memarium-plugin: Instructions file for Claude Code

CLAUDE.md

memarium-plugin CLAUDE.md is an instructions file for Claude Code from june9593/memarium-plugin. It costs 833 tokens per session, scanned A, original, MIT.

A contributor guide for the memarium-plugin codebase, documenting its product boundary, file layout, safety rules, data contracts, skills, and hooks. It is written as instructions for coding agents and contributors.

In plain words
What is it for?
Use it when modifying memarium-plugin and need to understand its memory workflows, command-line code, hooks, tests, and documentation.
Why use it?
It gives agents and maintainers a shared reference for how the project is structured and what changes are allowed.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions AGENTS.md; mentions Codex.

This is june9593/memarium-plugin's own configuration. It tells Claude Code how to work on memarium-plugin 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 memarium-plugin configures →

Reuse

Borrowing it

Nothing to install: this file belongs to june9593/memarium-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/june9593/memarium-plugin/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/june9593/memarium-plugin

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 memarium-plugin CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/june9593/memarium-plugin/claude-md/github.svg)](https://agentmods.dev/instructions/june9593/memarium-plugin/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/june9593/memarium-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/june9593/memarium-plugin/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 memarium-plugin CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/june9593/memarium-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/june9593/memarium-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 833 This file is loaded in full into every session.
When invoked 833 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00833 $0.00833
Opus 5 $0.00417 $0.00417
Sonnet 5 $0.00167 $0.00167
Haiku 4.5 $0.00083 $0.00083

Measured 5d ago against content hash 1f3f3dcc2777, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

memarium-plugin 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 5d 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

memarium-plugin — contributor / agent guide

Product boundary

This repository is the standalone digest + recall half of memarium. The optional npm CLI handles cross-device session transport, aggregation, and resume. Read README.md for installation and the public workflow. Read versions from package.json, not a status note.

The plugin CLI and hooks do pure I/O; they do not call an LLM. The model's reasoning and memory writing happen in the current session through the skills. Do not add a background inference service as part of a bug fix.

Layout

  • skills/ — four canonical workflows: digest, context, recall, and retro.
  • hooks/ — SessionStart primer and one advisory Stop assessment.
  • src/commands/ — CLI dispatch targets, including the read-only retro gate.
  • src/spool/ — autonomous source scan, single-Markdown rendering, and import.
  • src/_shared/ — modules mirrored from npm; @sync-from names the canonical file.
  • src/memory/, src/entity/, src/qa/ — typed memory and derived knowledge.
  • bin/memarium-plugin.js — committed bundle used by installed plugins.
  • tests/ — isolated Vitest fixtures; docs/ — tracked bilingual Astro site.

Safety and data contracts

  • Shared spool identity is {tool}:{sessionId}. Preserve IDs during title/path changes; render one .md per session, not raw JSON/JSONL siblings.
  • Keep npm and plugin mirrors aligned for shared adapters, types, project identity, writer/index contracts, and manifest/TOC changes. Plugin-only memory and hook logic stays here.
  • memory/ is shared by multiple projects. Never wipe a whole subtree or reset the index as a shortcut for a project-scoped repair. Inspect and back up data before destructive work; do not run a live sync/digest without user approval.
  • Core/procedural/pinned edits, protected supersession, and trust elevation use memory-propose. Proposals are local-only and require human review. Never approve your own proposals or silently turn a refusal into another attempt.
  • Live/partial retro entries leave sourceSessions: []; those IDs are consumed receipts for the batch digest, not general-purpose session provenance.
  • finalize can initialize Git, commit allowlisted files, and push when a remote is configured. Never replace its whitelist with repository-wide staging.

Read the full file on GitHub · 66 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. 5d ago First seen · 66 lines · 833 tokens per session scan A 1f3f3dcc2777

Subscribe to this mod's changes

memarium-plugin CLAUDE.md is an instructions file published in the GitHub repository june9593/memarium-plugin (1 stars, last pushed 5d ago), licensed MIT. It adds 833 tokens to every session, about $0.0042 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 2026-09-08.

Related

Other instructions, from other repositories

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

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 · 7,126 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 · 4,469 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