tages: Instructions file for Claude Code

CLAUDE.md

tages CLAUDE.md is an instructions file for Claude Code from ryantlee25-droid/tages. It costs 1,110 tokens per session, scanned A, original, MIT.

Project instructions for Tages, an open-source server, command-line tool, and dashboard that gives coding agents memory across coding sessions. It covers the project’s setup, structure, design choices, security, and commands.

In plain words
What is it for?
Use it when changing Tages, its Node.js and TypeScript packages, dashboard, database setup, or tests. It also helps when working in a pnpm monorepo, a repository that contains several related packages and apps.
Why use it?
It gives an agent the project context needed to work consistently in a multi-package codebase. This reduces guesswork about where code belongs and which rules or commands to follow.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is ryantlee25-droid/tages's own configuration. It tells Claude Code how to work on tages 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 tages configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ryantlee25-droid/tages. 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/ryantlee25-droid/tages/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ryantlee25-droid/tages

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 tages CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ryantlee25-droid/tages/claude-md.svg)](https://agentmods.dev/instructions/ryantlee25-droid/tages/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ryantlee25-droid/tages/claude-md"><img src="https://agentmods.dev/badge/instructions/ryantlee25-droid/tages/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,110 This file is loaded in full into every session.
When invoked 1,110 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 $0.01110 $0.01110
Opus 5 $0.00555 $0.00555
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 7d ago against content hash b587d79253f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

tages 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 7d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tages — Project Configuration

Overview

Tages is an open-source MCP server + CLI + dashboard that gives AI coding agents persistent, cross-session memory about codebases. Named after the Etruscan divine child who dictated sacred knowledge to scribes.

Repo: https://github.com/ryantlee25-droid/tages Stack: pnpm monorepo — Node.js/TypeScript npm packages: @tages/cli (CLI), @tages/server (MCP server), @tages/shared (types)

Architecture

packages/
  server/     # MCP server (@modelcontextprotocol/sdk, stdio transport)
              # 56 MCP tools, 22 server modules, 74 test suites (817 tests: 804 passing, 13 skipped)
  cli/        # tages CLI (commander.js, 42 top-level commands, 71 incl. subcommands)
  shared/     # Shared types + Supabase client factory
apps/
  dashboard/  # Next.js 16 + Supabase Auth + Tailwind + shadcn/ui
              # Auth, project list, memory browser, stats, conflicts, graph
supabase/
  migrations/ # 64 Postgres migrations (schema, RLS, RPCs, indexes)

Key Design Decisions

  • Primary storage: Supabase Postgres with pg_trgm fuzzy search + pgvector semantic search
  • Local cache: SQLite (better-sqlite3) for sub-10ms MCP queries, 60s async sync to Supabase
  • Auth: Supabase Auth with GitHub OAuth; CLI tokens hashed with SHA-256
  • Encryption: Optional AES-256-GCM field-level encryption (set TAGES_ENCRYPTION_KEY)
  • LLM for auto-indexing: Ollama (local) -> Claude Haiku (API) -> dumb mode (file paths only)
  • Transport: stdio (standard for Claude Code / Cursor MCP integration)

Security

  • RBAC: Owner/admin can write, member read-only (migration 0031)
  • RLS: Enabled on all tables with per-user/per-project policies
  • Token management: SHA-256 hashed, supports expiration + tages token rotate
  • Encryption at rest: AES-256-GCM for memory values (opt-in via env var)
  • Secret/PII detection: Blocks high-severity secrets, warns on PII before storage
  • Auth audit logging: Tracks login success/failure, token validation events
  • Transport security: HSTS, CSP (no unsafe-eval in production), SameSite=Strict cookies
  • Input validation: Zod schemas on all 56 MCP tools, URL slug validation, 1MB request limits
  • SECURITY.md: Responsible disclosure policy at repo root

Read the full file on GitHub · 87 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. 7d ago First seen · 87 lines · 1,110 tokens per session scan A b587d79253f3

Subscribe to this mod's changes

tages CLAUDE.md is an instructions file published in the GitHub repository ryantlee25-droid/tages (4 stars, last pushed 7d ago), licensed MIT. It adds 1,110 tokens to every session, about $0.0056 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.

Related

Other instructions, from other repositories

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 · 5,182 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

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

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

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens