central-intelligence CLAUDE.md

central-intelligence CLAUDE.md is an instructions file for coding agents from AlekseiMarchenko/central-intelligence. It costs 379 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Central Intelligence, a system that stores and retrieves information for AI agents. The project includes a local memory service and several client packages.

In plain words
What is it for?
Use them to route tasks such as remembering facts, investigating bugs, discussing product ideas, or deploying changes through the project's memory and skill system.
Why use it?
They tell the agent when to load, recall, save, or delete memories and which specialized workflow to use for different requests.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/alekseimarchenko/central-intelligence/claude-md
Clone the repo
git clone --depth 1 https://github.com/AlekseiMarchenko/central-intelligence

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 central-intelligence CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alekseimarchenko/central-intelligence/claude-md.svg)](https://agentmods.dev/instructions/alekseimarchenko/central-intelligence/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alekseimarchenko/central-intelligence/claude-md"><img src="https://agentmods.dev/badge/instructions/alekseimarchenko/central-intelligence/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 379 This file is loaded in full into every session.
When invoked 379 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00379 $0.00379
Opus 5 $0.00189 $0.00189
Sonnet 5 $0.00076 $0.00076
Haiku 4.5 $0.00038 $0.00038

Measured 4d ago against content hash e19c7eb2c0f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

central-intelligence 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 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.

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.

CLAUDE.md · 37 lines

What it actually says

Central Intelligence

Persistent memory API for AI agents. Monorepo with packages: api, mcp-server, cli, local, node-sdk, python-sdk, openclaw-skill.

CI Local Memory

At the start of every session, call the context tool from CI Local to load relevant memories.

When the user asks things like:

  • "what do you know about..." → call recall with their query
  • "remember that..." → call remember to store it
  • "forget the one about..." → call forget on the matching memory
  • "what have I told you before" → call recall with a broad query
  • "transfer from ChatGPT" → call transfer_chatgpt with action "transfer_paste"

Always show the user what memories were found and their source (which tool they came from).

Skill routing

When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.

Key routing rules:

  • Product ideas, "is this worth building", brainstorming → invoke office-hours
  • Bugs, errors, "why is this broken", 500 errors → invoke investigate
  • Ship, deploy, push, create PR → invoke ship
  • QA, test the site, find bugs → invoke qa
  • Code review, check my diff → invoke review
  • Update docs after shipping → invoke document-release
  • Weekly retro → invoke retro
  • Design system, brand → invoke design-consultation
  • Visual audit, design polish → invoke design-review
  • Architecture review → invoke plan-eng-review
  • Save progress, checkpoint, resume → invoke checkpoint
  • Code quality, health check → invoke health
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. 4d ago First seen · 37 lines · 379 tokens per session scan A e19c7eb2c0f5

Subscribe to this mod's changes

central-intelligence CLAUDE.md is an instructions file published in the GitHub repository AlekseiMarchenko/central-intelligence (3 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 379 tokens to every session, about $0.0019 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 2026-08-31.

Related

Other instructions, from other repositories