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 mworldorg/markdown-memory --skill mm-handoffgit clone --depth 1 https://github.com/mworldorg/markdown-memoryWrote 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-handoff)<a href="https://agentmods.dev/skills/mworldorg/markdown-memory/mm-handoff"><img src="https://agentmods.dev/badge/skills/mworldorg/markdown-memory/mm-handoff/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-handoff"><img src="https://agentmods.dev/badge/skills/mworldorg/markdown-memory/mm-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Prompt Injection · line 141 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 141 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- 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.
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 | $0.00164 | $0.04479 |
| Opus 5.5 | $0.00066 | $0.01792 |
| Sonnet 5.5 | $0.00033 | $0.00896 |
| Haiku 4.5 | $0.00016 | $0.00448 |
Grade A, and why
mm-handoff 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 — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mm-handoff — Snapshot for Next claude.ai Chat
Решает проблему: контекст в чате claude.ai заполнен. Дополняет Anthropic Memory структурированным компактным snapshot'ом, который загружается в Project Knowledge.
Memory vs Handoff: Memory (Anthropic, авто) хранит долгосрочные факты о тебе и проекте. Handoff (этот skill, ручной) — свежий контекст за 1-2 недели: что сделано, что в работе, что открыто. Не конкурируют — дополняют.
Когда вызывать
- Автоматически — из
/mm-save-session(шаг 5.6) при каждом закрытии сессии, чтобы handoff.md в Project Knowledge claude.ai всегда был свежим. Это основной путь, руками дёргать не надо. - Вручную (
/mm-handoffили/mm next) — когда контекст текущего чата забился, а сессию закрывать рано: обновить handoff, не закрывая сессию. - Перед стартом нового чата в claude.ai по тому же проекту
- В конце большой вехи (после серии сессий)
- Перед паузой на несколько дней — чтобы вернуться без раскачки
Скелет handoff.md создаётся ещё на
/mm-init-project; первый же/mm-save-sessionзаменяет его полноценной версией через этот skill.
Конфиг
Загрузи mm-config.json по алгоритму из <repo>/docs/CONFIG-LOADING.md. Поддержка mm-config.local.json overlay обязательна.
Понадобятся:
paths.obsidian_projectspaths.obsidian_sessionspaths.obsidian_index(INDEX.md)
Процесс
Шаг 1. Определи проект и хранилище Vault
- Прочитай
passport.mdв текущейcwd. Если нет — спроси: «Для какого проекта handoff? Дай путь.» или «Запустить /mm-init-project сначала?» - Из паспорта возьми: имя, тип, путь.
- Определи путь базы знаний
<vault_root>(определяй по единому алгоритму: (1) из секции## Obsidian Knowledge VaultвCLAUDE.mdсо строкойХранилище знаний: <путь>, если она есть; (2) локальная папка.vault/в корне проекта; (3) глобальная папка проекта<obsidian_projects>/<name>/из конфига).
Шаг 2. Собери сводку последних сессий — index-first, тела лениво
Progressive disclosure (достройка существующей 3-слойной структуры mm, не новый механизм). Индекс однострочников уже есть — не вычитывай полные тела сессий ради «Что сделано». Раньше handoff читал 3-5 ПОЛНЫХ тел при каждом вызове; теперь основной источник — дешёвый индекс, а тела открываются лениво. Цель — экономия контекста на «толстых» проектах.
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 · 265 lines · 164 tokens per session scan A 33842ada89ee
mm-handoff is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed today), licensed MIT. It adds 164 tokens to every session and 4,479 once invoked, about $0.0007 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
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-memory
A hybrid memory system that provides persistent, searchable knowledge management for AI agents.
accint-frames
Drain acc's deliberation queue — open/waiting brainframes checkpointed by headless runs — via accact(runtime="continue").
accint-solve
Route a goal through acc's scored-memory loop via accact(runtime="solve"); deliberate any returned brainframe and submit via continue.
agent-memory-systems
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.