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 remember-md/remember --skill askgit clone --depth 1 https://github.com/remember-md/rememberWrote 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/remember-md/remember/ask)<a href="https://agentmods.dev/skills/remember-md/remember/ask"><img src="https://agentmods.dev/badge/skills/remember-md/remember/ask/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/remember-md/remember/ask"><img src="https://agentmods.dev/badge/skills/remember-md/remember/ask.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 | $0.00045 | $0.02074 |
| Opus 5.5 | $0.00018 | $0.00830 |
| Sonnet 5.5 | $0.00009 | $0.00415 |
| Haiku 4.5 | $0.00005 | $0.00207 |
Grade A, and why
remember:ask 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/remember:ask — Ask the Brain
Wraps the mcp__remember__search_brain MCP tool with: query reformulation, multi-call retry, citation-rich answer synthesis, and honest "not found" handling.
Prerequisite
The @remember-md/mcp server must be configured in the host's MCP config (added automatically by /remember:init since plugin v2.5.0). The tool mcp__remember__search_brain must be available in this session. If it isn't:
⚠️ The brain search MCP server isn't connected. Run `/remember:init` to
auto-configure, then restart Claude Code.
Don't proceed without the tool — there's no fallback in v1.
Step 1: Parse the user's question
The slash command is invoked as /remember:ask <question>. If the question is empty or only the slash command itself, ask the user what they want to know and stop.
Note the user's language (Romanian / English / mixed). Final answer will mirror the user's language unless content forces English (e.g., technical terms).
Step 2: Reformulate the query
Convert the natural-language question into a topical search phrase that matches how the brain is actually written. Apply these rules (also documented in the search_brain tool description — read it before this step):
- 3–7 words, declarative noun-phrase
- Strip stopwords + question words ("what", "how", "ce", "cum", "do I", "am I")
- Keep nouns, concepts, proper names
- Language match the content, not the question. Technical notes in this brain are usually English. Personal/strategic/relational notes are usually Romanian. If unsure, plan to try both languages (Step 3 retry).
Quick reformulation table
| User says | Reformulated query |
|---|---|
| "what do I think about postgres for small projects" | postgres small projects preferences |
| "who works on dollie" | dollie project people contributors |
| "ce decizii am luat în martie" | decisions march 2026 |
| "ce stiu despre cezar" | cezar (proper name; let BM25 + wikilinks carry it) |
| "cum lucrez în paralel pe proiecte" | multiple parallel projects orchestration |
| "what's my strategic direction for 2026" | strategic direction 2026 priorities |
| "ce zice persona despre comunicare" | SKIP — Persona is already in your session context |
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 · 178 lines · 45 tokens per session scan A 7a083ca703a7
remember:ask is a skill published in the GitHub repository remember-md/remember (63 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 2,074 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 2026-08-30.
Other skills, from other repositories
log
Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.
analyse-call
Use this when a local call transcript or meeting note should be analyzed into traceable PersonalOS context. Preserves the source, separates evidence from interpretation, updates only proven owner truth, routes confirmed commitments through task-manager, and never sends messages or triggers external actions without…
lint-brain
Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".
ingest-article
Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.
wrap-session-up
End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.
kickoff
Guided first-run setup for a forked brain-starter vault. Walks through identity, first project, semantic search, integrations, indexes, and the first commit - verifying each phase before moving on. Use when the user has just forked or cloned brain-starter, says "set up my brain", "I just forked brain-starter", or runs…