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.
npx agentmods add instructions/nikmcfly/shared-vault-template/claude-mdgit clone --depth 1 https://github.com/nikmcfly/shared-vault-templateWrote 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.
[](https://agentmods.dev/instructions/nikmcfly/shared-vault-template/claude-md)<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>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 | $0.01023 | $0.01023 |
| Opus 5 | $0.00511 | $0.00511 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00102 | $0.00102 |
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.
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
- Filenames:
YYYY-MM-DD Title.md(or justTitle.mdif it's a long-lived doc) - Linking: Every new note links to at least one existing note via
[[wikilinks]]. Orphan notes die. - Frontmatter: Every note starts with YAML frontmatter:
--- tags: [] created: YYYY-MM-DD author: a / b / both related: [[]] ---
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.
- 3d ago First seen · 93 lines · 1,023 tokens per session scan A d92b2598162b
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.
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.
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.
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.
SECOND-BRAIN CLAUDE.md
Claude Code instructions for ericediger/SECOND-BRAIN, covering second brain, tech stack, project structure, api routes and obsidian file conventions.
obsidian-mind AGENTS.md
AGENTS.md instructions for breferrari/obsidian-mind, covering obsidian mind, hooks, commands, memory and reaching this vault from another repo.
superbrain CLAUDE.md
Instructions for m3talux/superbrain, covering superbrain — repository rules, non-negotiables, public-facing content, versioning and workflow.