Borrowing it
Nothing to install: this file belongs to joseairosa/recall. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/joseairosa/recall/main/CLAUDE.mdgit clone --depth 1 https://github.com/joseairosa/recallWrote 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/joseairosa/recall/claude-md)<a href="https://agentmods.dev/instructions/joseairosa/recall/claude-md"><img src="https://agentmods.dev/badge/instructions/joseairosa/recall/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 | $0.02930 | $0.02930 |
| Opus 5 | $0.01465 | $0.01465 |
| Sonnet 5 | $0.00586 | $0.00586 |
| Haiku 4.5 | $0.00293 | $0.00293 |
Grade A, and why
recall CLAUDE.md scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8080/health How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Context
Recall is an MCP (Model Context Protocol) server providing long-term memory for Claude conversations. It stores context in Redis or Valkey with semantic search capabilities to survive context window limitations.
Key Principle: This server IS the solution to context loss - treat it with care and always maintain backward compatibility.
Build & Run Commands
npm run build # Production build (tsup)
npm run dev # Watch mode for development
npm run start # Run MCP server (stdio transport)
npm run start:http # Run HTTP server (for SaaS deployment)
Testing
# Unit tests with vitest (primary test runner)
npm test # Run all tests once
npm run test:watch # Watch mode
npm run test:coverage # With coverage report
# Run specific test file
npx vitest run src/services/rlm.service.test.ts
# Static checks (fast, no dependencies)
./tests/test-v1.5.0-simple.sh
# Runtime tests (requires Redis)
ANTHROPIC_API_KEY="test-key" node tests/test-runtime.js
Manual Testing
# Start Redis
redis-server
# Run MCP server manually
REDIS_URL=redis://localhost:6379 ANTHROPIC_API_KEY=sk-... node dist/index.js
# Run HTTP server for SaaS testing
REDIS_URL=redis://localhost:6379 STRIPE_SECRET_KEY=sk_test_... node dist/server-http.js
# Test Redis connection
redis-cli ping # Should return PONG
redis-cli KEYS memory:*
Architecture Overview
Entry Points
- index.ts - MCP server (stdio transport) - use for Claude Desktop/Claude Code
- server-http.ts - HTTP server for SaaS deployment (recallmcp.com)
Core Components
src/
├── index.ts # MCP server entry (stdio)
├── server-http.ts # HTTP server entry (SaaS)
├── types.ts # Zod schemas, TypeScript types
├── persistence/ # Storage layer (abstracted)
│ ├── storage-client.interface.ts # Interface for storage adapters
│ ├── storage-client.factory.ts # Creates Redis or Valkey adapter
│ ├── storage-client.ts # Storage client singleton
│ ├── memory-store.ts # Core memory CRUD operations
│ ├── redis-client.ts / redis-adapter.ts
│ └── valkey-client.ts / valkey-adapter.ts
├── embeddings/ # Multi-provider embedding system
│ ├── factory.ts # Auto-detects provider from API keys
│ ├── generator.ts # Embedding generation orchestration
│ ├── types.ts # Provider interface
│ └── providers/ # Provider implementations
│ ├── voyage-provider.ts # Voyage AI (best quality)
│ ├── cohere-provider.ts # Cohere (multilingual)
│ ├── openai-compatible-provider.ts # OpenAI/Deepseek/Grok
│ ├── anthropic-provider.ts # Anthropic (keyword fallback)
│ └── ollama-provider.ts # Local Ollama
├── services/ # Business logic services
│ └── rlm.service.ts # RLM (Recursive Language Model) for large context
├── tools/ # MCP tool handlers
│ ├── index.ts # Core tools (store, search, delete)
│ ├── context-tools.ts # Smart context (recall, analyze, summarize)
│ ├── rlm-tools.ts # RLM tools (create_execution_context, decompose, etc.)
│ ├── relationship-tools.ts # Memory linking/graphs
│ ├── version-tools.ts # Version history/rollback
│ ├── template-tools.ts # Memory templates
│ ├── category-tools.ts # Category management
│ └── export-import-tools.ts # Backup/restore
├── resources/ # MCP resource handlers
├── prompts/ # MCP prompt handlers
├── analysis/ # Claude-powered conversation analysis
└── http/ # HTTP/SaaS infrastructure
├── server.ts # Express server setup
├── mcp-handler.ts # MCP-over-HTTP with session management
├── auth.middleware.ts # API key authentication + tenant isolation
├── billing.service.ts # Stripe subscription management
├── workspace.service.ts # Workspace limit enforcement
├── team.service.ts # Team/organization management
├── oauth.service.ts # OAuth flow for Claude Desktop
├── audit.service.ts # API usage auditing
├── firebase-admin.ts # Firebase auth integration
└── types.ts # HTTP-specific types (TenantContext, etc.)
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.
- 8d ago First seen · 344 lines · 2,930 tokens per session scan A db1c8ad93fa3
recall CLAUDE.md is an instructions file published in the GitHub repository joseairosa/recall (176 stars, last pushed 8d ago), licensed MIT. It adds 2,930 tokens to every session, about $0.0146 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.
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).
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.
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.
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).
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.