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/datasift-ty-personal/siftstack/vendor-directory-buildernpx skills add DataSift-Ty-Personal/SiftStack --skill vendor-directory-buildergit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWrote 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/datasift-ty-personal/siftstack/vendor-directory-builder)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/vendor-directory-builder"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/vendor-directory-builder.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 | $0.00208 | $0.02240 |
| Opus 5 | $0.00104 | $0.01120 |
| Sonnet 5 | $0.00042 | $0.00448 |
| Haiku 4.5 | $0.00021 | $0.00224 |
Grade A, and why
vendor-directory-builder 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 5d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendor Directory Builder
What this produces
A filterable Excel workbook the user can actually work from:
- Directory tab: one row per provider, with contact info, service area, a "Serves " flag, ratings, license/credential status, strengths, the source signal (who recommended them / how they surfaced), cautions, a confidence read, and a top-pick star.
- Top Picks tab: the single best, verified, market-serving option per category, plus runners-up and a small summary block.
- Methodology tab: how the list was built and a reusable vetting playbook, so the user (or their team) trusts the list and can keep filling it.
- Optional reference tab(s): domain-specific "obscure but critical" data the job needs (e.g., the utility districts that own the water main and set tap fees, permit offices, licensing boards). Add these whenever the use case has a hidden layer.
scripts/build_directory.py generates all of this from one JSON config, so the format
is consistent every time and you never hand-format a spreadsheet.
Why this method works (read this, it drives every decision)
Two weak signals combine into one strong one:
- Community recommendations are social proof from people who actually paid. When an investor in a local Facebook group answers "who's a good plumber?" by naming a company, that's a referral backed by a real transaction, far better than an ad. The single strongest signal is cross-validation: when two or more different people independently name the same provider, call that one first.
- Public records are independent verification. Reviews, license boards, BBB, and the company's own site confirm the provider exists, is licensed where required, is still in business, and serves the target area, none of which a forum post proves.
Neither alone is enough. A forum name with no paper trail might be someone's cousin; a 5-star Google result might be a national lead-gen shop that never picks up. The value of this skill is doing both and being honest about what couldn't be confirmed.
What ships with it
7 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.
- 5d ago First seen · 168 lines · 208 tokens per session scan A 61b702d2b944
vendor-directory-builder is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed yesterday), licensed MIT. It adds 208 tokens to every session and 2,240 once invoked, about $0.0010 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
dcf-model
Build discounted cash flow valuation workbooks in Excel.
audit-xls
Audit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this…
google-drive-sheets
Find, read, export, edit, and manage the user's Google Drive, Docs, Sheets, and Slides through per-user OAuth.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
excel-basic-statistics-and-routing
Skill "excel-basic-statistics-and-routing" from OpenSenseNova/SenseNova-Skills, covering skill steps, 保存区间提取与汇总结果 and 保存筛选与统计结果.
dynamic-percentage-and-large-file-analysis
根据文件行数动态切换大文件处理策略(Parquet转换),通过逐行扫描或列匹配提取关键指标并计算占比、均值等统计量,最终输出结构化Excel报告及可视化图表。.