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 sefodo26/mempalace-server --skill mempalace-zettelkastengit clone --depth 1 https://github.com/sefodo26/mempalace-serverWrote 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/sefodo26/mempalace-server/mempalace-zettelkasten)<a href="https://agentmods.dev/skills/sefodo26/mempalace-server/mempalace-zettelkasten"><img src="https://agentmods.dev/badge/skills/sefodo26/mempalace-server/mempalace-zettelkasten/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/sefodo26/mempalace-server/mempalace-zettelkasten"><img src="https://agentmods.dev/badge/skills/sefodo26/mempalace-server/mempalace-zettelkasten.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 | $0.00079 | $0.01284 |
| Opus 5 | $0.00039 | $0.00642 |
| Sonnet 5 | $0.00016 | $0.00257 |
| Haiku 4.5 | $0.00008 | $0.00128 |
Grade A, and why
mempalace-zettelkasten scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`/mp/api/v1`) with `curl`. Writing needs a **write** key; reading is fine with How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zettelkasten in MemPalace
The Zettelkasten ("slip box") method turns scattered thoughts into a linked web of small, reusable notes. This skill applies it on top of MemPalace so ideas are reformulated in your own words and found again quickly through meaning and links.
The four rules of a good Zettel:
- Atomic — one idea per note. If it needs "and", split it.
- In your own words — reformulate; never paste raw. Writing it forces understanding and makes it searchable by concept, not just keywords.
- Self-contained — readable alone, months later, without the source.
- Linked — every note connects to at least one other note.
How it maps to MemPalace
| Zettelkasten | MemPalace |
|---|---|
| Slip box | one wing, e.g. zettelkasten |
| Topic / cluster | a room, e.g. learning, product-ideas |
| A single note (Zettel) | a drawer |
| Stable note ID | a slug at the top of the drawer, e.g. z-2026-0042-spaced-repetition |
| Link between notes | inline [[z-id]] refs and a mempalace_create_tunnel |
| Index / structure note | a special drawer in room index that lists entry points |
Access
Use MCP tools (mempalace_*) if connected, else the REST API
(/mp/api/v1) with curl. Writing needs a write key; reading is fine with
a read-only key.
Adding a note (the main flow)
-
Catch the raw idea from the user (a sentence, a paragraph, a link).
-
Search first — always. Run
mempalace_searchwith the idea's core concept before writing. This does two jobs:- finds notes to link to,
- reveals if the idea already exists (then extend/refine that note instead of duplicating it).
-
Reformulate atomically. Rewrite the idea in clear, plain words as a standalone claim. One idea only. If you find two, make two notes.
-
Give it a stable ID and title. Use a slug like
z-<YYYY>-<NNNN>-<short-title>. Keep the ID forever, even if you edit the text — links depend on it. Ask the user for the next free number, or derive one (e.g. count existing notes + 1).
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.
- 11d ago First seen · 112 lines · 79 tokens per session scan A cd09b9f6f268
mempalace-zettelkasten is a skill published in the GitHub repository sefodo26/mempalace-server (2 stars, last pushed 13d ago), licensed MIT. It adds 79 tokens to every session and 1,284 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.