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/maintainnpx skills add timurgaleev/memex --skill maintaingit 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 | $0.00044 | $0.03682 |
| Opus 5 | $0.00022 | $0.01841 |
| Sonnet 5 | $0.00009 | $0.00736 |
| Haiku 4.5 | $0.00004 | $0.00368 |
Grade A, and why
maintain 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 3d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Skill
Periodic brain health checks and cleanup.
Contract
This skill guarantees:
- All health dimensions are checked (stale, orphan, dead links, cross-refs, backlinks, citations, filing, tags)
- Each issue found has a specific fix action
- Back-link iron law is enforced
- Citation format is validated against the standard
- Results are reported with counts per dimension
Phases
Autonomous path — when you want the brain fixed, not audited
If the user asks "fix what's broken" or "get my brain healthy", prefer the server's own machinery over walking each dimension by hand:
memex doctor # categorized report: brain / ops / meta findings
memex cycle # run the full background maintenance cycle now
run_doctor (or memex doctor from the shell) reports every dimension with a
cause-ranked, root-first list — fix the root causes first, the downstream
findings usually clear themselves. The background cycle already remediates
most mechanical dimensions on its own schedule: embedding backfill, link
derivation, decay, salience, chronicle. For heavy one-off work (bulk
re-embedding, large backfills), submit a durable job with jobs_submit and
watch it with jobs_get / jobs_logs rather than blocking the conversation.
When a target is unreachable for the brain (an empty brain with no entity pages cannot have graph coverage; a brain with no embeddings configured cannot have vector freshness), report what's missing rather than looping.
Use the per-dimension walk below when:
- The user explicitly asks for a dimension-by-dimension audit
- You're investigating why doctor keeps reporting the same finding
- A specific dimension needs manual judgment that the automatic path skips
Manual path
- Run health check. Call
run_doctorandstatsto get the dashboard. - Check each dimension:
Stale pages
Pages where compiled_truth is older than the latest timeline entry. The assessment hasn't been updated to reflect recent evidence.
- Check the doctor output for stale page findings
- For each stale page:
page_getit, review the timeline, determine if compiled_truth needs rewriting
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.
- 3d ago First seen · 397 lines · 44 tokens per session scan A f943a0dba9b3
maintain is a skill published in the GitHub repository timurgaleev/memex (8 stars, last pushed 8d ago), licensed MIT. It adds 44 tokens to every session and 3,682 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
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.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
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…