mem-graph CLAUDE.md

mem-graph CLAUDE.md is an instructions file for coding agents from GoVanAI/mem-graph. It costs 921 tokens per session, scanned A, original, MIT.

A project instruction file for mem-graph, a repository connected to Cognitive OS, an agent framework for managing project knowledge and practice. It defines the project's scope and required startup checks before substantial work.

In plain words
What is it for?
Use it when reviewing, changing, or recording mem-graph or Cognitive OS work, including selecting the correct project scope and reading the required practice guide.
Why use it?
It prevents the coding agent from using the wrong project context or skipping required governance and progress-tracking steps.

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/govanai/mem-graph/claude-md
Clone the repo
git clone --depth 1 https://github.com/GoVanAI/mem-graph

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 mem-graph CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/govanai/mem-graph/claude-md.svg)](https://agentmods.dev/instructions/govanai/mem-graph/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/govanai/mem-graph/claude-md"><img src="https://agentmods.dev/badge/instructions/govanai/mem-graph/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 921 This file is loaded in full into every session.
When invoked 921 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 $0.00921 $0.00921
Opus 5 $0.00461 $0.00461
Sonnet 5 $0.00184 $0.00184
Haiku 4.5 $0.00092 $0.00092

Measured 3d ago against content hash ba42165c7e7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mem-graph 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 3d 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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mem-Graph Project Instructions for Claude

This file adds repository-specific routing to the global Claude rules. It is a startup contract, not the source of live milestone state.

Before non-trivial mem-graph or Cognitive OS work, read and follow .agents/skills/mem-graph-practice/SKILL.md. Its vendor-neutral source is cognitive-os/agent-practice/practice.v1.json; generated host adapters must not be edited by hand.

Scope

Cognitive OS is a global, cross-project agent framework. This repository is its current additive proving ground and persistence substrate; it is not the framework's architectural boundary. Canonical tracker, scope-boundary, and optional role-record IDs are deployment-local and must come from operator or project configuration, not from this repository.

Use project_id=cognitive-os for Cognitive OS governance, experiments, policies, event evidence, roadmap work, and program state. Keep unrelated mem-graph substrate work in its applicable project scope. Cross-project availability never implies automatic applicability.

Mandatory Cognitive OS Bootstrap

Before reviewing, changing, or recording Cognitive OS work:

  1. Prefer cognitive_agent_bootstrap with project_id=cognitive-os, a narrow task query, include_canonical_content=true, and include_global=false unless global guidance is explicitly required. Supply canonical_ids only when the operator or project has configured tracker, scope-boundary, or role records; otherwise omit it and discover governing candidates. The bootstrap does not touch access tracking or write a receipt.
  2. Directly verify any candidate canonical records. When a tracker is resolved, read the roadmap and active artifacts it references before modifying implementation or judging milestone completion.
  3. Fetch selected records directly when their full content or authority still needs verification. A verified, operator/project-designated tracker—not a static onboarding example—is the authority for current program state.
  4. If the bootstrap tool is unavailable, use the dynamic fallback sequence: resolve configured canonical IDs or discover exact-project governing candidates; memory_get each resolved record; read referenced roadmap/artifacts; cognitive_policy_lookup for request_type/current_canonical_guidance; exact-project guidance search or diagnosis; and direct fetch of every selected record.

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 921 tokens per session scan A ba42165c7e7d

Subscribe to this mod's changes

mem-graph CLAUDE.md is an instructions file published in the GitHub repository GoVanAI/mem-graph (0 stars, last pushed today), licensed MIT. It adds 921 tokens to every session, about $0.0046 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

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

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.

github/spec-kit · 7,104 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 · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js 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