What is cf-memory-plugin AGENTS.md?

Project instructions for cf-memory, a service that stores information in Cloudflare and recalls it across agent sessions. It includes setup, credentials, server tools, and command-line examples.

Use it to remember and recall information, list or retrieve stored memories, ingest message files, create namespaces, and export or delete memory.

It helps an agent retain facts and conversation information after a session ends instead of starting with an empty context each time.

How hansakoch/cf-memory-plugin configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hansakoch/cf-memory-plugin. 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/hansakoch/cf-memory-plugin/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hansakoch/cf-memory-plugin

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hansakoch/cf-memory-plugin/agents-md/github.svg)](https://agentmods.dev/instructions/hansakoch/cf-memory-plugin/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hansakoch/cf-memory-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/hansakoch/cf-memory-plugin/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hansakoch/cf-memory-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/hansakoch/cf-memory-plugin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 691 This file is loaded in full into every session.

When invoked 691 The same file — it is already loaded in full.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5.1	$0.00691	$0.00691
Opus 5	$0.00345	$0.00345
Sonnet 5	$0.00138	$0.00138
Haiku 4.5	$0.00069	$0.00069

Measured 7d ago against content hash 76e587161c64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cf-memory-plugin AGENTS.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 7d 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.

AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cf-memory — Agent Memory via Cloudflare

Persistent semantic memory across sessions. GitHub

Install

pip install git+https://github.com/hansakoch/cf-memory-plugin.git
cf-memory doctor  # verify

Credentials

export MCP_CLOUDFLARE_API_KEY="token-with-agent-memory-permission"
export CF_ACCOUNT_ID="your-account-id"
export CF_MEMORY_NAMESPACE="hermes"
export CF_MEMORY_PROFILE="alfred"

MCP Server (any harness)

cf-memory serve        # 10 tools
cf-memory serve --slim # remember + recall only

Tools: remember, recall, list_memories(type, session_id), get_memory, delete_memory, ingest, summary, list_namespaces, create_namespace, delete_namespace

CLI

cf-memory remember "fact"
cf-memory recall "query"
cf-memory list --type fact --session my-session --limit 20
cf-memory export --format json -o backup.json
cf-memory export --format markdown --type fact -o facts.md
cf-memory get <id>
cf-memory delete <id>
cf-memory ingest messages.json --session-id my-session
cf-memory summary

Harness Configs

Grok CLI (~/.grok/config.toml):

[mcp_servers.cf-memory]
command = "cf-memory"
args = ["serve"]
[mcp_servers.cf-memory.env]
MCP_CLOUDFLARE_API_KEY = "token"
CF_ACCOUNT_ID = "account"
CF_MEMORY_NAMESPACE = "hermes"
CF_MEMORY_PROFILE = "alfred"

Hermes (profile config.yaml):

mcp:
  cf-memory:
    url: http://127.0.0.1:9120
    auth: { type: none }
    timeout: 30
    capabilities: [remember, recall, ingest, summary]

Start: cf-memory a2a --port 9120

Claude Code: claude mcp add cf-memory -- cf-memory serve

Cursor/OpenClaw: Add to .cursor/mcp.json or openclaw.json:

{"mcpServers": {"cf-memory": {"command": "cf-memory", "args": ["serve"],
  "env": {"MCP_CLOUDFLARE_API_KEY": "...", "CF_ACCOUNT_ID": "...", "CF_MEMORY_NAMESPACE": "...", "CF_MEMORY_PROFILE": "..."}}}}

Auto-Ingest (add to your system prompt)

Read the full file on GitHub · 92 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.

7d ago First seen · 92 lines · 691 tokens per session scan A 76e587161c64

Subscribe to this mod's changes

cf-memory-plugin AGENTS.md is an instructions file published in the GitHub repository hansakoch/cf-memory-plugin (1 stars, last pushed 8d ago), licensed MIT. It adds 691 tokens to every session, about $0.0035 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 2026-09-04.

Memory and context

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

cf-memory-plugin: Instructions file for Codex