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 flaqai/backlink_skills --skill backlink-batch-expansiongit clone --depth 1 https://github.com/flaqai/backlink_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/flaqai/backlink_skills/backlink-batch-expansion)<a href="https://agentmods.dev/skills/flaqai/backlink_skills/backlink-batch-expansion"><img src="https://agentmods.dev/badge/skills/flaqai/backlink_skills/backlink-batch-expansion/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/flaqai/backlink_skills/backlink-batch-expansion"><img src="https://agentmods.dev/badge/skills/flaqai/backlink_skills/backlink-batch-expansion.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 | $0.00073 | $0.01763 |
| Opus 5.5 | $0.00029 | $0.00705 |
| Sonnet 5.5 | $0.00015 | $0.00353 |
| Haiku 4.5 | $0.00007 | $0.00176 |
Grade A, and why
backlink-batch-expansion 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 27d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
外链批量扩量
将大量来源整理成一个可持续更新的批量提交候选库，再从总库自动生成执行批次。核心目标是减少重复研究、重复查重和重复制表，同时明确区分候选、已核验、已提交和已收录。
在 backlink-expansion-matrix 端到端流程中，本技能只负责批量线筛选、分类和候选池，不直接修改最终工作簿；完成后交给 backlink-workbook-delivery 统一去重、冻结批次和制表。单独调用本技能且用户明确要求工作簿时，仍可按下述交付规则直接生成。
适用边界
- 适用于工具目录、产品导航、创业项目库、社区资料页和资源推荐页等批量提交机会。
- 文章投稿线单独处理，不把必须写正式文章或新闻稿的入口混入批量提交表。
- 候选表不是提交授权，也不证明入口有效、链接可控、提交成功、页面公开或已被搜索引擎收录。
- 未经用户授权，不注册、不登录、不付款、不提交、不联系站方。
- 若筛选阶段不做逐站人工核验，必须把交付物明确标为“待执行候选”，并把确认成本交给执行人员在真实提交时记录。
启动前冻结范围
确认并记录：目标品牌、候选来源、现有工作簿、目标是“现有表补足到某个总数”还是“另建一个固定数量的新批次”、批次大小、批量提交线的排除条件、是否允许轻量公开页检测、是否允许子代理并行、输出目录和最终列名。用户已给出这些信息时直接执行，不重复询问。
“现有 A 条补足到 B 条”表示保留原记录并新增 B-A 条，不得解释成另外生成 B 条。若现有记录已经属于某个已导出批次，保留原有批次关系；新增记录只填补当前目标或进入尚未冻结的新批次。
工作流程
- 建立总候选库：保留原始来源，不直接从多个来源分别生成最终工作簿。
- 分片研究：只有用户明确要求并行时，才把互不重叠的来源或候选范围交给子代理。先登记分片编号、负责代理、来源范围、输出文件和状态。每个子代理只写自己的中间文件，不能同时修改总库或最终工作簿。
- 单点合并：主代理统一标准化域名和 URL、全局查重、分类、分配品牌并维护状态。
- 轻量入口识别：按授权检查公开首页、页脚和少量常见路径；不扫描全站，不绕过验证码或安全验证。没有发现入口不等于网站无机会，应转入备用池。
- 一次分类：费用、入口类型、品牌适配、候选池和风险只在总库中判断一次。只有找到明确提交入口或满足用户的宽松收录规则时才进入可执行池；仅有首页、联系页或待确认入口的记录进入备用池。
- 自动分批：批次大小作为参数。已导出的批次编号冻结；改变批次大小只影响尚未分配的记录。
- 机械导出：从总库生成每个批次的工作簿，避免逐批重新研究、查重和制表。
- 回写结果：执行人员提交时记录真实费用、登录要求、强制回链、有效性和提交结果，供下一批调整排序和排除规则。
候选来源可以包含 Semrush 优先候选、竞品引荐域名、历史候选表、资源推荐页、导航站出站域名和公开外链清单。来源只决定检查顺序，不替代具体入口判断。
详细字段、去重、费用和状态规则见 references/schema-and-rules.md。
开始并行前复制 assets/shard-registry.csv 作为分片登记表。合并总候选库后运行 scripts/validate_candidate_pool.py --input <总候选库.csv>，检查必需字段、固定枚举、URL、费用分类和重复项；修正错误后再生成批次。
候选保留规则
批量线以扩量为先，允许注册、登录、验证码、人工审核、较长产品资料和 nofollow。排除以下对象：
- 必须发布正式文章或新闻稿；
- 强制回链、强制徽章或存在明确删除风险；
- 成人、赌博、恶意软件、明显垃圾或失效网站；
- 没有任何可识别提交入口，且没有保留价值。
链接实力、自然流量和竞品覆盖主要决定检查顺序，不作为严格淘汰条件。高权重通用网站不自动等于可提交平台；小型垂直目录也不因权重低而自动删除。
费用与证据
- 明确存在可用的免费基础路线才能进入免费组；允许同站另有可选付费升级。
- 明确收费进入付费组。
- 免费路线本身是否存在尚未确认时，不得因为“可能免费”或“未看到收费”写成免费。若交付结构只有“免费”和“付费”，暂放付费组，并在投递条件中写“费用待确认”；统计时不得把它与明确付费混为一谈。
- 保存具体入口 URL 和简短证据说明。搜索结果、公开页面或可读表单只证明候选存在，不证明链接一定可控或会被收录。
工作簿要求
What ships with it
4 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.
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.
- 27d ago First seen · 81 lines · 73 tokens per session scan A 7168661f9841
backlink-batch-expansion is a skill published in the GitHub repository flaqai/backlink_skills (789 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 1,763 once invoked, about $0.0003 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 2026-09-24.
Other skills, from other repositories
after-action-report
Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons. Use this skill whenever the user wants to run a postmortem, retrospective, AAR, or after-action review on any past event.…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
import-sop
Import agency procedures as role-assigned SOP steps with approval gates. "import our launch checklist".
beta-program-management
Running closed and open betas that produce real signal. Beta participant selection, structured feedback collection, beta-to-GA decision criteria, and the difference between soft-launch (no structure, no signal), kitchen-sink (everyone in, no actionable feedback), and structured beta (calibrated cohort, intentional…
okr-design
OKR design as actually shipped, not as conference-talk theory. Outcome statements that drive decisions, key results that measure the right thing, scoring discipline, mid-quarter recalibration, and the difference between sandbagged OKRs (always 100%) and aspirational OKRs (always 30%) and stretch OKRs (genuine ambition…