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 the-essential/reliquery --skill memorizegit clone --depth 1 https://github.com/the-essential/reliqueryWrote 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/the-essential/reliquery/memorize)<a href="https://agentmods.dev/skills/the-essential/reliquery/memorize"><img src="https://agentmods.dev/badge/skills/the-essential/reliquery/memorize.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 | $0.00165 | $0.03853 |
| Opus 5 | $0.00082 | $0.01927 |
| Sonnet 5 | $0.00033 | $0.00771 |
| Haiku 4.5 | $0.00016 | $0.00385 |
Grade A, and why
memorize 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 7d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Memorize is the consecration step — the pipeline that takes committed relics and makes them remembered. A relic sitting in the vault but absent from the palace is an artifact no one can find: perfectly preserved, perfectly useless. Memorize bridges that gap, transforming static files into living, searchable memory.
Indexing is not summarizing. Every drawer stores verbatim relic content, chunked by section so searches return the precise passage relevant to a query — not a paraphrase, not a digest. The goal is section-level retrieval granularity: a search for "the finisher's method" should surface the relevant section, not the whole character file.
There are three input modes — identify which applies before proceeding:
- File mode: User provides specific relic files (or they were just created in this session) — index those
- Batch mode: Index all relics produced by a recent chronicle pass in one operation
- Audit mode: User wants to know which vault files have no palace representation, or which indexed entries are stale
⚠️ Reload required. Changes to the palace (new or updated drawers) will not be visible to Claude until the MCP server is restarted. For Claude Desktop: exit from the system tray, then relaunch — not just closing the window. The MCP server caches its connection state at launch. Remind the user of this at the end of every memorize session.
Session Drawer Log
Memorize maintains a running log of every drawer touched during the session — created, updated, or skipped. This log lives in conversation context only (not persisted to disk) and serves three purposes:
- Progress tracking — the user can ask "what have we indexed so far?" at any point
- Verification — Phase 5 uses it to know exactly which drawer IDs to spot-check
- Rollback scope — if something goes wrong, it identifies exactly which drawers were affected
Per drawer, track: drawer ID (or "pending" if not yet filed), source file, section(s) covered, action taken (created / updated / skipped).
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.
- 7d ago First seen · 324 lines · 165 tokens per session scan A c18eede93989
memorize is a skill published in the GitHub repository the-essential/reliquery (5 stars, last pushed 3mo ago), licensed MIT. It adds 165 tokens to every session and 3,853 once invoked, about $0.0008 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.