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-bridgenpx skills add mworldorg/markdown-memory --skill mm-bridgegit 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 | $0.00164 | $0.02801 |
| Opus 5 | $0.00082 | $0.01401 |
| Sonnet 5 | $0.00033 | $0.00560 |
| Haiku 4.5 | $0.00016 | $0.00280 |
Grade A, and why
mm-bridge 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mm-bridge — Prompt Composer for PowerShell Claude Code
Я работаю в app/web инстансе Claude Code или в claude.ai. У пользователя есть другой Claude Code в PowerShell — там идёт реальная работа. Этот skill пишет файл-мост в Obsidian. Пользователь копипастит из файла в PowerShell-сессию.
PowerShell-инстанс не видел этот разговор. Каждый промпт — самодостаточен.
Конфиг
Загрузи mm-config.json по алгоритму из <repo>/docs/CONFIG-LOADING.md (env MM_REPO_ROOT → resolve junction → fallback). Поддержка mm-config.local.json overlay обязательна.
Понадобятся ключи:
paths.obsidian_bridge— куда писатьnext-prompt.mdpaths.obsidian_bridge_archive— куда переносить старые промптыdefault_language—ruпо умолчанию
Процесс
Шаг 1. Собери контекст задачи
Из текущего разговора пойми:
- Что сделать? — действие в одном предложении
- В каком проекте? — абсолютный путь
- Какой результат? — definition of done
Шаг 2. Авто-подгрузка паспорта проекта
Если ты знаешь целевой путь проекта — попробуй прочитать <project_path>/passport.md. Из него возьми:
project(имя)- Стек (секция 2): язык, фреймворк, главные зависимости
- Конвенции (секция 7)
- Секция 8 «Контекст для промптов» — критично, перенеси в промпт целиком
- Точки входа (секция 4)
- Команды (секция 5)
Если паспорта нет — попроси пользователя дать минимальный контекст (одно сообщение, не больше 3 вопросов):
- Целевая папка (абсолютный путь)?
- Какие файлы должен прочитать другой Клод первыми?
- Что считаем готовым?
Если пользователь говорит «ты решай» / «default» — выбираешь сам, отмечаешь в промпте <assumed: ...>.
Шаг 2.5. Выбери prompt framework
Шаблоны лежат в <repo>/templates/prompt-frameworks.md. Доступны: none | CRISPE | XML | PERSONA | HYPOTHESIS.
Если юзер передал --framework <name> — используй его. Точка.
Иначе auto-detect — применяй эвристики из <repo>/templates/prompt-frameworks.md (раздел «Auto-detect»). Этот документ — единственный source-of-truth для эвристик; не дублируй здесь.
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 · 200 lines · 0 tokens per session scan A 305e7d82073d
mm-bridge is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 15d ago), licensed MIT. It adds 164 tokens to every session and 2,801 once invoked, about $0.0008 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
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.
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…
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.
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.
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.
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.