agentmods.dev

mm-save-session

An end-of-session recorder for Claude Code that saves the conversation summary and project state in Obsidian notes. Obsidian is a note-taking app that stores information as files.

In plain words
What is it for?
Use it when ending a coding session to update session notes, the project note, an index, and the handoff information for the next session.
Why use it?
It preserves what was discussed, changed, decided, and left unfinished so work can resume later. In projects using GSD, a system for planning development work, it also saves the technical pause state.

Skill for Claude CodeCodex

25 16d ago A scan 129 tokens original MIT
View the source file mworldorg/markdown-memory
Install

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.

agentmods
npx agentmods add skills/mworldorg/markdown-memory/mm-save-session
Any agent
npx skills add mworldorg/markdown-memory --skill mm-save-session
Clone the repo
git clone --depth 1 https://github.com/mworldorg/markdown-memory

Made for: Claude Code, Codex.

Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,693 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00129 $0.04693
Opus 5 $0.00064 $0.02346
Sonnet 5 $0.00026 $0.00939
Haiku 4.5 $0.00013 $0.00469

Measured 2d ago against content hash 5cc7e137a8f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mm-save-session 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 2d 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.

skills/mm-save-session/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mm-save-session — End-of-Session Logger

Оформляет финал Claude Code сессии в три места: Sessions/, Projects/, INDEX.md. Реализует правила из ~/.claude/CLAUDE.md как skill (раньше выполнялось вручную, теперь гарантированно).

Конфиг

Загрузи mm-config.json по алгоритму из <repo>/docs/CONFIG-LOADING.md. Поддержка mm-config.local.json overlay обязательна.

Понадобятся:

  • paths.obsidian_sessions
  • paths.obsidian_projects
  • paths.obsidian_index

Процесс

Шаг 1. Собери контекст сессии

Из текущего разговора:

  • Что обсуждали (тема в 1-2 предложениях)
  • Что было сделано (список фактов: что создано, изменено, исправлено)
  • Какие решения приняты и почему
  • Что осталось / открытые вопросы / следующие шаги

Из git (если репо):

git log --since="6 hours ago" --oneline
git status --short
git diff --stat HEAD~5 2>/dev/null || git diff --stat

Список изменённых файлов и коммитов сегодня.

Из cwd: имя проекта = имя корневой папки (или из passport.md если есть).

Шаг 1.5. Собери «Точку возврата»

Чтобы следующее возвращение было без раскачки, на КАЖДОМ save фиксируй три вещи (команда остаётся одна — никаких отдельных режимов сохранения):

  1. Следующий конкретный шаг — одно действие, с которого продолжить. Бери из «Открытых вопросов / следующих шагов» этой сессии. Если из разговора он неочевиден — спроси louise одной строкой: С чего продолжить в следующий раз? (одна строка).
  2. Недокоммиченный WIP — из git status --short (уже собран в Шаге 1). Перечисли файлы или нет, дерево чисто.
  3. Готовый, но неотправленный промпт — если в этой сессии был собран промпт для PowerShell-Клода / claude.ai, который так и не выполнили, — запиши его текст целиком. Иначе нет.

Это пойдёт в секцию «Точка возврата» файла сессии (Шаг 3) и оттуда — в handoff.md (Шаг 5.6 через /mm-handoff).

Шаг 2. Определи целевые пути

  • Имя проекта: из passport.md (если в cwd или его родителях есть) → frontmatter project. Иначе — имя папки cwd.
  • Файл сессии: <obsidian_sessions>/<YYYY-MM-DD-HHMM>-<тема-slug>.md. Время — текущее, тему-slug сгенерируй из 3-5 слов на русском в kebab-case (транслит, нижний регистр).
    • Если файл уже существует — добавь суффикс -2, -3.

Read the full file on GitHub · 225 lines

Changes

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.

  1. 2d ago First seen · 225 lines · 129 tokens per session scan A 5cc7e137a8f1

Subscribe to this mod's changes

mm-save-session is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 16d ago), licensed MIT. It adds 129 tokens to every session and 4,693 once invoked, about $0.0006 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 2026-08-30.

Memory and contextPlanningProductivityantigravityclaude-codeclaude-skillsmarkdownmarkdown-memoryskills
Related

Other skills, from other repositories

performance-optimization

Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.

addyosmani/agent-skills · 59 tokens

doubt-driven-development

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…

addyosmani/agent-skills · 67 tokens

test-driven-development

Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

addyosmani/agent-skills · 50 tokens

ci-cd-and-automation

Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.

addyosmani/agent-skills · 45 tokens

context-engineering

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

addyosmani/agent-skills · 43 tokens

documentation-and-adrs

Records decisions and documentation. Use when making architectural decisions, changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

addyosmani/agent-skills · 43 tokens