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/deep-prospecting-v5npx skills add DataSift-Ty-Personal/SiftStack --skill deep-prospecting-v5git 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-v5)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/deep-prospecting-v5"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/deep-prospecting-v5.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 5.1 | $0.00141 | $0.02940 |
| Opus 5 | $0.00071 | $0.01470 |
| Sonnet 5 | $0.00028 | $0.00588 |
| Haiku 4.5 | $0.00014 | $0.00294 |
Grade A, and why
deep-prospecting-v5 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 6d 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 — 160 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 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."
Version 5 (2026-07-29). The heir engine changed. v4 resolved relatives through the Enformion/Endato Person Search. v5 replaces that with SmartSkip, measured head to head on live Knox and Blount County records. Enformion's person search is retired from this skill. Enformion BusinessV2 is retained, for entity owners only, where nothing else works.
Why the change, with the numbers that drove it:
- Coverage. Enformion returned zero relatives on 6 of 12 owners tested. SmartSkip returned relatives on 12 of 12.
- Phones. Enformion's
relativesSummarycarries names but no phone numbers. Every relative you actually want to call costs another billed search. SmartSkip returns the relatives and their phones in one batch row.- Cost. For a 100-owner batch with 682 relatives: SmartSkip plus Tracerfy = $15.90. The Enformion equivalent = $78.20. That is 4.9x.
- Precision. On the validation record, SmartSkip returned exactly 3 relatives and all 3 appeared in the published obituary. Enformion returned 50 (a capped blob) plus out-of-state numbers that looked like wrong-person bleed.
What did NOT change: the research layer. SmartSkip is wrong about death (Gotcha 1). The obituary and web pass is now mandatory, not optional.
The v5 stack
| Stage | Tool | Cost | What it gives you |
|---|---|---|---|
| A. Relatives plus phones | SmartSkip bulk skip | $0.15/hit | The grounded people graph, with numbers |
| B. Gap-fill | Tracerfy | $0.02/record | Phones for relatives SmartSkip named but left phoneless (about 7%) |
| C. Death and relationship truth | Obituary / web research | free | Date of death, who actually died, true relationships |
| D. Dial scoring | TrestleIQ | $0.015/number | Dial tiers, line type, litigator risk |
| E. Entity owners only | Enformion BusinessV2 | ~$0.10 | LLC and trust principals (nothing else can do this) |
What ships with it
11 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.
- references/deed-analysis.md 4.1 KB
- references/entity-owners-enformion-business.md 2.2 KB
- references/google-dorking.md 2.5 KB
- references/obituary-web-research.md 3.4 KB
- references/smartskip-api.md 3.0 KB
- references/tracerfy-gap-fill.md 1.9 KB
- scripts/enformion_person_search.py 15 KB runs code
- scripts/parse_smartskip.py 8.1 KB runs code
- scripts/smartskip_trace.py 15 KB runs code
- templates/example-research-pack-ANONYMIZED.md 3.9 KB
- templates/research-pack-template.md 6.0 KB
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.
- 6d ago First seen · 160 lines · 141 tokens per session scan A 794841b05f28
deep-prospecting-v5 is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 2d ago), licensed MIT. It adds 141 tokens to every session and 2,940 once invoked, about $0.0007 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…