agentmods.dev

cerefox: Instructions file for Claude Code

CLAUDE.md

cerefox CLAUDE.md is an instructions file for Claude Code from fstamatelopoulos/cerefox. It costs 13,284 tokens per session, scanned B, original, Apache-2.0.

A project guide for Cerefox, a shared long-term memory system for AI agents. It stores Markdown knowledge in a database and makes it searchable through MCP and REST.

In plain words
What is it for?
Use it to understand Cerefox's architecture, technology choices, project structure, and development conventions.
Why use it?
It helps agents find useful information across separate conversations, sessions, and contexts instead of losing that knowledge over time.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; reads ~/.codex paths.

This is fstamatelopoulos/cerefox's own configuration. It tells Claude Code how to work on cerefox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cerefox configures →

not rated 19repo changed 6d ago B scan 13,284 tokens original Apache-2.0
View source ↗ fstamatelopoulos/cerefox cerefox.org
Reuse

Borrowing it

Nothing to install: this file belongs to fstamatelopoulos/cerefox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fstamatelopoulos/cerefox/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/fstamatelopoulos/cerefox

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 cerefox CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fstamatelopoulos/cerefox/claude-md/github.svg)](https://agentmods.dev/instructions/fstamatelopoulos/cerefox/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fstamatelopoulos/cerefox/claude-md"><img src="https://agentmods.dev/badge/instructions/fstamatelopoulos/cerefox/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for cerefox CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fstamatelopoulos/cerefox/claude-md"><img src="https://agentmods.dev/badge/instructions/fstamatelopoulos/cerefox/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13,284 This file is loaded in full into every session.
When invoked 13,284 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.13284 $0.13284
Opus 5.5 $0.05314 $0.05314
Sonnet 5.5 $0.02657 $0.02657
Haiku 4.5 $0.01328 $0.01328

Measured 6d ago against content hash 282f4293ba1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

cerefox CLAUDE.md scanned grade B with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| OpenAI Codex (CLI + desktop-app Codex threads) | Preferred: `cerefox configure-agent --tool codex` (local MCP, `~/.codex/config.toml`). Advanced (remote): `url` + `bearer_token_env_var` | Local: **verified 2026-10-08**

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. **AI agents / Edge Functions** — callers (GPT Actions, remote MCP, curl) present the **Cerefox access token** (`cfx_pat_…`, iter-28E) as `Authorization: Bearer`. Every data Edge Function runs `--no-verify-jwt` and val
CLAUDE.md · 530 lines

How it starts

The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cerefox - Project Guide

What Is This

Cerefox is a user-owned knowledge memory layer for AI agents. It stores curated Markdown documents in Supabase (Postgres + pgvector), supports hybrid search (FTS + semantic), and exposes everything via MCP and REST so any AI agent can read and write.

Cerefox is asynchronous shared memory, not a message bus. It solves the persistent context problem: knowledge written in one context is findable in any other, dissolving boundaries between agents, sessions, human and machine, and across time. It does not handle real-time agent-to-agent communication; protocols like A2A handle that. Cerefox handles persistent memory.

Single-user, open-source (Apache 2.0), designed to be cheap/free to operate. See docs/research/vision.md for the full project vision.

Tech Stack

  • Language: TypeScript via Bun (CLI, web server, local MCP server, build/release scripts, Edge Functions). The Python implementation was fully removed at v1.0.0 (iter-28G) — only the SQL schema assets under src/cerefox/db/ remain (they are not Python).
  • Database: PostgreSQL 16+ with pgvector (Supabase free tier or local Docker)
  • Embeddings: OpenAI text-embedding-3-small (768-dim, cloud API, default) or the local ONNX nomic-embed-text-v1.5 (768-dim, CEREFOX_EMBEDDER=local — Cerefox Local only, shipped at v1.0.0); Fireworks AI is roadmap (not wired); Edge Functions handle embedding server-side for agents (cloud path)
  • Web framework: Hono on Bun/Node (TypeScript), in packages/memory — served by cerefox web.
  • Web UI: React + TypeScript SPA (Mantine UI, TanStack Query, Vite); served at /app/
  • CLI: commander (TypeScript) in @cerefox/memory; resource-verb shape (v0.9.0).
  • Local MCP server: @cerefox/memory npm package (Node ≥24 / Bun ≥1.0); single artifact growing to host CLI + web server + ingestion in future iterations
  • Shared TS modules: _shared/{config,db-client,db-status,embeddings,mcp-tools}/ — imported by both Edge Functions (Deno) and local server (Node/Bun) via structural typing
  • Package management: bun workspaces for TS
  • Testing: bun test (TypeScript) — the only test runner as of v0.9.0 (pytest retired; tests/**/*.py deleted)
  • Type-checking: bun run typecheck — tsc --noEmit for _shared + packages/memory, tsc -b for the frontend (a plain --noEmit there checks nothing)

Read the full file on GitHub · 530 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. 6d ago Changed · +1 lines · +39 tokens per session 282f4293ba1d
  2. 20d ago Changed · +91 tokens per session 22ce6bb726d6
  3. 28d ago Changed · -1 lines · +107 tokens per session 4b6cb0bef279
  4. 1mo ago Changed · -2 tokens per session c726b39dc836
  5. 1mo ago Changed · +82 tokens per session 11a50ff8bc80
  6. 1mo ago Changed · +1 lines · +216 tokens per session 309159f19001
  7. 1mo ago Changed · +1 lines · +284 tokens per session b4c6df5b4dcf
  8. 1mo ago Changed · +15 lines · +232 tokens per session e88cf7618e60
  9. 1mo ago Changed · +39 tokens per session 68143c8e0778
  10. 1mo ago First seen · 513 lines · 12,196 tokens per session scan B 34470b997134

Subscribe to this mod's changes

cerefox CLAUDE.md is an instructions file published in the GitHub repository fstamatelopoulos/cerefox (19 stars, last pushed 4d ago), licensed Apache-2.0. It adds 13,284 tokens to every session, about $0.0531 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

PythonRAG and vectorsai-knowledge-basehybrid-searchmcppgvector
Related

cerefox CLAUDE.md compared with instructions from other repositories

cerefox CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cerefox CLAUDE.mdfstamatelopoulos/cerefoxInstructions file194d agoApache-2.0B13,284Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode