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 deal-analyzergit 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/deal-analyzer)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/deal-analyzer"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/deal-analyzer/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/deal-analyzer"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/deal-analyzer.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 | $0.00137 | $0.06688 |
| Opus 5.5 | $0.00055 | $0.02675 |
| Sonnet 5.5 | $0.00027 | $0.01338 |
| Haiku 4.5 | $0.00014 | $0.00669 |
Grade A, and why
deal-analyzer 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deal Analyzer — Full Property Analysis Pipeline
Orchestrate a complete investment property analysis from raw photos and an address through to ARV, rehab cost, deal math, and offer strategy. This skill ties together the real-estate-comping skill (for valuation) and the rehab-estimator skill (for renovation costs) into one streamlined pipeline.
The user should walk away with a clear picture: what's it worth, what does it cost to fix, what should I offer, and which exit strategy makes more money.
Pipeline Overview
INTAKE → PHOTO ANALYSIS → COMP ANALYSIS → REHAB ESTIMATE → DEAL MATH → OFFER & EXIT STRATEGY → DELIVERABLES
Each phase feeds into the next. Data flows forward — comp findings inform rehab scope, rehab costs feed deal math, and deal math drives the offer.
Phase 1: Intake
Collect from the user:
Required:
- Property address (full: street, city, state, zip)
- Property photos OR condition description (photos strongly preferred)
Helpful (ask if not provided):
- Square footage / bed / bath / year built (can be researched if address is given)
- Number of units (default: 1)
- Occupied? (Y/N) — affects hold time and eviction/vacancy considerations
- Purchase price or contract price (needed for deal math)
- Current "As Is" Value (if known — useful for wholesaling spread analysis)
- Known issues (roof, foundation, HVAC, etc.)
- Financing structure (supports multiple loans — see Phase 5 for details):
- First Mortgage / primary lender terms (amount or LTV, rate, points)
- Second Mortgage / Gap Fund / Private Money (if applicable)
- Miscellaneous financing or liens (if applicable)
- If not provided, defaults to 100% LTV hard money on purchase + rehab as a single first mortgage
- Exit strategy preference (or analyze both flip and wholetail)
- Evaluator name (for report attribution)
- Property description (e.g., "Off Market Lead", "MLS Listing", "Driving for Dollars")
If the user only provides an address: Use web search and browser tools to look up the property on Zillow, Redfin, or county records to gather:
- GLA, bed/bath, year built, lot size
- Any available listing photos (for condition assessment)
- Tax records for annual property tax amount
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 · 512 lines · 137 tokens per session scan A 9426e15fc2d1
deal-analyzer is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (23 stars, last pushed 23d ago), licensed MIT. It adds 137 tokens to every session and 6,688 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 2026-08-30.
deal-analyzer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deal-analyzerDataSift-Ty-Personal/SiftStack | Skill | 23 | 23d ago | MIT | A | 137 | Claude Code |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 3d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |