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 agentmods add skills/luutru433-coder/local-knowledge-suite/memorizernpx skills add luutru433-coder/local-knowledge-suite --skill memorizergit clone --depth 1 https://github.com/luutru433-coder/local-knowledge-suiteWrote 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/luutru433-coder/local-knowledge-suite/memorizer)<a href="https://agentmods.dev/skills/luutru433-coder/local-knowledge-suite/memorizer"><img src="https://agentmods.dev/badge/skills/luutru433-coder/local-knowledge-suite/memorizer.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 | $0.00090 | $0.00720 |
| Opus 5 | $0.00045 | $0.00360 |
| Sonnet 5 | $0.00018 | $0.00144 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
memorizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memorizer
Use the plugin-owned runtime with the absolute project root. Require schema 2
and a Memory-enabled profile (memory-only or combined). Never use a company
repository or another project's vault.
Read references/memory-policy.md before capture, correction, or export. Read references/vault-format.md before repair, migration, snapshot inspection, or integration work.
Prefer MCP
Use recall_context with only Memory enabled for normal search and
capture_memory for one durable signal. Follow capture with
knowledge_status; require zero pending events.
Use the pinned CLI for recovery:
& "$PluginRoot\scripts\Invoke-LocalKnowledge.ps1" `
-Tool memorizer -Root $ProjectRoot `
-ToolArguments @("status")
The launcher never imports code from the target project.
Recall
- Check status after an interrupted capture.
- Distill pending events. Rebuild only when derived state is stale.
- Search with a focused query and small limit.
- Use supporting excerpts and surface contradictions.
- Distinguish remembered project context from verified company facts.
- Use
show MEMORY_ID --no-touchfor inspection; count a revisit only when the Memory informs the work.
Capture or correct
- Search for equivalent and conflicting active Memory.
- Capture one user-grounded durable signal with
kind,title,text, and a stablememory_key. - Remove every credential value. A
secretevent may record only a safe indicator, never the secret. - For correction, use exact active IDs in
supersedes; never guess. - Use a stable event ID for retries.
- Require
distilled: true, an accepted or matched ID, and zero pending events before reporting success.
Supported kinds: correction, preference, habit, decision,
commitment, entity-fact, project-knowledge, and safe-indicator secret.
Maintain
- Preserve history by superseding rather than erasing.
- Use
pin,link,backlinks, andgraphfor intentional curation. - After supported Markdown repair, run
rebuildandvalidate. - Preserve unknown frontmatter and user-authored bodies.
- Never edit SQLite or delete
.write.lockas a repair shortcut.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 77 lines · 90 tokens per session scan A 5b15c0664251
memorizer is a skill published in the GitHub repository luutru433-coder/local-knowledge-suite (0 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 720 once invoked, about $0.0005 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
llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture. Use this skill whenever the user wants to understand the wiki pattern, set up a new knowledge base, or needs guidance on the three-layer architecture (raw sources…
wiki-lint
Audit and maintain the health of the Obsidian wiki. Use this skill when the user wants to check their wiki for issues, find orphaned pages, detect contradictions, identify stale content, fix broken wikilinks, or perform general maintenance on their knowledge base. Also triggers on "clean up the wiki", "what needs…
hermes-history-ingest
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their /.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest…
project-wiki
组织和维护 Vibe Coding 项目的 wiki 文档体系。当用户要求初始化/重构 wiki 结构、进入新项目且 wiki/ 不存在、需要诊断和修复文档腐化、或需要管理 specs/refs/reviews 子目录的生命周期时触发。.
mindos-zh
MindOS 是用户的本地知识助手,也是跨会话、跨 Agent 共享的知识库。它保存决策记录、会议纪要、SOP、 排错经验、架构选型、调研结论和偏好设置。 仅 mindRoot 知识库内任务。不用于:改代码仓库、项目源码、KB 外路径。 核心概念:空间、指令(INSTRUCTION.md)、技能(SKILL.md);笔记可承载指令与技能。 触发场景:保存或记录任何内容、搜索历史笔记或上下文、更新或编辑文件、整理或重组文件结构、 执行SOP或工作流、捕获对话中的决策、复盘或总结经验、追加表格或CSV数据、跨Agent交接上下文、 提炼经验教训、同步关联文档、查找之前是否讨论过某事、查询历史决策、查找模板或SOP、…
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…