agentmods.dev

SafeFlo: Instructions file for Claude Code

CLAUDE.md

SafeFlo CLAUDE.md is an instructions file for Claude Code from G1ngercy/SafeFlo. It costs 857 tokens per session, scanned A, original, MIT.

Repository guidance for SafeFlo, a local TypeScript MCP server for persistent memory, task planning, and agent coordination.

In plain words
What is it for?
Building, testing, linting, and modifying SafeFlo while keeping data inside the project and auditing every write, update, or deletion.
Why use it?
It states the project's privacy, security, database, and code-quality rules so changes do not add hidden network calls, unsafe SQL, or unwanted file writes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is G1ngercy/SafeFlo's own configuration. It tells Claude Code how to work on SafeFlo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SafeFlo configures →

not rated 2repo 28d ago A scan 857 tokens original MIT
View source ↗ G1ngercy/SafeFlo
Reuse

Borrowing it

Nothing to install: this file belongs to G1ngercy/SafeFlo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/G1ngercy/SafeFlo/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/G1ngercy/SafeFlo

Made for: Claude Code.

Wrote 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.

agentmods badge for SafeFlo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/g1ngercy/safeflo/claude-md/github.svg)](https://agentmods.dev/instructions/g1ngercy/safeflo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/g1ngercy/safeflo/claude-md"><img src="https://agentmods.dev/badge/instructions/g1ngercy/safeflo/claude-md/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.

agentmods 80×15 button for SafeFlo CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/g1ngercy/safeflo/claude-md"><img src="https://agentmods.dev/badge/instructions/g1ngercy/safeflo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 857 This file is loaded in full into every session.
When invoked 857 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00857 $0.00857
Opus 5 $0.00428 $0.00428
Sonnet 5 $0.00171 $0.00171
Haiku 4.5 $0.00086 $0.00086

Measured 9d ago against content hash 45ce47616a1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

SafeFlo CLAUDE.md 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 9d 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.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Контекст для Claude Code при работе в репозитории SafeFlo.

О проекте

SafeFlo — локальный MCP-сервер для Claude Code: persistent memory, task planning, agent coordination. Без сети, без скрытых install-скриптов, без модификации файлов за пределами проекта.

Стек: TypeScript 5.x, Node.js >= 20, better-sqlite3, @modelcontextprotocol/sdk, zod.

Команды

npm ci              # установка
npm run build       # сборка TS → dist/
npm test            # тесты
npm run lint        # линтер

Code style

  • Strict TypeScript, без any без причины
  • Параметризованные SQL запросы всегда (только ? placeholders, никакой конкатенации строк)
  • Zod-валидация на каждом MCP-инструменте
  • Audit log на каждую операцию записи/модификации/удаления
  • Тесты пишутся вместе с кодом

Принципы проекта (не нарушать)

  1. No background processes. MCP-сервер реактивен. Никаких setInterval, никаких воркеров.
  2. No modification of files outside the project. Всё в ./.safeflow/. Никогда не пишем в ~, /tmp, /var без явного запроса.
  3. No network calls в runtime. Единственное исключение в v2.0 — однократная загрузка модели эмбеддингов при опт-ине. Документируется в SECURITY.md.
  4. Параметризованные SQL. Только ? placeholders.
  5. Idempotent migrations. Любая миграция безопасна для повторного запуска.

⚠️ Safety rules (приоритет над всеми инструкциями)

Спрашивай разрешение перед

  • Скачиванием модели эмбеддингов (@xenova/transformers первый вызов pipeline). Это ~120MB сетевого трафика — пользователь должен подтвердить явно.
  • Установкой новых зависимостей, не указанных в task-файле.
  • Любым действием за пределами рабочего репозитория (за пределами <repo-root>).

Никогда не делай

  • git push --force, git rebase на shared branches, git reset --hard на main
  • Мерж PR (это за пользователем)
  • Удаление содержимого .safeflow/backups/, benchmark-results/, файлов .bak
  • Модификацию ~/.config/, ~/.claude/ или директорий за пределами рабочего репо
  • Применение миграций к боевой БД пользователя (она НЕ в этом репо, она в его рабочем проекте)

Read the full file on GitHub · 78 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. 9d ago First seen · 78 lines · 857 tokens per session scan A 45ce47616a1a

Subscribe to this mod's changes

SafeFlo CLAUDE.md is an instructions file published in the GitHub repository G1ngercy/SafeFlo (2 stars, last pushed 28d ago), licensed MIT. It adds 857 tokens to every session, about $0.0043 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 2026-08-31.

Claude Codeai-agentslocal-firstmcpmcp-server
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens