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/aliasunder/vault-onboarding/agents-mdgit clone --depth 1 https://github.com/aliasunder/vault-onboardingWhat 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 | $0.01846 | $0.01846 |
| Opus 5 | $0.00923 | $0.00923 |
| Sonnet 5 | $0.00369 | $0.00369 |
| Haiku 4.5 | $0.00185 | $0.00185 |
Grade A, and why
vault-onboarding AGENTS.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 yesterday.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
This file provides guidance to Claude Code (claude.ai/code), Codex CLI, and other AI agents when working with code in this repository.
Project Overview
vault-onboarding is an Agent Skills-standard onboarding skill that bootstraps an agent collaboration system into an Obsidian vault. It runs a branching conversational interview and scaffolds memory files, session protocols, task boards, generated skills, and per-client instruction files — all tailored to the user's setup and needs.
Distribution: npx skills add aliasunder/vault-onboarding.
Repository Structure
vault-onboarding/
README.md
skills/vault-onboarding/ # The installable skill payload — everything under
# here (and only this) ships via `npx skills add`
SKILL.md # Interview flow + generation orchestration
references/ # 7 best-practice reference files (loaded on demand)
vault-organization.md # Folder taxonomy, tags, linking, schemas
memory-system.md # Three-layer model, entry policies, growth
protocol-guide.md # Session protocol, board conventions
client-instructions.md # Per-client loading matrix
generated-skills-guide.md # Skill parameterization
progressive-adoption.md # Adoption tiers, evolution paths
setup-verification.md # Per-client verification
assets/ # 20 asset files (16 templates + 4 skills)
templates/memory/ # 5 About Me/ templates
templates/instructions/ # 8 client-specific instruction templates
templates/protocol.md # Genericized session protocol
templates/tasks-board.md # 5-lane Kanban
templates/onboarding-progress.md # Checkpoint file
skills/ # 4 generated skill templates
session-start.md
session-end.md
remember.md
project-role.md
scripts/
validate-structure.ts # Structural coherence checks (run by CI)
render-social-preview.ts # Renders social-preview.svg → .png via Puppeteer
.github/workflows/validate.yml # Runs the structural checks on PR + push
.github/social-preview.svg + .png # Repo social card (SVG source + committed render)
.github/fonts/ # Fonts embedded by the render script
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.
- yesterday First seen · 136 lines · 1,846 tokens per session scan A 0b0bfef6fda5
vault-onboarding AGENTS.md is an instructions file published in the GitHub repository aliasunder/vault-onboarding (1 stars, last pushed 5d ago), licensed MIT. It adds 1,846 tokens to every session, about $0.0092 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
flowix CLAUDE.md
Instructions for text2future/flowix, covering claude.md, 命令, dev / prod 并存打包, macos 本地生产包 ad-hoc 签名 and macos 发布流水线（developer id 直分发 + notarization）.
gingugu AGENTS.md
Instructions for gingugu/gingugu, covering agents.md, memory protocol, session start, during the session and credentials.
mnemonic memory-files.instructions.md
Instructions for modeled-information-format/mnemonic, covering memory file guidelines (mif level 3), required frontmatter fields, optional temporal fields, optional provenance fields and memory types.
mnemonic plugin-files.instructions.md
Instructions for modeled-information-format/mnemonic, covering claude code plugin file guidelines, commands (commands/.md), skills (skills//skill.md), agents (agents/.md) and general guidelines.
vant AGENTS.md
Instructions for dhaupin/vant, covering agents.md — vant agent guide, what is vant?, your job, brain router interface and middleware chain.
gingugu CLAUDE.md
Instructions for gingugu/gingugu, covering gingugu, quick reference, what this repo is, critical rules and reasoning & agentic operation (opus 4.8).