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 skills/liutod/scream-code/makenpx skills add LIUTod/scream-code --skill makegit clone --depth 1 https://github.com/LIUTod/scream-codeWrote 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/liutod/scream-code/make)<a href="https://agentmods.dev/skills/liutod/scream-code/make"><img src="https://agentmods.dev/badge/skills/liutod/scream-code/make.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.01943 |
| Opus 5 | $0.00010 | $0.00971 |
| Sonnet 5 | $0.00004 | $0.00389 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade A, and why
make-skill 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 yesterday.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make Skill: 从上下文提炼 Skill
用户调用了 /make-skill。你的任务是通过对话引导用户,把当前会话中解决问题的方式沉淀为一个可复用的 Scream Code Skill,并安装到插件中心。
激活参数
本次激活的参数:
$ARGUMENTS
initialRequest:用户输入/make-skill时附带的一句话描述,可能为空。
工作方式
这不是一次性任务。你需要通过多轮对话澄清以下信息,每一轮只问一个问题,等用户回答后再进入下一阶段:
- Skill 类型(
workflow/code-pattern/troubleshooting/tool-chain/custom) - Skill 名称(kebab-case)
- 这个 Skill 主要解决什么问题
- 希望重点关注哪些内容
- 生成草案并确认安装
阶段判断
根据当前对话历史判断你处于哪个阶段:
- 阶段 0:本 Skill 刚激活,还没有问过任何问题。先分析会话上下文和
initialRequest,然后用AskUserQuestion询问 Skill 类型。 - 阶段 1:已经确定了 Skill 类型,但还没有确定名称。根据类型和上下文建议一个 kebab-case 名称,用
AskUserQuestion询问用户是否接受或修改。 - 阶段 2:已经确定了名称,但还没有明确解决的问题。根据上下文总结一句话描述,用
AskUserQuestion询问用户是否接受或修改。 - 阶段 3:已经确定了问题,但还没有明确关注重点。给出 2-4 个关注重点建议,用
AskUserQuestion让用户选择或输入。 - 阶段 4:类型、名称、问题、重点都已确定。调用
MakeSkillPlanTool生成草案,展示给用户,并用AskUserQuestion询问是否确认安装。 - 阶段 5:用户已确认安装。调用
MakeSkillApplyTool写入插件中心。
如何判断“已确定”:历史消息中已经有你提出的 AskUserQuestion 以及用户给出的明确回答(或选择了你建议的选项)。
每轮提问规范
除非处于阶段 4/5,否则每轮必须也只允许使用一次 AskUserQuestion。不要直接用普通文本提问,这样无法给用户结构化选项。
阶段 0:询问 Skill 类型
先分析当前会话上下文,判断最可能想沉淀什么。给出 2-4 个建议选项,不要列出全部 5 种。把最相关的放在最前面,并标记 (Recommended)。
示例问题:
{
"questions": [
{
"question": "根据刚才的会话,你想把什么沉淀成 Skill?",
"header": "类型",
"options": [
{ "label": "Code pattern (Recommended)", "description": "把 React 表单验证的代码模式提炼为可复用模板" },
{ "label": "Workflow", "description": "把解决表单验证问题的步骤沉淀为流程" },
{ "label": "Troubleshooting", "description": "把常见验证错误排查过程沉淀为诊断指南" }
],
"multi_select": false
}
]
}
注意:系统会自动添加 "Other" 选项,不要自己添加。如果用户想选未列出的类型(如 tool-chain 或 custom),他们会通过 Other 输入。
阶段 1:询问 Skill 名称
根据已确定的类型和上下文,建议一个 kebab-case 名称。用 AskUserQuestion 让用户接受、修改或自己输入。
示例:
{
"questions": [
{
"question": "建议把这个 Skill 命名为 react-form-validate,是否接受?",
"header": "名称",
"options": [
{ "label": "使用 react-form-validate (Recommended)", "description": "简洁直观,符合 kebab-case" },
{ "label": "换一个名称", "description": "我给出其他建议" },
{ "label": "我自己输入", "description": "手动指定名称" }
],
"multi_select": false
}
]
}
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.
- yesterday First seen · 195 lines · 20 tokens per session scan A 39b71a67a39d
make-skill is a skill published in the GitHub repository LIUTod/scream-code (137 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,943 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
memmachine-memory
Use when an agent or model needs durable project, user, or session context from MemMachine, needs to save information to MemMachine memory, has requests involving mem-cli, memmachine, or memmachineclient, has insufficient conversation context, or is tempted to search local files for prior context that should come from…
external-memory-plugin
Develop, adapt, review, test, and troubleshoot Nexent external memory provider plugins, including plugin.yaml manifests, searchable and ingestible provider protocols, error mapping, network-isolated unit tests, deployment configuration, and Mem0-based examples. Use when adding a new external memory vendor, changing an…
agent-memory-onboarding
On-demand provisioning guide for a Memmy GUI task that fully connects an explicitly named local Agent: discover its active history store, install or remove its rendered Memmy Skill, bootstrap a scan boundary, persist a validated automatic-sync recipe, and verify GUI-visible readiness.
session-summaries
What the chat right-panel session summary shows, what it costs, and how to make a session summarize well. Load when the user asks about the session summary panel, why a summary looks wrong or empty, or how to turn it on.
update-setup
One-time setup wizard for the memmy upgrade skill. Triggers: setup update, configure update, 切设置更新, 初始化更新.