents/using-memsproutnpx skills add memsprout/agents --skill using-memsproutgit clone --depth 1 https://github.com/memsprout/agentsWhat 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 | $0.00088 | $0.01021 |
| Opus 5 | $0.00044 | $0.00511 |
| Sonnet 5 | $0.00018 | $0.00204 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
using-memsprout 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 2d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using memsprout
memsprout is the user's persistent knowledge base, reachable as an MCP server. It is shared memory: what you write is read later by the user, by collaborators in shared spaces, and by other AI agents across many tools. They trust it. Write accordingly — it is the user's externalised brain, not a temporary scratchpad.
The one rule
Store memories liberally, and default to giving each one a concise, descriptive title — especially anything durable: a decision, a procedure, a fact, a conclusion worth finding by name later, and anything going into a shared space. A title costs little and buys a lot: it makes a memory individually retrievable, auditable, and readable on its own.
Leave the title off only for genuinely raw, ephemeral personal captures —
a stream-of-consciousness note, a voice memo, a half-formed idea not
meant to stand alone. Raw captures are cheap; no polish needed. You can
promote one later by adding a title via update_memory once it's clear
the memory is worth naming.
Search first
- Call
search_memoriesbefore assuming something isn't recorded, and before storing, so you don't create duplicates. It searches everything you can read by default. - Use
list_memorieswhen you want recency browsing instead of meaning-based lookup.
Workflow
- At the start of a substantive task, search memsprout for relevant prior context.
- When capturing into a space, check
list_topicsfirst and pass the best-fitting topic — don't rely on auto-classification as your first move. - Give most memories a concise, descriptive title as you capture them — especially durable conclusions and anything going into a shared space. This is the default, not an extra step.
- Reserve untitled captures for genuinely raw, ephemeral personal fragments.
- Attach supporting files as assets on the relevant memory.
Be proactive: search at the start of a task and capture durable conclusions at the end — titled, so they're findable later — without waiting to be asked. Treat memsprout as part of how the user thinks, not as an optional tool.
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.
- 2d ago First seen · 102 lines · 88 tokens per session scan A 3822e7d63c29
using-memsprout is a skill published in the GitHub repository memsprout/agents (0 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,021 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…