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.
npx agentmods add instructions/bayramannakov/retain/claude-mdgit clone --depth 1 https://github.com/BayramAnnakov/retainWrote 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.
[](https://agentmods.dev/instructions/bayramannakov/retain/claude-md)<a href="https://agentmods.dev/instructions/bayramannakov/retain/claude-md"><img src="https://agentmods.dev/badge/instructions/bayramannakov/retain/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03435 | $0.03435 |
| Opus 5 | $0.01717 | $0.01717 |
| Sonnet 5 | $0.00687 | $0.00687 |
| Haiku 4.5 | $0.00344 | $0.00344 |
Grade A, and why
retain 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retain
Native macOS app that aggregates AI conversations from multiple platforms into a unified, searchable knowledge base with intelligent learning extraction.
GitHub: https://github.com/BayramAnnakov/retain
Architecture
┌─────────────────────────────────────────────────────────────┐
│ SwiftUI │
│ ContentView → ConversationDetailView, MenuBarView, etc. │
├─────────────────────────────────────────────────────────────┤
│ AppState (@MainActor) │
│ - conversations, searchResults, syncState │
│ - manages all UI state and coordinates services │
├─────────────────────────────────────────────────────────────┤
│ Services │
│ ┌─────────────┐ ┌─────────────┐ ┌────────────────────┐ │
│ │ SyncService │ │ FileWatcher │ │ WebSyncEngine │ │
│ │ (actor) │ │ (FSEvents) │ │ (claude.ai/gpt) │ │
│ └──────┬──────┘ └──────┬──────┘ └─────────┬──────────┘ │
│ └────────────────┴───────────────────┘ │
│ │ │
│ ┌─────────────────────────────────────────────────────────┐│
│ │ ConversationRepository / LearningRepository (GRDB) ││
│ └─────────────────────────────────────────────────────────┘│
│ │ │
│ ┌─────────────────────────────────────────────────────────┐│
│ │ SQLite + FTS5 (~/.../Retain/retain.sqlite) ││
│ └─────────────────────────────────────────────────────────┘│
└─────────────────────────────────────────────────────────────┘
Project Structure
Sources/Retain/
├── App/ # Entry point, AppState, ContentView
├── Components/ # Reusable UI (SyncOverlay, ProviderBadge)
├── Data/
│ ├── Models/ # Conversation, Message, Learning, Provider
│ ├── Parsers/ # ClaudeCodeParser, CodexParser
│ └── Storage/ # Database, Repositories
├── Features/
│ ├── ConversationBrowser/
│ ├── Learning/
│ ├── MenuBar/
│ ├── Settings/
│ └── Onboarding/
├── Integrations/ # macOS native integrations
│ ├── SpotlightIndexer.swift # Core Spotlight indexing
│ └── URLSchemeHandler.swift # retain:// deep linking
├── Intents/ # App Intents for Shortcuts/Siri
│ ├── ConversationEntity.swift
│ ├── ConversationQuery.swift
│ ├── RetainIntents.swift
│ └── ShortcutsProvider.swift
└── Services/
├── FileWatcher.swift # FSEvents for file changes
├── SyncService.swift # Background sync (actor)
├── Learning/ # CorrectionDetector, CLAUDEMDExporter
├── Search/ # SemanticSearch, OllamaService
└── WebSync/ # ClaudeWebSync, ChatGPTWebSync
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.
- 6d ago First seen · 359 lines · 3,435 tokens per session scan A 6d2a027217cb
retain CLAUDE.md is an instructions file published in the GitHub repository BayramAnnakov/retain (169 stars, last pushed 6mo ago), licensed MIT. It adds 3,435 tokens to every session, about $0.0172 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.
Other instructions, from other repositories
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.