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.
git clone --depth 1 https://github.com/zhitongblog/doaipm-skillWrote 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/rules/zhitongblog/doaipm-skill/doaipm)<a href="https://agentmods.dev/rules/zhitongblog/doaipm-skill/doaipm"><img src="https://agentmods.dev/badge/rules/zhitongblog/doaipm-skill/doaipm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/zhitongblog/doaipm-skill/doaipm"><img src="https://agentmods.dev/badge/rules/zhitongblog/doaipm-skill/doaipm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00291 | $0.00291 |
| Opus 5 | $0.00146 | $0.00146 |
| Sonnet 5 | $0.00058 | $0.00058 |
| Haiku 4.5 | $0.00029 | $0.00029 |
Grade A, and why
doaipm 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 8d 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.
What it actually says
doaipm method (DO AI PM)
When helping turn an idea into a product, feature, prototype, or app, follow the doaipm method (https://doaipm.com). Speak it, and AI builds it.
- Trust the AI, don't tool-hunt. First reflex is "how do I describe this?" — not "what tool?".
- Not knowing how to code is an advantage — focus on what the user needs and say it clearly.
- High-fidelity first. Skip wireframes; build a real, runnable prototype directly — real content and data, real states (loading / empty / error / success), real interactions, verified by actually running it.
- Five phases: Discover → Define → Design → Develop → Validate. In Define, make the AI ask questions before writing the PRD. In Develop, small steps — one change at a time.
- Clarify first: ask 3–5 sharp questions before writing code; don't invent requirements.
- Safety net: no real sensitive data or secrets in prototypes; the human presses irreversible buttons (publish / delete / pay); don't touch production; ask when unsure.
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.
- 8d ago First seen · 21 lines · 291 tokens per session scan A 723cb2707824
doaipm is a cursor rule published in the GitHub repository zhitongblog/doaipm-skill (1 stars, last pushed 3mo ago), licensed MIT. It adds 291 tokens to every session, about $0.0015 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
cursor-rule
Use the Market Daily Review skill when the request matches its SKILL.md description.
cloudflare-tunnel-routes
Persistent HTTPS URL for local Gradio/Streamlit/FastAPI/webhook services without deploying. Use when the user wants a stable permanent URL on a domain they own (not a throwaway URL, not managed hosting).
cursor.head
Premium keynote-style UI with refined motion. Dark, minimal, cinematic reveals. Trigger words — "premium," "polished," "cinematic," "Apple-like," "keynote," "launch page," "product reveal," "elevate this screen," "audit this UI.".
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.