AIBootSAFE
An engineering playbook for AI coding agents. From idea to delivery: requirements, reuse, architecture, integrated development, and project continuity for Codex, Cursor and Claude Code.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Build beyond the first demo. Your AI agent’s engineering playbook — from idea to delivery.
English · 简体中文 Quick start · Usage & prompts · Skills & tools · Contribute
Turn ambitious ideas into thoughtfully engineered software.
AIBoot brings a shared engineering playbook to Codex, Cursor, and Claude Code: clarify requirements, research proven solutions, choose architecture, plan the work, build integrated features, and prepare a usable delivery. It gives your agent guidance for the whole journey, including future sessions and maintenance.
A shared core. Focused capability routes. Your own stack. Add the English guidance to your project's native instruction entry, then describe the outcome you want. Your coding tool provides execution, planning, Skills, MCP connections, session recovery, and permitted collaboration. AIBoot connects those capabilities to practical engineering decisions.
Great results come first. Invest in the analysis, design, documentation, and verification the product needs. Keep architecture and process grounded in actual users, constraints, and business value.
Why AIBoot
- Start with direction. Turn an idea into a clear scope, observable acceptance,
and an actionable development plan.
- Stand on proven foundations. Consider maintained libraries, existing
app
3600388b8225OBSERVED · 2026-10-13Install
Commands as the repository documents them. They are shown, not run.
git clone https://github.com/Liu-2026/AIBoot.git
git clone https://github.com/Liu-2026/AIBoot.git
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned | |
| cursor | mentioned |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
docs/assets/aiboot-hero.png
Gates applied: no_behavioural_pass.
3600388b8225full audit observations/trust-audit/skill/liu-2026__aiboot.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | 3600388b8225 | SAFE | B | 89 | first audit |
Questions
What does the AIBoot skill do?
An engineering playbook for AI coding agents. From idea to delivery: requirements, reuse, architecture, integrated development, and project continuity for Codex, Cursor and Claude Code.
Is AIBoot safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can AIBoot access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does AIBoot work with?
Its documentation mentions claude-code, codex and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (3600388b8225), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.