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 deep-prospectinggit 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/deep-prospecting)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/deep-prospecting"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/deep-prospecting/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/deep-prospecting"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/deep-prospecting.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 | $0.00155 | $0.09679 |
| Opus 5.5 | $0.00062 | $0.03872 |
| Sonnet 5.5 | $0.00031 | $0.01936 |
| Haiku 4.5 | $0.00015 | $0.00968 |
Grade A, and why
deep-prospecting 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.
This is a copy
88% identical to deep-prospecting-v4 — 72 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 727 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Prospecting
Deep prospecting is the process for identifying and verifying the heirs/decision-makers (owner/heir/executor) behind a distress lead, and determining who must actually sign for the property to sell. Core philosophy: "When everyone hits a wall, we bring a shovel."
Two Paths - Pick API-First
| Path | When | Reliability | Cost/record |
|---|---|---|---|
| Primary: API-Based Heir Resolution (recommended) | You have Enformion/Endato + Trestle API access | HIGH - heir set comes from the provider's relationship graph; deterministic; nothing inferred | ~$2.30-3.00 |
| Fallback: 3-Site Browser Waterfall | No API access, or API returns thin data | MEDIUM - manual assembly from obituaries/people-search sites; slower; hallucination risk | $0-0.15 + your time |
Use the Primary Path below first. It replaces hours of manual obituary and genealogy hunting with a handful of API calls and produces a grounded heir set, a signing analysis, and scored phones. Drop to the browser waterfall only when the API can't resolve a record.
Grounding rule (both paths): every name, address, phone, and relationship must come from a source you actually retrieved (an API response or a page you read). Never infer or fabricate an heir. Surface conflicts; do not resolve them by guessing.
When to Use This Skill
- Skip trace returned no usable phone numbers
- Called 3+ attempts with no contact
- Vacant mailing address discovered
- Return mail (bad address)
- Probate cases (often only docket number available)
- Entity/LLC ownership (need actual decision-maker)
- Conflicting owner/address information in public records
Input Requirements
User provides any combination of:
- Property address
- Owner name (full or partial)
- Filing/docket number
- Probate case information
- Foreclosure notice details
- Any distress record data
Workflow Overview
For a deceased owner with API access, go straight to the Primary Path: API-Based Heir Resolution (Steps A-E) below, then produce the signing analysis - it covers identification, family tree, signers, and scored phones in a few API calls. The numbered flow below is the manual/fallback sequence and the deeper research levels.
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 · 727 lines · 155 tokens per session scan A e535c928c097
deep-prospecting is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 155 tokens to every session and 9,679 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to deep-prospecting-v4, differing in 72 lines, and is treated as a copy.
deep-prospecting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deep-prospectingDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 155 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |