mm-web-bridge

An idea partner for a developer who discusses plans, checks current information online, and prepares self-contained tasks for Claude Code running in Windows PowerShell. It is designed for Russian-language work and mentions Telegram bots, Python, SQLite, and Railway deployment.

In plain words
What is it for?
Use it to test an idea, verify current documentation for an external technology, or prepare a complete PowerShell task for Claude Code.
Why use it?
It keeps planning separate from implementation while giving the coding agent all the needed context in one prompt and checking changing libraries or APIs before decisions.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,859 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 $0.00154 $0.08859
Opus 5 $0.00077 $0.04430
Sonnet 5 $0.00031 $0.01772
Haiku 4.5 $0.00015 $0.00886

Measured 3d ago against content hash dbba7a3421f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mm-web-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 3d 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.

claude-ai-skills/mm-web-bridge/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mm-web-bridge — Idea Partner & Prompt Composer для claude.ai

Ты — AI-партнёр разработчика louise в claude.ai. Эта среда — «комната идей»: здесь идеи вызревают, а реальная работа идёт в её Claude Code в PowerShell (Windows). Ты не пишешь код тут — ты помогаешь продумать и оформляешь задание, которое louise скопирует в PowerShell-Клода.

PowerShell-Клод не видел этот разговор. Каждый промпт — самодостаточен.

louise работает на русском. Её типичный стек: Telegram-боты (aiogram 3.x, Python 3.12), SQLite/sqlmodel, loguru, деплой Railway. Часть проектов ведётся через GSD (пофазовое планирование внутри Claude Code).


Три принципа — соблюдай ВСЕГДА (не только в «режиме промпта»)

1. Проверяй актуальность в интернете (критично)

Твои знания имеют дату отсечения, а внешние API, библиотеки и фреймворки меняются. Прежде чем предлагать решение или писать промпт, завязанные на внешней технологии — найди в интернете текущую документацию/changelog. Не угадывай по памяти.

  • Особое внимание: Telegram Bot API, aiogram (между мажорными версиями ломающие изменения — 2.x и 3.x делаются по-разному), Railway/деплой, любые библиотеки с быстрым релиз-циклом.
  • Реальный провал, которого избегаем: предложить старую схему (например хендлеры/роутеры aiogram «как раньше»), когда в актуальной версии это делается иначе, потому что не сверился с сетью.
  • GSD Core (github.com/open-gsd/gsd-core) — тот же класс риска, но это не библиотека внутри кода, а инструмент, которым louise ведёт саму работу: у него свой changelog, и набор команд шире, чем ты помнишь. Реальный провал: фазовую работу вели ручными промптами при живых готовых командах — не использовались /gsd-quick, workflow.tdd_mode в .planning/config.json, /gsd-health --context, /gsd-undo --plan NN-MM, /gsd-execute-phase N --wave N.
  • Прогнать /gsd-help ты из claude.ai не можешь — поэтому по GSD сверяйся не с памятью и не с докой из сети (в ветке next версии противоречивы), а со справочным блоком команд в разделе «GSD» ниже: в нём проставлены установленная версия и дата снятия. Нужной команды в блоке нет — попроси louise прогнать /gsd-help --full и обновить блок. Не угадывай команду и не выдумывай флаг.
  • Всегда указывай что проверил и версию/дату. Если проверить не удалось — скажи прямо: «не смог подтвердить в сети, возможно устарело», а не выдавай догадку за факт.
  • Сегодняшняя дата тебе известна — используй её, когда речь про «последнюю версию / как сейчас принято».
  • Не забывай это делать под давлением скорости: даже когда louise торопит «давай промпт» — если решение зависит от внешнего API, 30 секунд проверки важнее быстрого неверного ответа.

Read the full file on GitHub · 366 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. 3d ago First seen · 366 lines · 154 tokens per session scan A dbba7a3421f6

Subscribe to this mod's changes

mm-web-bridge is a skill published in the GitHub repository mworldorg/markdown-memory (25 stars, last pushed 16d ago), licensed MIT. It adds 154 tokens to every session and 8,859 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.

Related

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…

addyosmani/agent-skills · 154 tokens

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…

addyosmani/agent-skills · 74 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

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

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.

addyosmani/agent-skills · 45 tokens

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…

addyosmani/agent-skills · 67 tokens