Starcat: Skill for Claude Code

.claude/skills/starcat-weekly-import/SKILL.md

starcat-weekly-import is a skill for Claude Code, Codex from starcat-app/Starcat. It costs 153 tokens per session (1,852 once invoked), scanned A, original, MIT.

A tool for turning news, project lists, and other bulk text into verified GitHub repository links, then adding confirmed repositories to Starcat Weekly. It checks that each link belongs to the actual project owner.

In plain words
What is it for?
Use it to find official GitHub repositories mentioned in AI news or project lists, fill in missing repository links, remove duplicates, and submit a confirmed batch to Starcat Weekly.
Why use it?
It removes the manual work of finding the right repository and avoids adding unrelated pages, third-party projects, or guessed links. It also waits for confirmation before making a lasting import.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: reads .claude/ paths.

This is starcat-app/Starcat's own configuration. It tells Claude Code and Codex how to work on Starcat itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Starcat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to starcat-app/Starcat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/starcat-app/Starcat/main/.claude/skills/starcat-weekly-import/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/starcat-app/Starcat

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for starcat-weekly-import

README.md
[![agentmods](https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-weekly-import/github.svg)](https://agentmods.dev/skills/starcat-app/starcat/starcat-weekly-import)
Your own site
<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-weekly-import"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-weekly-import/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.

agentmods 80×15 button for starcat-weekly-import

Your own site · 80×15
<a href="https://agentmods.dev/skills/starcat-app/starcat/starcat-weekly-import"><img src="https://agentmods.dev/badge/skills/starcat-app/starcat/starcat-weekly-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,852 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 3
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 70
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00153 $0.01852
Opus 5 $0.00077 $0.00926
Sonnet 5 $0.00031 $0.00370
Haiku 4.5 $0.00015 $0.00185

Measured 6d ago against content hash 7cae04dff4a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

starcat-weekly-import 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 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/submit_import.py, scripts/test_submit_import.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/starcat-weekly-import/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Starcat Weekly 情报采集

把非结构化文本转换为经核验的 GitHub owner/repo 列表,并在用户确认后一次性提交。当前默认分类是 ai_intelligence;分类必须来自服务端允许人工录入的固定来源目录,禁止自行创造分类。

硬性边界

  • 先解析、搜索、核验和展示候选,得到用户明确确认后才能调用写接口。
  • 写入前调用 GET /internal/sources?manual_import=true,只使用响应中 enabled=truemanual_import_enabled=true 的来源。
  • 未指定分类时使用 ai_intelligence。如果用户指定的分类不在允许列表中,停止提交并解释原因。
  • 只提交确定为 GitHub 仓库的 owner/repo;组织主页、用户主页、GitHub Topics、Issue、Release、文件路径和搜索页都不是仓库。
  • 新闻标题是检索线索,不是仓库名:对于没有显式 GitHub URL 的每一条输入,必须联网定位发布主体和实际项目;不要要求用户自行补链接,也不要按标题字面猜测仓库。
  • 仅提交与新闻主体直接对应的官方仓库。若新闻是闭源产品、云服务、论文、仅在 Hugging Face/Civitai 发布的模型或硬件发布,而没有该主体的官方 GitHub 仓库,记为“未找到”;不得用同名第三方实现、上游项目、配套节点或辅助工具替代。
  • 一个输入批次最多提交 200 个仓库。批内按小写 owner/repo 去重,但保留用户原文标题和来源链接。
  • 用户未明确说明“测试”时,一律固定使用生产服务 https://starcat-api.fly.dev,并通过 X-SC-Svc: weekly 路由到 Weekly,不得接受或推断其他 Base URL。
  • 生产 Admin Key 只从 supports/starcat-api/.envWEEKLY_ADMIN_API_KEYS 读取;多值时使用第一个非空 Key。不得要求用户导出生产 Key,也不得在 Skill、命令或输出中显示 Key。
  • 只有用户明确说明“测试”时才使用 --test,此时才允许通过 --base-url / STARCAT_WEEKLY_BASE_URLSTARCAT_WEEKLY_ADMIN_KEY 注入测试配置。
  • POST 只代表持久化入队成功,不代表 GitHub 数据已补全;拿到 batch_id 后必须轮询批次终态。

工作流

1. 提取显式仓库

从文本中优先提取:

  • https://github.com/{owner}/{repo}
  • github.com/{owner}/{repo}
  • 独立出现且上下文明确的 {owner}/{repo}

规范化时移除 .git、结尾 /、query、fragment,以及仓库后面的 /issues/releases/tree/... 等路径,只保留前两个 path segment。

2. 联网甄别新闻并搜索缺失地址

把没有显式 GitHub URL 的条目视为新闻线索,逐条联网检索。先确认新闻提及的是开源项目、产品/服务、论文、模型还是硬件,再定位其发布方及实际项目;不要假设新闻标题与仓库名相同。搜索式优先使用:

"项目名" GitHub
"项目名" 官方 GitHub
"公司名" "项目名" GitHub

优先级依次为官方组织仓库、项目官网链接的 GitHub、维护者公开仓库。名称相似但证据不足时标记为“待确认”,不要猜测并提交。

3. 核验真实性

每个候选至少检查:

  1. GitHub 仓库页面真实存在,且 canonical 地址与候选一致;
  2. 仓库 README、描述、官网或发布者与输入文本指向同一项目;
  3. 不是 fork 冒充上游、镜像、占位仓库或同名无关项目;
  4. 仓库与新闻主体直接对应;新闻仅提及模型权重、论文、云服务或产品时,不得以同作者的配套节点、示例、上游或第三方实现替代。
  5. 新闻描述的是闭源产品、论文或模型但没有官方 GitHub 仓库时,明确记为“未找到”,不要用第三方实现代替。

4. 展示并请求确认

提交前给出紧凑表格:原始条目、规范化 owner/repo、GitHub URL、核验结论、依据。把“已确认”“待确认”“未找到”分开;只把“已确认”加入拟提交列表。

明确询问用户是否提交该列表到指定来源。用户修改列表后重新展示最终集合;不得把之前被排除的候选带回。

Read the full file on GitHub · 112 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 6d ago Changed · +1 lines · -4 tokens per session 7cae04dff4a6
  2. 11d ago First seen · 111 lines · 157 tokens per session scan A f4f22b7372fc

Subscribe to this mod's changes

starcat-weekly-import is a skill published in the GitHub repository starcat-app/Starcat (159 stars, last pushed yesterday), licensed MIT. It adds 153 tokens to every session and 1,852 once invoked, about $0.0008 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 2026-08-30.