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 rules/yunbow/ai-dev-os-plugin-cursor/ai-dev-os-initgit clone --depth 1 https://github.com/yunbow/ai-dev-os-plugin-cursorWhat 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 | $0.00040 | $0.00682 |
| Opus 5 | $0.00020 | $0.00341 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
ai-dev-os-init 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 2d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Dev OS Setup Wizard
Execution Flow
1. Interview the User
- Tech stack (Next.js / Python / Go / etc.)
- Project scale (personal / team / enterprise)
- Existing rule files (.cursorrules, CLAUDE.md, .kiro/steering/, etc.)
2. Detect and Import Existing Rules
Scan the project for existing configuration and rule files:
| Source | Action |
|---|---|
.cursorrules |
Classify into L3-L4 |
Existing CLAUDE.md |
Convert to L3 guidelines |
Existing AGENTS.md |
Classify into L3-L4 |
.editorconfig |
Import formatting rules into L3 common/code.md |
.eslintrc / eslint.config.* |
Extract coding rules into L3 guidelines |
biome.json / biome.jsonc |
Extract lint/format rules into L3 guidelines |
ruff.toml / pyproject.toml [tool.ruff] |
Extract Python lint rules into L3 guidelines |
.prettierrc / prettier.config.* |
Import formatting config into L3 common/code.md |
tsconfig.json (strict settings) |
Reference in L3 common/code.md |
.github/workflows/*.yml |
Reference CI/CD patterns in L3 common/cicd.md |
Existing .cursor/rules/ |
Merge with AI Dev OS structure |
For each detected file:
- Read its content
- Extract rules that map to AI Dev OS guideline categories
- Present the extracted rules to the user for confirmation
- Write confirmed rules into the appropriate L3 guideline files
3. Generate Templates
Generate the following structure:
ai-dev-os/
├── 01_philosophy/
│ └── core-values.md # Minimal placeholder
├── 02_decision-criteria/
│ └── coding.md # 5-10 basic principles
├── 03_guidelines/
│ ├── common/
│ │ ├── code.md # Basic rules based on tech stack
│ │ ├── naming.md
│ │ └── security.md
│ └── frameworks/
│ └── [selected-stack]/
│ └── overview.md
└── 04_ai-frames/
└── cursor.md # Cursor-specific configuration
4. Generate .cursorrules
- Auto-insert references to the ai-dev-os directory
- Set up Specificity Cascade
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.
- 2d ago First seen · 76 lines · 40 tokens per session scan A 0be7381e976a
ai-dev-os-init is a cursor rule published in the GitHub repository yunbow/ai-dev-os-plugin-cursor (2 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 682 once invoked, about $0.0002 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 cursor rules, from other repositories
90-devops-deployment
Docker, CI/CD, AWS, Vercel, and VPS deployment rules.
00-global-architect
Global default behavior for the entire repository.
35-api-contracts
API versioning, contracts, and schema evolution rules.
45-environment-config
Environment configuration and secrets management rules.
50-rag-system
Retrieval-augmented generation rules.
55-data-model-versioning
Dataset versioning, model checkpoint management, and training reproducibility rules.