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 DataSift-Ty-Personal/SiftStack --skill contractor-call-sheetgit 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/contractor-call-sheet)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/contractor-call-sheet"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/contractor-call-sheet/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/datasift-ty-personal/siftstack/contractor-call-sheet"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/contractor-call-sheet.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 | $0.00212 | $0.01101 |
| Opus 5.5 | $0.00085 | $0.00440 |
| Sonnet 5.5 | $0.00042 | $0.00220 |
| Haiku 4.5 | $0.00021 | $0.00110 |
Grade A, and why
contractor-call-sheet 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 2mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contractor Call Sheet
What this produces
Two deliverables that turn a vetted directory into same-day outreach:
- A one-page call sheet (printable HTML): the top picks grouped by trade, each with phone, the one-line reason it's the pick, what to confirm on the call, and empty Status / Notes / Next-step columns to work down. Call-first (cross-validated) providers are flagged at the top.
- Personalized first-contact messages: a short, human text or voicemail for each top pick, varied so they don't read like a mass blast, plus the vetting-call question script for when someone picks up.
The call sheet is generated by scripts/build_call_sheet.py (deterministic). The messages
are drafted by you (the model) from references/outreach-templates.md, personalized per
provider. That part shouldn't be a template mail-merge; it should sound like a real person.
Why it's split this way
The sheet is mechanical (same columns every time), so a script does it perfectly and free. The outreach is the opposite: a message that lands is specific ("saw you do a lot of investor work in Maryville") and varied, which is a judgment task, not a merge. Doing the merge in a script would produce the exact spammy sameness we're trying to avoid.
Workflow
1. Get the input
Ideally the Excel from vendor-directory-builder (it has the columns this expects:
Category, Company, Phone, Serves, Why, Cautions, Source, Confidence, Top Pick). Any
spreadsheet or pasted list with company names + phones also works: map the columns
mentally and pass what you have.
2. Build the call sheet
python scripts/build_call_sheet.py <directory.xlsx> <call_sheet.html> [--all]
By default it includes only the top picks (starred rows), the people to call first.
Pass --all to include every provider. It groups by trade, puts cross-validated
"call-first" providers in a banner at the top, and leaves Status / Notes / Next-step
columns blank to work down. Open or deliver the HTML (it prints cleanly to one or two
pages). The script's header shows the market and date if present in the file.
What ships with it
2 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.
- 2mo ago First seen · 87 lines · 212 tokens per session scan A f582bf9b88a1
contractor-call-sheet is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 212 tokens to every session and 1,101 once invoked, about $0.0008 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 2026-08-30.
contractor-call-sheet compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| contractor-call-sheetDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 212 | Claude Code, Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| gogopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 20 | Claude Code, Codex |
| boxNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 14 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 6d ago | MIT | A | 33 | Claude Code, Codex |
| material-organizerOrkas-AI/Orkas | Skill | 9.0k | yesterday | MIT | A | 3 | Claude Code, Codex |
| recipe-save-email-attachmentsgoogleworkspace/cli | Skill | 32k | 4d ago | Apache-2.0 | A | 20 | Claude Code, Codex |