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.
git clone --depth 1 https://github.com/aristoapp/claude-membaseWrote 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/commands/aristoapp/claude-membase/login)<a href="https://agentmods.dev/commands/aristoapp/claude-membase/login"><img src="https://agentmods.dev/badge/commands/aristoapp/claude-membase/login/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/commands/aristoapp/claude-membase/login"><img src="https://agentmods.dev/badge/commands/aristoapp/claude-membase/login.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 | $0.00015 | $0.00178 |
| Opus 5.5 | $0.00006 | $0.00071 |
| Sonnet 5.5 | $0.00003 | $0.00036 |
| Haiku 4.5 | $0.00002 | $0.00018 |
Grade A, and why
login 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 1mo 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.
What it actually says
Ask the user to choose an auto-capture mode before connecting:
wiki: enable Wiki auto-capture for user/assistant conversation transcripts.off: disable automatic transcript capture. Explicit saves through memory and wiki tools still work.
Then call the Membase MCP login tool with the chosen capture_mode.
This opens a browser for OAuth. After login completes, show the returned safe account fields and tell the user to verify the connected account before storing data.
If the result includes account_switched: true or a
stale_session_context_warning, explain that earlier Membase context in this
Claude Code session may still refer to the previous account. Recommend /clear
or a new Claude Code session before using memory/wiki after an account switch.
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.
- 1mo ago First seen · 21 lines · 15 tokens per session scan A d46cc448b0c7
login is a command published in the GitHub repository aristoapp/claude-membase (3 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 178 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
ai-act-ask
Answer an EU AI Act question grounded in the bundled knowledge base — verbatim statute text, obligation paraphrases, and the compound-risk taxonomy. Offline and deterministic by default; cites the articles it relies on.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.
check
Is the context layer still true? 0-token staleness + broken-citation audit (no LLM, CI-friendly). Add --status for the fast hash-only subset.
quarry
Manage your quarry knowledge base.