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 jvanderberg/wikimemory --skill wikimemory-installgit clone --depth 1 https://github.com/jvanderberg/wikimemoryWrote 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/jvanderberg/wikimemory/wikimemory-install)<a href="https://agentmods.dev/skills/jvanderberg/wikimemory/wikimemory-install"><img src="https://agentmods.dev/badge/skills/jvanderberg/wikimemory/wikimemory-install.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 5.1 | $0.00044 | $0.01023 |
| Opus 5 | $0.00022 | $0.00511 |
| Sonnet 5 | $0.00009 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
wikimemory-install 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 7d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install Wikimemory
Determine whether the user wants to connect to an existing instance or deploy a new one. Read the repository installation documentation before changing configuration because supported commands and prerequisites may evolve.
Connect a client
- Require an HTTPS base URL from the user and normalize the endpoint to
/mcp. - Add it as a remote HTTP MCP server using the current Codex CLI or Claude Code command documented in
docs/installation.md. - Let the user complete the browser passkey flow. Never request passkey data, setup tokens, or bearer tokens in chat.
- Verify connection with
orient, then a narrowrecallquery. - Install or expose the recall, ingest, and lint skills using the client-specific paths in the installation guide.
If browser approval succeeds but the active conversation remains unauthenticated,
do not repeat approval indefinitely. The host may retain the connector session it
opened before login. Start a new conversation or restart the CLI; if needed, use the
documented mcp logout then mcp login sequence and verify orient from a fresh
conversation. The Worker cannot refresh client-owned in-memory connector state.
For Claude on phone, configure the same HTTPS endpoint as a custom connector in Claude's web settings.
Deploy a new instance
- Confirm the user controls a Cloudflare account. Deployment changes external state, so show the exact target account, Worker name, D1 database name, and KV namespace before applying it.
- Run
npx wikimemory install. Use--deployment NAMEfor a non-default installation. Do not reimplement provisioning steps ad hoc. - Stop after the installer prints the one-time URL. The human must open it and create the owner passkey; never open, copy, or retain that URL for them.
- After the user confirms passkey setup, verify protected-resource metadata, OAuth login, and an authenticated
orientcall. - Do not enable local fixture identity in production. Never print, commit, or persist setup material outside the installer's one-time handoff and Cloudflare's secret store.
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.
- 7d ago First seen · 77 lines · 44 tokens per session scan A e8bd3b7dacba
wikimemory-install is a skill published in the GitHub repository jvanderberg/wikimemory (1 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,023 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 2026-08-31.
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.