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/mbucknam/retavyn/claude-mdgit clone --depth 1 https://github.com/mbucknam/retavynWrote 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/mbucknam/retavyn/claude-md)<a href="https://agentmods.dev/instructions/mbucknam/retavyn/claude-md"><img src="https://agentmods.dev/badge/instructions/mbucknam/retavyn/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 | $0.01350 | $0.01350 |
| Opus 5 | $0.00675 | $0.00675 |
| Sonnet 5 | $0.00270 | $0.00270 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade B, and why
retavyn CLAUDE.md scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
## Hooks (in ~/.claude/settings.json) How it starts
The opening of the file, as written. The whole thing — 111 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.
Memory Recall — Cache-First Pattern
A local cache of all memories lives at ~/.claude/retavyn-cache.md. Before calling mcp__retavyn__recall over HTTP, always check the cache first:
Read ~/.claude/retavyn-cache.mdand search for relevant content- If found locally, use it — skip the HTTP call
- If not found (or the cache is missing), call
mcp__retavyn__recall - After getting results from HTTP, append any new memories to
~/.claude/retavyn-cache.mdso future lookups find them locally
The PostToolUse hook refreshes the full cache after every remember call. To manually refresh:
./retavyn-cache.sh
To set up a daily cron refresh (optional):
0 6 * * * /path/to/retavyn/retavyn-cache.sh
Project Overview
Personal MCP memory server that gives Claude persistent memory across sessions using a PostgreSQL backend. Supports two transports:
- stdio — used by Claude Code via
.mcp.json - streamable-http — used by claude.ai at
https://mcp.retavyn.com/mcp
Both transports share the same main.py entrypoint; transport is selected via MEMORY_TRANSPORT env var.
Stack
- Python + FastMCP SDK + Starlette (HTTP mode only)
- PostgreSQL 18 on GCE VM (host configured via MEMORY_DB_HOST env var), accessed remotely
- Full-text search: tsvector/tsquery + GIN index
- Semantic search: pgvector (
text-embedding-3-small, 1024 dims) via OpenAI or Cohere - Cloudflare tunnel for
mcp.retavyn.com
Running
./setup.sh # first-time setup (venv + DB schema)
python main.py # stdio mode (default)
MEMORY_TRANSPORT=sse python main.py # HTTP mode on port 8765
CLI Commands
All CLI commands auto-load .env for DB and API credentials:
python main.py dump # export all memories to ~/.claude/retavyn-cache.md
python main.py ingest <path> [category] # ingest local files into DB with auto-backfill
python main.py health # show category stats, missing embeddings, orphans, duplicates
python main.py session-wrap # summarize transcript from stdin JSON, store as journal
python main.py proactive-recall [cwd] # surface memories relevant to current git context
python main.py generate-token # generate a new rtv_* access token
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.
- 4d ago First seen · 111 lines · 1,350 tokens per session scan B f17166423566
retavyn CLAUDE.md is an instructions file published in the GitHub repository mbucknam/retavyn (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,350 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).