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 timurgaleev/memex --skill maintaingit clone --depth 1 https://github.com/timurgaleev/memexWrote 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/timurgaleev/memex/maintain)<a href="https://agentmods.dev/skills/timurgaleev/memex/maintain"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/maintain/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/timurgaleev/memex/maintain"><img src="https://agentmods.dev/badge/skills/timurgaleev/memex/maintain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 344 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 349 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 244 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 305 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 336 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.03682 |
| Opus 5.5 | $0.00018 | $0.01473 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 397 lines · 44 tokens per session scan A f943a0dba9b3
maintain is a skill published in the GitHub repository timurgaleev/memex (11 stars, last pushed 29d ago), licensed MIT. It adds 44 tokens to every session and 3,682 once invoked, about $0.0002 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 skills, from other repositories
memory
Use this skill when Pioneer should proactively use durable memory or recalled context: decide whether memory can improve a turn, answer from remembered user/project facts, request memory tools, search/list/get stored memories, save durable preferences or project decisions, forget memories, audit or clean up memory, or…
weasley-deepmind
A reference for using weasley-deepmind, a server that stores and retrieves an AI agent’s long-term memories between sessions. It describes memory storage, search, language processing, and related tools.
thebrain-ingest
Lay material into TheBrain as a connected graph rather than a pile of notes. Use when asked to "put this article in my brain", "save this", "add it to the knowledge base", "break this down and record it" — about an article, a document, a discussion, a research result or the user's own thinking. Covers: how finely to…
thebrain-organize
Tidy up TheBrain: find duplicates, thoughts with no links, empty stubs, scattered branches about the same thing. Use when asked to "clean up my brain", "find duplicates", "what is dangling with no links", "sort this out", "the structure has drifted". Covers: how to hunt for disorder, what you may fix yourself, and…
thebrain-digest
Report what happened in the brain over a period, and what deserves going back to. Use when asked "what did I add this week", "show me a digest", "what have I been working on", "what is new in the brain", and at the start of a session when the context of previous work needs recalling. Covers: how to read the…
thebrain-research
Use TheBrain as a knowledge base when answering a question: look at what is already known first, and only then reason. Use when asked "what do I know about X", "what do I have on this topic", "have we discussed this already", "remind me what we concluded", and before any substantive answer on a topic that might be in…