agentmods.dev

symphony CLAUDE.md

symphony CLAUDE.md is an instructions file for coding agents from lrgendie/symphony. It costs 1,497 tokens per session, scanned A, original, MIT.

Project instructions in Turkish for Symphony, a system that runs local and cloud AI models and coding agents from one background service. It provides both a terminal interface and a desktop application.

In plain words
What is it for?
Use them when developing Symphony, choosing files to edit, checking the roadmap, recording session progress, or working on its terminal, desktop, daemon, and model integrations.
Why use it?
They tell an AI coding agent where to find the current project status and file map before making changes. They also define rules for keeping session notes and project documentation up to date.

Instructions file

not rated 2 1mo ago A scan 1,497 tokens original MIT
View the source file lrgendie/symphony
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 instructions/lrgendie/symphony/claude-md
Clone the repo
git clone --depth 1 https://github.com/lrgendie/symphony

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 symphony CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lrgendie/symphony/claude-md.svg)](https://agentmods.dev/instructions/lrgendie/symphony/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lrgendie/symphony/claude-md"><img src="https://agentmods.dev/badge/instructions/lrgendie/symphony/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,497 This file is loaded in full into every session.
When invoked 1,497 The same file — it is already loaded in full.
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 $0.01497 $0.01497
Opus 5 $0.00749 $0.00749
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00150 $0.00150

Measured 4d ago against content hash ea50b6eb69d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

symphony 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 4d 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 · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Symphony Proje Anayasası

Bu repoda çalışan her AI modeli (Fable, Opus, Sonnet, yerel model) için bağlayıcı talimatlar. Bu belge, projenin tasarımı Fable 5 ile yapılırken yazıldı; buradaki kurallar daha zayıf bir modelin bile mimariyi bozmadan katkı verebilmesi içindir.

Proje nedir?

Symphony: yerel (Ollama) + bulut (Claude/GPT/Gemini) LLM'leri ve kod agent'larını tek daemon'dan yöneten, Win/mac/ARM çapraz platform orkestrasyon sistemi. Terminal (symphony) ve masaüstü (Tauri) aynı daemon'a bağlı iki eş zamanlı arayüzdür.

Her oturumda ilk iş

  1. memo/DURUM.md oku → kaldığımız yer ve sıradaki adım orada.
  2. memo/BAGLAM.md oku → dosya haritası + "görev → ne okumalı" tablosu orada. Geniş kod taraması yapma; yalnız o oturumda dokunacağın dosyaları, haritadan bulup hedefli oku (token bütçesi kuralları BAGLAM.md sonunda).
  3. Oturum sonunda: memo/DURUM.md + (yapısal değişiklik olduysa) memo/BAGLAM.md güncelle + memo/oturumlar/YYYY-AA-GG.md günlüğü yaz. (Commit+push'u SessionEnd hook'u otomatik yapar; elle yapıyorsan mesaj formatı: oturum: ...)

Belge haritası

Belge İçerik Ne zaman bak
ROADMAP.md Fazlar, kabul testleri Yeni faza başlarken
docs/PROTOKOL.md WS/REST protokol spesifikasyonu shared/core/cli/ui'ye dokunmadan önce mutlaka
docs/SPEC-AGENT.md Agent motoru + izin sistemi şartnamesi Faz 3+ işlerinde mutlaka
docs/kararlar/KARARLAR.md Mimari kararlar ve gerekçeleri (ADR) Teknoloji değiştirmek istediğinde
docs/GEREKSINIMLER.md Kütüphane envanteri, dizin planı Bağımlılık eklerken
docs/TASARIM.md Görsel dil, palet, "yaşayan arayüz" vizyonu Arayüz (ui/desktop) görsel işinde mutlaka

Dokunulmaz kurallar

  1. Protokol kutsaldır. CLI ve UI, daemon'la YALNIZCA packages/shared'daki tiplerle konuşur. Yeni mesaj/olay eklemek = önce docs/PROTOKOL.md güncelle, sonra shared'a zod şeması ekle, sonra kullan. Şeması olmayan mesaj gönderilemez.
  2. Mimari kararlar ADR'siz değişmez. "Electron'a geçelim", "LangChain kullanalım" gibi bir değişiklik yapmadan önce docs/kararlar/KARARLAR.md'deki ilgili kaydı oku; reddedilme gerekçesi hâlâ geçerliyse değiştirme. Değiştireceksen önce ADR'ye yeni kayıt yaz.
  3. API anahtarı asla dosyaya/koda/loga yazılmaz. Anahtarlar OS keychain'inde (keytar). providers.json yalnızca anahtar-DIŞI yapılandırma içerir.
  4. Temperature varsayılanı 0'dır. Agent tanımında açıkça belirtilmedikçe yükseltilmez.
  5. Test geçmeden iş bitmiş sayılmaz. Her yeni özellik Vitest testiyle gelir; fazın ROADMAP'teki kabul testi geçmeden faz kapanmaz.
  6. Agent izinsiz dosya değiştiremez / komut çalıştıramaz. İzin akışı docs/SPEC-AGENT.md'de; bu akışı atlayan kısayol ekleme.
  7. Dikey dilim. Uçtan uca çalışmayan 3 haftalık altyapı işi açma; her adım çalışan bir şey bırakır.

Read the full file on GitHub · 80 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. 4d ago First seen · 80 lines · 1,497 tokens per session scan A ea50b6eb69d9

Subscribe to this mod's changes

symphony CLAUDE.md is an instructions file published in the GitHub repository lrgendie/symphony (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,497 tokens to every session, about $0.0075 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.

ai-agentsautomationdesktop-appdeveloper-toolsllm-orchestration
Related

Other instructions, from other repositories

1flowbase AGENTS.md

AGENTS.md instructions for taichuy/1flowbase, covering 记忆, 用户偏好, 本项目相关skill在, 本项目 skills and 质量控制.

taichuy/1flowbase · 1,444 tokens

nextclaw AGENTS.md

AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.

Peiiii/nextclaw · 3,095 tokens

moonproxy-desktop AGENTS.md

AGENTS.md instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.

MoonProxyHQ/moonproxy-desktop · 3,883 tokens

code-by-wire CLAUDE.md

Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.

luojiahai/code-by-wire · 1,073 tokens

markra AGENTS.md

AGENTS.md instructions for markrahq/markra, covering markra engineering guidelines, package management, tech stack, code organization and codemirror editor invariants.

markrahq/markra · 1,368 tokens

Token-Dashboard CLAUDE.md

Instructions for Arylmera/Token-Dashboard, covering claude.md, project overview, status, architecture and data source.

Arylmera/Token-Dashboard · 2,495 tokens