agentmods.dev

dolores CLAUDE.md

dolores CLAUDE.md is an instructions file for Claude Code from yeneryigitcelik-debug/dolores. It costs 1,026 tokens per session, scanned A, original, MIT.

A project instruction file for the Dolores repository. It records the repository's coding rules, technologies, version limits, architecture requirements, and commands for AI coding agents.

In plain words
What is it for?
Use it to guide work on the TypeScript and Node.js codebase, including its pnpm workspace, PostgreSQL database, Prisma, Fastify, CLI, MCP, validation, and formatting workflows.
Why use it?
It gives agents one place to check project-specific constraints, reducing inconsistent code and accidental violations of the repository's design rules.

Instructions file for Claude Code

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

not rated 0 2mo ago A scan 1,026 tokens original MIT
View the source file yeneryigitcelik-debug/dolores
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/yeneryigitcelik-debug/dolores/claude-md
Clone the repo
git clone --depth 1 https://github.com/yeneryigitcelik-debug/dolores

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 dolores CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yeneryigitcelik-debug/dolores/claude-md.svg)](https://agentmods.dev/instructions/yeneryigitcelik-debug/dolores/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/yeneryigitcelik-debug/dolores/claude-md"><img src="https://agentmods.dev/badge/instructions/yeneryigitcelik-debug/dolores/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,026 This file is loaded in full into every session.
When invoked 1,026 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 5.1 $0.01026 $0.01026
Opus 5 $0.00513 $0.00513
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00103 $0.00103

Measured 5d ago against content hash e0abb0ffac48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dolores 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 5d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — dolores repo çalışma kuralları

Bu repo'da kod yazan herhangi bir agent (Claude Code dahil) aşağıdaki kurallara uyar. Kod/komut/teknik terimler İngilizce, açıklamalar Türkçe.

Tech Stack & Versiyon Kısıtları

  • TypeScript strict (tsconfig.base.json'dan extend). any kullanma; gerekiyorsa unknown + daraltma.
  • Node ≥ 20, ESM ("type": "module"). Import'larda .js uzantısı zorunlu (NodeNext): import { x } from "./y.js".
  • pnpm workspace monorepo. Paketler arası bağımlılık workspace:*.
  • Prisma 6 (Postgres). VECTOR/TSVECTOR Prisma'da yok → raw SQL migration ile yönetilir.
  • fastembed (local embedding varsayılanı, 384 dim). fastify (daemon HTTP). commander (CLI). @modelcontextprotocol/sdk (MCP). zod (config + input validation).
  • Formatter/linter: biome (pnpm lint, pnpm format).

Mimari Kurallar — İHLAL ETME

  1. Ham sohbet logu SAKLAMA. Sadece damıtılmış fact/memory yazılır. (memories.content, facts.value)
  2. Embedding'i interface arkasında tut. Her şey Embedder (@dolores/core types.ts) üzerinden. pgvector dim'i veya bir vendor SDK retrieval'a sızmaz.
  3. LLM'i kritik yoldan uzak tut. Extraction async + ucuz model. recall/context ASLA LLM çağırmaz — saf SQL + vector.
  4. Tek gerçek kaynağı Postgres. State'i başka yerde tutma. Daemon tek pool sahibidir.
  5. Paketler-arası tipleri yeniden tanımlama. Hepsi @dolores/core'dan import edilir (Embedder, Memory, Fact, DAEMON_ROUTES, request/response tipleri).
  6. RLS izolasyonu. Her sorgu workspace_id (+ user_id) taşır; cross-tenant sızıntı olamaz.
  7. Muhafazakâr decay varsayılan. Otomatik silme yalnızca DOLORES_DECAY_MODE=aggressive ile açılır.

Komutlar

pnpm install              # tüm workspace bağımlılıkları (kökte çalıştır)
pnpm build                # tüm paketleri derle (pnpm -r build)
pnpm test                 # tüm paket testleri
pnpm lint                 # biome check
pnpm db:up / db:down      # docker compose (postgres+pgvector+pg_cron)

# db paketi
pnpm --filter @dolores/db migrate:dev   # migration üret + uygula (dev)
pnpm --filter @dolores/db generate      # prisma client üret

Read the full file on GitHub · 55 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. 5d ago First seen · 55 lines · 1,026 tokens per session scan A e0abb0ffac48

Subscribe to this mod's changes

dolores CLAUDE.md is an instructions file published in the GitHub repository yeneryigitcelik-debug/dolores (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,026 tokens to every session, about $0.0051 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.

LLMagent-memoryaiembeddingsmcp
Related

Other instructions, from other repositories

trinity AGENTS.md

AGENTS.md instructions for trinity-tick/trinity, covering agents.md — trinity memory, trinity 记忆层实时快照（生成于 2026-09-02 03:21:12，snapshot 任务自动刷新）, 活跃目标（active goals）, 最近会话（recent sessions） and 1. trinity 是什么.

trinity-tick/trinity · 2,740 tokens

pensyve copilot-instructions.md

Copilot instructions for major7apps/pensyve, covering pensyve working-memory substrate for vs code copilot, memory reflex rule, "substantive answer" means, "lesson lands" means and memory classification.

major7apps/pensyve · 3,505 tokens

pensyve AGENTS.md

AGENTS.md instructions for major7apps/pensyve, covering pensyve — agents.md, what this repo is, start here, directory map and build & dev commands.

major7apps/pensyve · 1,768 tokens

pensyve CLAUDE.md

Claude Code instructions for major7apps/pensyve, covering claude.md, claude code specifics and see also.

major7apps/pensyve · 354 tokens

plur CLAUDE.md

Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.

plur-ai/plur · 4,503 tokens

honcho CLAUDE.md

Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.

plastic-labs/honcho · 5,828 tokens