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 skills add gongyijie85/mattpocock-skills-dsh-zh --skill grilling-zhgit clone --depth 1 https://github.com/gongyijie85/mattpocock-skills-dsh-zhWrote 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/skills/gongyijie85/mattpocock-skills-dsh-zh/grilling-zh)<a href="https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/grilling-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/grilling-zh/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/skills/gongyijie85/mattpocock-skills-dsh-zh/grilling-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/grilling-zh.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 | $0.00050 | $0.00518 |
| Opus 5.5 | $0.00020 | $0.00207 |
| Sonnet 5.5 | $0.00010 | $0.00104 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
grilling-zh 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 1mo 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
持续盘问用户，直到达成共识。将整个过程建模为一棵 design tree（设计树）：每个决策都会分支成挂在其下的各个决策。
以 rounds（轮次） 的方式推进这棵树。frontier（前沿） 是所有前提条件已经确定、可以 现在就 提出的决策——这些问题无需猜测你尚未听到的答案。每一轮提出整个 frontier 上的全部问题：为每个问题编号，并给出你推荐的答案。然后等待用户回答，再进行下一轮。
按轮次格式化如下：
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
---
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
用户每一轮的回答都会重塑这棵树：已确定的决策把 frontier 向外推进，并解锁依赖它们的提问。重新计算 frontier，然后提出下一轮问题。某个问题的答案如果依赖于本轮仍处于开放状态的另一个问题，它应属于_更靠后_的轮次，而不是本轮。
查找_事实_是你的职责，永远不是用户的。当 frontier 上的某个问题需要来自环境（文件系统、工具等）的事实时，派遣一个 sub-agent 去查明；不要向用户询问任何你自己能查到的东西。不要因此阻塞：一次进行中的探查属于尚未确定的前提条件，所以只有它下游的问题需要等待 sub-agent 回报；现在就提出 frontier 上其余的问题。_决策_属于用户：把每个决策交还给用户，然后等待。
当 frontier 为空时，本次会话即告完成：design tree 的每个分支都已遍历，没有任何遗留的静默假设。在用户确认我们已达成共识之前，不要据此采取行动。
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.
- 1mo ago First seen · 29 lines · 50 tokens per session scan A fe4908114ff9
grilling-zh is a skill published in the GitHub repository gongyijie85/mattpocock-skills-dsh-zh (8 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 518 once invoked, about $0.0002 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 2026-09-11.
Other skills, from other repositories
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
promentor
A tool that turns a software project into a hands-on course in the style of an MIT course. It can produce lessons, code walkthroughs, practical labs, behavior tests, grading, explanations, and AI reviews.
dsh-skill-dev
A specialist review agent for software that handles purchasing, suppliers, payments, or spending approvals.
hook-development
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "wire command hooks", "use ${PLUGINROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStart, SubagentStop…
init
Set up a minimal AGENTS.md (and optionally skills and hooks) for this repo. Use when the user asks to "initialize the project", "generate AGENTS.md", "set up project instructions", or runs /init.