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/mworldorg/markdown-memory/mm-updatenpx skills add mworldorg/markdown-memory --skill mm-updategit clone --depth 1 https://github.com/mworldorg/markdown-memoryWhat 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 | $0.00102 | $0.02033 |
| Opus 5 | $0.00051 | $0.01017 |
| Sonnet 5 | $0.00020 | $0.00407 |
| Haiku 4.5 | $0.00010 | $0.00203 |
Grade A, and why
mm-update 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.
How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mm-update — Self-Update from Git Remote
Обновляет mm-систему до свежей версии из origin/main. mm установлен как git-клон с junction'ами в ~/.claude/skills/ — поэтому обновление это git pull репозитория + повторный прогон register-skills, а не пакетный менеджер.
Ничего не сливает и не ребейзит автоматически. При любом расхождении или ошибке --ff-only — стоп с инструкцией разрулить вручную.
Ручной интерактивный аналог фонового
scripts/auto-update.py(ff-only, дёргается изmm-resume); git-поток общий — отличие в том, что здесь показывается changelog и спрашивается подтверждение.
Где работать
Корень репозитория mm:
$env:MM_REPO_ROOTесли задан;- иначе текущая рабочая директория (
cwd).
Все git-команды и register-skills выполняй из этого корня.
Процесс
0. Guard: это вообще git-репо?
Проверь, что в корне репо (см. «Где работать») есть .git:
Test-Path (Join-Path $repoRoot ".git")
Если .git нет — mm установлен не как git-репо (например, распакован из tarball). Стоп:
❌ mm установлен не как git-репозиторий — обновлять через git нечем.
Обнови через `npx markdown-memory update` или переустанови mm.
Не продолжай. (По смыслу как auto-update.py: «Not a git repository. Skipping update».)
1. Забрать состояние remote
git fetch origin main
Если git fetch упал (нет сети / нет доступа к origin) — стоп: ⚠️ Не удалось связаться с origin. Проверь сеть и доступ к github.com/mworldorg/markdown-memory. Не продолжай.
2. Сравнить версии
- Локальная версия: поле
versionизconfig/mm-config.json(читай файл напрямую). - Удалённая версия:
распарси JSON, возьмиgit show origin/main:config/mm-config.jsonversion.
Это поле — единый источник версии системы (repo-wide release). Per-skill version: в каждом SKILL.md гранулярны и здесь не сравниваются.
3. Определить расхождение ветки
git rev-list --left-right --count HEAD...origin/main
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.
- 2d ago First seen · 162 lines · 102 tokens per session scan A 94f25fd6925f
mm-update is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 16d ago), licensed MIT. It adds 102 tokens to every session and 2,033 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 2026-08-30.
Other skills, from other repositories
constraint-driven-development
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or…
git-workflow-and-versioning
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump…
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.
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.
shipping-and-launch
Prepares production launches. Use when preparing to deploy to production. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
spec-driven-development
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a…