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/jetyu/snaptium/agents-mdgit clone --depth 1 https://github.com/jetyu/SnaptiumWhat 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 | $0.01040 | $0.01040 |
| Opus 5 | $0.00520 | $0.00520 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
Snaptium 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 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snaptium Agent Instructions
This file is the short, always-loaded entrypoint for AI coding agents.
Reference rule files
Follow these files when they are relevant to the task:
CLAUDE.md— coding behavior: think first, keep changes simple, make surgical edits, and verify.docs/DevGuide.md— Snaptium architecture, TypeScript rules, Electron boundaries, IPC, i18n, service layering, testing, and release checks.
Do not copy the full contents of those files here. Read them when the task touches their scope.
Core behavior
- Read the relevant project files before answering code questions or making changes.
- Do not guess from memory.
- State important assumptions before implementing.
- If ambiguity affects architecture, data safety, security, public behavior, or user data, ask before changing.
- For low-risk implementation details, choose the smallest reasonable solution and mention the assumption.
- Make the minimum necessary change.
- Do not add features that were not requested.
- Do not refactor unrelated code.
- Do not reformat unrelated files.
- Match the existing style of the touched files.
- Hard constraint: only use file naming and layering patterns already established in this repository. Do not invent a file type, suffix, or architectural layer that is neither defined by the project rules nor demonstrated by an existing repository precedent.
- Remove only unused code introduced by your own changes.
Snaptium architecture rules
- Snaptium is an Electron + Vue 3 + TypeScript app.
- Respect the Electron layer boundary: Renderer → Preload/Bridge → Main.
- Renderer must not access Node.js APIs directly.
- Renderer must use
window.electronAPIfor system capabilities. - IPC channels must be centralized in
electron/main/constants/ipc.constants.ts. - IPC input must be validated at the boundary.
- Main process services provide system capabilities.
- Renderer services should handle business orchestration.
- Avoid duplicate logic. Reuse existing
utils,services,shared, orcorecode before adding new helpers.
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 · 104 lines · 1,040 tokens per session scan A fd64fbe47b17
Snaptium AGENTS.md is an instructions file published in the GitHub repository jetyu/Snaptium (74 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,040 tokens to every session, about $0.0052 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 2026-08-30.
Other instructions, from other repositories
Knote AGENTS.md
Instructions for 1661169091kiwi/Knote, covering agents.md, 构建与验证约定（用户明确要求，所有会话必须遵守） and 测试说明.
vnote AGENTS.md
AGENTS.md instructions for vnotex/vnote, covering vnote agent development guide, prerequisites, setup, build commands and release build.
vnote CLAUDE.md
Claude Code instructions for vnotex/vnote, covering claude.md, project overview, build commands, setup (first time after clone) and configure + build (release).
notebookmd CLAUDE.md
Instructions for minhlucvan/notebookmd, covering notebookmd — project instructions, architecture, built-in plugins, key patterns and creating a report.
vscode source-code-organization.instructions.md
VS Code source code organization — layers, target environments, dependency injection, and folder structure conventions. Reference when adding new modules, services, or contributions.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.