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 memseekai/memseek --skill memseek-remembergit clone --depth 1 https://github.com/memseekai/memseekWrote 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/memseekai/memseek/memseek-remember)<a href="https://agentmods.dev/skills/memseekai/memseek/memseek-remember"><img src="https://agentmods.dev/badge/skills/memseekai/memseek/memseek-remember.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00382 |
| Opus 5 | $0.00012 | $0.00191 |
| Sonnet 5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
memseek-remember 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 8d 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
Remember with Memseek
Persist $ARGUMENTS only when the user explicitly asks you to remember it or clearly
confirms it is durable. Never infer a preference, policy, deadline, or decision from
silence. Never store secrets, credentials, access tokens, private keys, or raw tool output.
The SessionStart context gives you the exact project entity and conversation session.
If its memory write policy is off, do not write. Explain that the user must change
MEMSEEK_CAPTURE_MODE to explicit or conversation and start a new session.
- If automatic capture mode is
conversationand$ARGUMENTSis already stated in the current user prompt, explain that the exact prompt is being captured; do not duplicate it. - Otherwise, call the Memseek MCP
remembertool with:entity: the exact project memory entity from SessionStarttype:messagetext: the user's exact words, without interpretationcontent.text: the same exact wordscontent.role:usercontent.session_id: the exact conversation session from SessionStartcontent.ordinal: a current Unix timestamp in millisecondsdedupe_key: a stableclaude-explicit:key derived from the entity and exact text
- Report that the append was accepted. Do not claim that derived memories already exist; the Memseek worker builds L1–L3 state asynchronously.
If the write tool is unavailable, run /memseek-memory:memseek-status and report the
specific configuration or tool-contract failure.
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.
- 8d ago First seen · 34 lines · 24 tokens per session scan A 831be729968d
memseek-remember is a skill published in the GitHub repository memseekai/memseek (7 stars, last pushed 13d ago), licensed Apache-2.0. It adds 24 tokens to every session and 382 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
atomicmemory
Persistent semantic memory across Claude Code sessions — user preferences, project context, prior decisions, codebase facts. Call memorysearch before answering questions that reference past work. Call memoryingest after the user shares durable facts.
atomicmemory-cli
Use the installed AtomicMemory CLI for memory search, ingestion, packaging, diagnostics, and agent-safe JSON output.
openmemory
Manage persistent memory via OpenMemory MCP. TRIGGER when: user says "remember this", "save to memory", "store this", "recall", "what do you remember about", "check memory", "forget this", "delete memory", "clean up memory", or when agent forms a stable conclusion worth persisting. DO NOT TRIGGER when: user refers to…
recall-before-claim
Forces a memorysearch before the agent sends a message containing a factual assertion that has not yet been grounded this turn. Closes the citation-rate gap from 40% to 90%+.
route-by-query-shape
When the agent calls memorysearch with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledgegraph backend where it will actually find the answer.
deja-search
Search deja before re-deriving past work: when the user refers to earlier sessions or decisions, before debugging an error, and before implementing something that may already exist. It searches this machine's own history across every AI coding tool used on it, going back further than deja itself was installed.