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 dispo-deal-blastgit 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/dispo-deal-blast)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/dispo-deal-blast"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/dispo-deal-blast/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/dispo-deal-blast"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/dispo-deal-blast.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 | $0.00129 | $0.01563 |
| Opus 5.5 | $0.00052 | $0.00625 |
| Sonnet 5.5 | $0.00026 | $0.00313 |
| Haiku 4.5 | $0.00013 | $0.00156 |
Grade A, and why
dispo-deal-blast 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispo Deal Blast
Send one deal to the buyers who actually buy at that price, then turn what comes back into an asset you keep.
Most dispo lists are a spreadsheet of everyone who ever bought a house. This builds the opposite: a small list of people whose recorded purchases say they buy this kind of property at this kind of price, reached on a number they have heard from before.
Use when someone says "blast this deal", "who do I send this to", "text my buyers", or "set up dispo texting".
Requirements
- Python 3.10+ (the bundled script is stdlib only)
- A CRM or data source with deed-level investor transactions
- An SMS provider with numbers you own, and a compliance posture you understand
Everything below is the method. None of it needs a key to read, and the bundled calculator runs on plain Python.
The chain
registry -> recency gate -> price band -> copy -> staged blast -> phonebook
- Registry. Sweep investor transactions in your county. Hydrate each property for the deed owner, because search results usually carry no name. Dedupe by mailing address. Resolve LLC principals.
- Recency gate. Re-run the sweep bounded to the last 12 months. Recency decides WHO is on the list; full history decides WHAT they buy.
- Price band. Each buyer's real purchase range, p10 to p90, from priced sales only.
- Copy. One message per buyer, audited before anything is staged.
- Staged blast. Everything lands as HELD. Release is a separate human act.
- Phonebook. Classify every reply, suppress the outs, keep the buyers.
The rules that matter
Each of these cost a real failure to learn. They are the actual content of this skill; the code around them is easy.
The semantic trap that ruins the list
Transaction labels describe the LAST SALE, not the current owner.
pending,wholesale,wholetail,rentalmean the investor still holds, so the current owner IS the buyer. These are your targets.flipmeans the exit already happened, so the current owner is a retail homebuyer. The investor you want is the last-sale SELLER.
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.
- 2mo ago First seen · 148 lines · 129 tokens per session scan A 899ae670defa
dispo-deal-blast is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 129 tokens to every session and 1,563 once invoked, about $0.0005 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 2026-09-04.
dispo-deal-blast compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dispo-deal-blastDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 129 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |