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/timurgaleev/memex/setupnpx skills add timurgaleev/memex --skill setupgit clone --depth 1 https://github.com/timurgaleev/memexWhat 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 | $0.00025 | $0.05232 |
| Opus 5 | $0.00013 | $0.02616 |
| Sonnet 5 | $0.00005 | $0.01046 |
| Haiku 4.5 | $0.00003 | $0.00523 |
Grade A, and why
setup 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 — 513 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup memex
Set up memex from scratch. Target: working brain in under 5 minutes on an existing Postgres; under 30 including infrastructure provisioning.
Contract
- Setup completes with a working brain verified by
memex doctor --json(all checks OK). - The brain-first lookup protocol is injected into the project's AGENTS.md or equivalent.
- Live indexing is configured and verified (a test change indexed and found via search).
- Setup choices are tracked on the
tasks/setup-statebrain page so future upgrades know what the user adopted or declined. - No provider API keys are requested; memex uses AWS Bedrock exclusively (Titan for embeddings, Claude Haiku for utility calls, Claude Sonnet for synthesis-tier work), authenticated via IAM.
Install (if not already installed)
Clone the repo on the host, then:
bun install
scripts/init.sh # interactive: secrets prefix, region, connection string
How memex connects
memex connects directly to Postgres over the wire protocol. You need the
database connection string (a postgresql:// URI), not a dashboard URL
or REST key. The password is embedded in the connection string.
The connection string lives in AWS Secrets Manager under
<secrets_prefix>/memex-postgres-url (default prefix: memex). Two gotchas:
- The secret is a parsed URL: a password containing
?#&:=+%must be URL-encoded before upload, or the parse silently mangles it. - Confirm the region: the instance and the RDS endpoint must agree, and Bedrock must be invocable in that region. A mismatched default region is the most common "everything times out" cause.
Do NOT ask for any model-provider API key. memex uses Bedrock via the host's IAM role; there is nothing to paste.
Why managed Postgres
RDS gives you managed Postgres + pgvector (vector search built in):
- No server to manage, automatic backups, snapshots for debugging
- pgvector pre-installed on current engine versions, just works
- Alternative: any Postgres with the pgvector extension (self-hosted, Neon, Railway, etc.) — memex only needs the connection string
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 · 513 lines · 25 tokens per session scan A c0624a3c1fc9
setup is a skill published in the GitHub repository timurgaleev/memex (8 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 5,232 once invoked, about $0.0001 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
wegent-knowledge
Knowledge base management and search tools for Wegent. Provides capabilities to list, create, update, and search knowledge bases and documents using RAG retrieval. Use this skill when the user wants to manage knowledge bases, documents, or search for information programmatically.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, and produces a tight report with concrete findings and numbered follow-up options. Use after adding or modifying definitions, or when the user asks to…