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/deal-analyzernpx 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.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 | $0.00137 | $0.06688 |
| Opus 5 | $0.00068 | $0.03344 |
| Sonnet 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 5d 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.
- 5d 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 (21 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 6,688 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
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…