Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mworldorg/markdown-memorynpx agentmods add skills/mworldorg/markdown-memory/mm-setupWrote 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/mworldorg/markdown-memory/mm-setup)<a href="https://agentmods.dev/skills/mworldorg/markdown-memory/mm-setup"><img src="https://agentmods.dev/badge/skills/mworldorg/markdown-memory/mm-setup/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/mworldorg/markdown-memory/mm-setup"><img src="https://agentmods.dev/badge/skills/mworldorg/markdown-memory/mm-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 113 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Agent Snooping · line 19 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 92 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Rogue Agent · line 113 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 113 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 114 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00152 | $0.02107 |
| Opus 5.5 | $0.00061 | $0.00843 |
| Sonnet 5.5 | $0.00030 | $0.00421 |
| Haiku 4.5 | $0.00015 | $0.00211 |
Grade A, and why
mm-setup 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mm-setup — Персонализация mm-системы под пользователя
Делает систему «своей»: имя, домен, стек, пути — без правки committed-файлов (репо общий, расшарен на GitHub). Личное идёт в gitignored оверлей и в генерируемую персональную копию claude.ai-скилла.
Контракт безопасности (соблюдай дословно)
Skill ПИШЕТ только в:
<repo>/config/mm-config.local.json— создаёт или мёрджит (gitignored, личный оверлей)<repo>/claude-ai-skills/_generated/mm-web-bridge/SKILL.md— персональная копия для загрузки в claude.ai (gitignored)
Skill НИКОГДА не трогает:
config/mm-config.json(committed — общие дефолты louise; их не перезаписываем)claude-ai-skills/mm-web-bridge/SKILL.md(committed шаблон — читаем как источник, не правим)- любые
skills/*/SKILL.md,~/.claude/CLAUDE.md(для глобального — только предложим сниппет) - git-операции
Конфиг
Загрузи mm-config.json по алгоритму из <repo>/docs/CONFIG-LOADING.md (нужен _repo_root). Если уже есть mm-config.local.json — прочитай его как текущие значения (режим повторной настройки).
Шаг 1. Интервью
Задай одним сообщением (не по одному вопросу), с разумными дефолтами в скобках:
Настрою mm-систему под тебя. Ответь (можно коротко):
1. Имя — как тебя называть? <текущее из config, если есть>
2. Чем занимаешься / домен? (например: «Telegram-боты», «веб на React», «data-инженерия»)
3. Основной стек? (язык · фреймворк · БД · деплой — например «Python · aiogram 3.x · SQLite · Railway»)
4. Язык общения по умолчанию? (ru / en) <текущий default_language>
5. Путь к Obsidian vault? <текущий obsidian_vault, или предложи C:\Users\<user>\Documents\Obsidian Vault>
Дополнительно (не спрашивай, выведи сам):
<user>для дефолтных путей возьми из$env:USERPROFILE/~.- Если на п.5 дают только vault — остальные obsidian-пути (
Claude/,Bridge/,Sessions/,Projects/,INDEX.md) выведи относительно него по той же структуре, что в committedmm-config.json. - Если пользователь говорит «как у тебя в дефолте / пропусти» — оставь committed-значение (не дублируй его в local без нужды).
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 · 137 lines · 152 tokens per session scan A a560b8d0851f
mm-setup is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 19d ago), licensed MIT. It adds 152 tokens to every session and 2,107 once invoked, about $0.0006 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
context-engineering-review
Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut token usage without losing quality, debug an agent that ignores instructions, or audit how retrieval results, history, and…
memory-file-maintenance
Keep your AI memory/context file (MEMORY.md, CLAUDE.md, custom instructions) healthy over time — pruning the stale, adding the new, and keeping it sharp so your AI keeps getting you right. Use when asked review my memory file, my AI context is outdated, clean up my CLAUDE.md, or maintain my AI instructions. Produces a…
session-memory-manager
Manages the entire session lifecycle: from context loading (PRD, Tech Stack) at startup, to maintaining project memory during active sessions, and creating ultra-compact checkpoints for handoff. / Mengelola siklus hidup sesi: dari pemuatan konteks awal, pemeliharaan memori proyek, hingga pembuatan checkpoint ringkas…
context-bankruptcy
Summarise what Context Bankruptcy does in one line. Use when asked to [trigger phrases the user would say]. Produces [the concrete artifact].
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE…