shared-vault-template CLAUDE.md

shared-vault-template CLAUDE.md is an instructions file for coding agents from nikmcfly/shared-vault-template. It costs 1,023 tokens per session, scanned A, original, MIT.

A template of instructions for an AI assistant working in a shared vault, a folder used as a common knowledge base. It explains the people involved, where information belongs, and how notes should be written.

In plain words
What is it for?
Use it to configure a shared workspace with team context, folder conventions, author labels, and note-taking guidance.
Why use it?
It gives the assistant shared context and consistent rules for handling technical, business, personal, and creative information. It also helps identify who is speaking when two people use the same vault.

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/nikmcfly/shared-vault-template/claude-md
Clone the repo
git clone --depth 1 https://github.com/nikmcfly/shared-vault-template

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 shared-vault-template CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikmcfly/shared-vault-template/claude-md.svg)](https://agentmods.dev/instructions/nikmcfly/shared-vault-template/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nikmcfly/shared-vault-template/claude-md"><img src="https://agentmods.dev/badge/instructions/nikmcfly/shared-vault-template/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,023 This file is loaded in full into every session.
When invoked 1,023 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 $0.01023 $0.01023
Opus 5 $0.00511 $0.00511
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00102 $0.00102

Measured 3d ago against content hash d92b2598162b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shared-vault-template 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for Claude

This file is the system prompt for the AI assistant working with this vault. Every Claude session that opens this folder reads it first. Edit the bracketed placeholders to fit your team.

Who we are

Two people who share a business and a life. We use this vault as our shared brain — for the company, for our personal projects, and for everything in between.

[Replace this section with:

  • A one-line description of your business
  • Key metrics or context the AI should always remember
  • Names or pseudonyms for the two partners — we use @a and @b]

Who's talking

When it's unclear which of us a note came from or who's asking, ask: "Which of us is this?"

Hints (edit these to fit your domains):

  • Technical work, code, servers → @a
  • Design and creative practice → @b
  • Content, brand, marketing → could be either

An explicit author tag in the message — "A:" or "B:" — overrides these hints.

Where things live

00-inbox/         raw capture, split by sender (mine/ and hers/)
01-business/      the company
  strategy/         OKRs, planning, long-term thinking
  clients/          leads, accounts, relationships
  finance/          budget, revenue, expenses (all financial data goes here, nowhere else)
  operations/       SOPs, processes, internal docs
  content/          marketing, posts, ideas, brand voice
  product/          roadmap, specs, features
  meetings/         call notes with dates
02-mine/          @a's personal zone
03-hers/          @b's personal zone
04-us/            shared life — travel, home, health, events, personal finance, goals
05-resources/     tools, contacts, references, templates

Note conventions

  1. Filenames: YYYY-MM-DD Title.md (or just Title.md if it's a long-lived doc)
  2. Linking: Every new note links to at least one existing note via [[wikilinks]]. Orphan notes die.
  3. Frontmatter: Every note starts with YAML frontmatter:
    ---
    tags: []
    created: YYYY-MM-DD
    author: a / b / both
    related: [[]]
    ---
    

Read the full file on GitHub · 93 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 · 93 lines · 1,023 tokens per session scan A d92b2598162b

Subscribe to this mod's changes

shared-vault-template CLAUDE.md is an instructions file published in the GitHub repository nikmcfly/shared-vault-template (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,023 tokens to every session, about $0.0051 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

cmds-llm-wiki AGENTS.md

Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.

johnfkoo951/cmds-llm-wiki · 14,302 tokens

cmds-llm-wiki CLAUDE.md

Schema and harness document for the CMDS LLM Wiki vault. Defines the 3-layer architecture (Raw Sources / Wiki / Schema), ingest-query-lint operations, file conventions, and frontmatter standards. This is the single source of truth for LLM behavior in this vault.

johnfkoo951/cmds-llm-wiki · 13,893 tokens

awesome-second-brain CLAUDE.md

Instructions for superuser-pal/awesome-second-brain, covering awesome second brain, rules, skills & capabilities, prompts & strategies and custom slash commands.

superuser-pal/awesome-second-brain · 2,653 tokens

SECOND-BRAIN CLAUDE.md

Claude Code instructions for ericediger/SECOND-BRAIN, covering second brain, tech stack, project structure, api routes and obsidian file conventions.

ericediger/SECOND-BRAIN · 1,427 tokens

obsidian-mind AGENTS.md

AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.

breferrari/obsidian-mind · 1,145 tokens

superbrain CLAUDE.md

Instructions for m3talux/superbrain, covering superbrain — repository rules, non-negotiables, public-facing content, versioning and workflow.

m3talux/superbrain · 566 tokens