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/foxzool/openlarkWrote 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/foxzool/openlark/pstack-models)<a href="https://agentmods.dev/rules/foxzool/openlark/pstack-models"><img src="https://agentmods.dev/badge/rules/foxzool/openlark/pstack-models/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/foxzool/openlark/pstack-models"><img src="https://agentmods.dev/badge/rules/foxzool/openlark/pstack-models.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 | $0.00249 | $0.00249 |
| Opus 5.5 | $0.00100 | $0.00100 |
| Sonnet 5.5 | $0.00050 | $0.00050 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
pstack-models 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 today.
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
pstack model configuration. One line per role.
inherit-parent or auto as a value: the role runs on the parent chat model (omit Task model). Alias entries in a panel list still count toward its fan-out.
不用 Claude 或 GPT，只用 Cursor、免费或 Grok 模型，也永远不退回 skill 默认值。
budget: inherit-parent (parent chat model only; no Claude, no GPT)
feature, refactoring: inherit-parent bug-fix: inherit-parent perf-issue: inherit-parent hillclimb: inherit-parent judgment and prose: inherit-parent hardest tasks: inherit-parent how explorer: inherit-parent how explainer: inherit-parent why investigators: inherit-parent why synthesizer: inherit-parent reflect tooling: inherit-parent reflect judgment, divergent, synthesizer: inherit-parent arena runners: inherit-parent, inherit-parent arena cross-judge pool: inherit-parent, inherit-parent swarm workers: inherit-parent architect runners: inherit-parent, inherit-parent interrogate reviewers: inherit-parent, inherit-parent
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.
- today First seen · 26 lines · 249 tokens per session scan A 64392579af1b
pstack-models is a cursor rule published in the GitHub repository foxzool/openlark (105 stars, last pushed today), licensed Apache-2.0. It adds 249 tokens to every session, about $0.0010 per session on Opus 5.5. 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 2026-10-18.
Other cursor rules, from other repositories
assistant-registration
A standard for registering webhook-based notifications, such as alerts, daily reports, and reminders, in a central assistant configuration system. A webhook is a URL that receives automated messages from another program.
cursor-capabilities
A set of Cursor Agent rules written in Chinese that maps common requests to tools and workflows.
Swift编码风格
A set of Swift coding rules covering formatting, naming, immutable values, error handling, and concurrency. Swift is Apple's programming language for apps and other software.
no-hardcoded-urls
A coding rule that prevents frontend files from containing hardcoded portal domain URLs and requires shared URL constants instead.
Go安全规范
A set of Go programming rules written in Chinese that covers secret handling, security scanning, and timeout control with contexts.
Python安全规范
A small set of Python security rules covering secret storage and code scanning. Python is a programming language, and Bandit is a tool that checks Python code for common security problems.