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 kennyzir/7deer_skills --skill seo-backlink-submittergit clone --depth 1 https://github.com/kennyzir/7deer_skillsWrote 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/kennyzir/7deer_skills/seo-backlink-submitter)<a href="https://agentmods.dev/skills/kennyzir/7deer_skills/seo-backlink-submitter"><img src="https://agentmods.dev/badge/skills/kennyzir/7deer_skills/seo-backlink-submitter/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/kennyzir/7deer_skills/seo-backlink-submitter"><img src="https://agentmods.dev/badge/skills/kennyzir/7deer_skills/seo-backlink-submitter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.00983 |
| Opus 5 | $0.00028 | $0.00491 |
| Sonnet 5 | $0.00011 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
seo-backlink-submitter 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Backlink Submitter
这个 Skill 使用统一的安全模型处理单目录和批量目录：默认只读取本地配置、验证输入并输出 dry-run 计划，不访问目录网站；只有命令中明确加入 --submit 才允许浏览器访问和点击提交。
目标数据
按 targets/README.md 创建本地 JSON：
{
"name": "网站名称",
"url": "https://example.com",
"description": "网站描述",
"email": "[email protected]",
"category": "Developer Tools",
"tags": ["AI", "Agents", "Automation"]
}
name、url、description、email 是必需字符串；category 和 tags 可选。URL 必须是无内嵌凭据的绝对 HTTP(S) URL。
单目录流程
先运行默认 dry-run；它不会导入 Playwright，也不会访问网络：
python scripts/submit_to_directory.py \
--directory https://directory.example/submit \
--target targets/example-com.json
人工核对目标和目录后，显式加入 --submit 才执行真实提交：
python scripts/submit_to_directory.py \
--directory https://directory.example/submit \
--target targets/example-com.json \
--submit
兼容入口 scripts/quick_submit.py 接受完全相同的参数并转发到上述逻辑；它同样默认 dry-run，不含硬编码目录。
批量流程
目录文本每行一个 HTTP(S) URL，空行和 # 注释会被忽略。可以使用 references/directories.txt，也可以按项目维护自己的文件。
默认只输出离线批量计划：
python scripts/batch_submit.py \
--target targets/example-com.json \
--directories references/directories.txt
核对计划后，显式加入 --submit 才逐项打开浏览器并尝试提交：
python scripts/batch_submit.py \
--target targets/example-com.json \
--directories references/directories.txt \
--submit
批量入口复用单目录入口的目标验证和真实提交函数，不会先默认联网检测再自动提交。
可选的只读目录检测
需要主动检查页面是否存在表单、登录、付费或反向链接要求时，可明确运行联网检测器：
python scripts/check_directory.py https://directory.example/submit
检测结果只是页面启发式判断，不会点击提交。
提交安全条件
- 没有
--submit时，单目录、批量和兼容入口都不得访问网络。 - 真实提交前，页面必须成功匹配并填写
name、url、description、email四个字段；缺少任何一个都会关闭浏览器、返回错误且不查询或点击提交控件。 category是可选字段，未匹配不会阻止四个必需字段完整的提交。submit_triggered只表示脚本点击了提交控件，不代表目录方接收、审核、发布或产生了反向链接。- 登录、验证码、付费墙或不受支持的表单需要人工处理；不要绕过访问控制。
- 凭据和项目目标文件不得写入仓库；当前
.gitignore已排除targets/下的项目数据。
输出与退出状态
- dry-run 输出
not_submitted和待处理目录，不写结果文件。 - 真实单目录成功点击时输出
submit_triggered。 - 批量真实提交逐项输出
submit_triggered或error；任一错误会使批量命令非零退出。 - 输入错误返回退出码 2；浏览器、依赖、字段或提交控件错误返回非零状态并打印明确原因。
What ships with it
9 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.
- references/directories_list.md 14 B
- references/directories.txt 1.1 KB
- scripts/batch_submit.py 3.7 KB runs code
- scripts/check_directory.py 3.7 KB runs code
- scripts/quick_submit.py 347 B runs code
- scripts/submit_to_directory.py 7.4 KB runs code
- targets/README.md 1.8 KB
- tests/test_batch_and_compat.py 3.8 KB runs code
- tests/test_submit_to_directory.py 4.1 KB runs code
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.
- 4d ago Changed · +3 lines · -2 tokens per session 725ebfadb0da
- 13d ago First seen · 99 lines · 58 tokens per session scan A 14640cc2e17f
seo-backlink-submitter is a skill published in the GitHub repository kennyzir/7deer_skills (313 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 983 once invoked, about $0.0003 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.
Other skills, from other repositories
verify
Build/launch/drive recipe for verifying apps/docs changes at runtime (demos, docs pages, llms.txt).
dev-browser
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
browser-debug-setup
One-time setup for a persistent debug browser on 127.0.0.1:9222 for dev-browser --connect. Use when browser work is needed but no reusable debug browser is running yet.
quality-engineering-playwright-cli
Standardizes token-efficient browser automation via playwright-cli. Use for web verification, navigation, and capturing snapshots/logs.
agent-browser-issue
Open a concise GitHub follow-up for reusable browser-use limitations. Use when browser automation is blocked by a likely tool-side issue that is worth fixing separately, especially for clicks, dropdowns, file inputs, focus traps, or other repeatable agent/browser failures.
proxy-setup
Set up test-proxy-recorder for any Playwright project. Covers the proxy CLI (test-proxy-recorder --port --dir), package.json scripts for the three-service architecture (UI app → proxy → backend API), playwright.config.ts webServer block pointing to /control, per-test fixtures using playwrightProxy.before(page…