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 Markgatcha/memos --skill memos-memorygit clone --depth 1 https://github.com/Markgatcha/memosWrote 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/markgatcha/memos/memos-memory)<a href="https://agentmods.dev/skills/markgatcha/memos/memos-memory"><img src="https://agentmods.dev/badge/skills/markgatcha/memos/memos-memory/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/markgatcha/memos/memos-memory"><img src="https://agentmods.dev/badge/skills/markgatcha/memos/memos-memory.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 | $0.00063 | $0.00614 |
| Opus 5 | $0.00032 | $0.00307 |
| Sonnet 5 | $0.00013 | $0.00123 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
memos-memory 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MemOS persistent memory
MemOS gives you persistent, local-first memory across sessions. Everything stays in a local SQLite database — never send secrets to it (it is a plain file on disk).
When to STORE (memos_store)
Store durable, reusable facts — not chatter. Store when the user:
- states a preference ("always use pnpm, never npm", "I like concise answers")
- makes a project decision ("we chose Postgres over Mongo because of JSONB")
- describes their environment ("Windows 11, RTX 5050 GPU, 16GB RAM")
- corrects something you did ("don't run tests with --watch")
- shares facts about people/projects ("the API base URL is staging.example.com")
Pick a sensible type: preference, fact, context, entity,
relationship. Confirm briefly after storing ("Remembered: …").
Do NOT store: secrets/keys, session-ephemeral details (file contents you already see), task checklists, or anything the user asks you to forget later.
When to RECALL
- Before answering questions like "why did we…", "what did I say about…",
"how do I usually…" → call
memos_context_packwithtokenBudget2000. It returns a token-budgeted, relevance-ranked slice ready to use. - For raw exploration →
memos_search(limit 10). - When the exact wording may have changed over time (renamed services,
moved URLs) →
memos_search_temporalwith a pastatTimeto see what was true then.
Keeping memory clean
- Outdated fact? Store the corrected version, then
memos_supersedethe old one (optionally passing the new memory id asreplacementId). Historical versions stay queryable viamemos_search_temporal. - Contradiction check: if a new fact conflicts with search results, surface the conflict to the user instead of silently storing both.
- If tools feel slow or results look lexical-only, call
memos_diagnostics: lownodesWithEmbeddingscoverage means the embedding provider is not configured (setMEMOS_EMBEDDING_*env vars, or runmemos reindex-embeddings --purge-staleafter switching models).
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 · 54 lines · 63 tokens per session scan A 796c509c5811
memos-memory is a skill published in the GitHub repository Markgatcha/memos (6 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 614 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
self_reflection
Periodically review memory for contradictions, gaps, stale information, and controlled improvement proposals.
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
brain_dump
Capture unstructured thoughts and organize them into structured notes saved to memory.
wiki_guide
Guidance for the Obsidian-compatible wiki vault.
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
weknora-rag-search
Use when retrieving from or asking questions against a WeKnora knowledge base via the weknora CLI — and especially when unsure whether to use chat, session ask, or search chunks for a given goal.