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 commands/datasift-ty-personal/siftstack/analyze-dealgit 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/commands/datasift-ty-personal/siftstack/analyze-deal)<a href="https://agentmods.dev/commands/datasift-ty-personal/siftstack/analyze-deal"><img src="https://agentmods.dev/badge/commands/datasift-ty-personal/siftstack/analyze-deal.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 | $0.00008 | $0.00524 |
| Opus 5 | $0.00004 | $0.00262 |
| Sonnet 5 | $0.00002 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
analyze-deal 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.
What it actually says
Run the complete deal-analyzer skill workflow for the property specified by $ARGUMENTS.
Load the deal-analyzer skill from ${CLAUDE_PLUGIN_ROOT}/skills/deal-analyzer/SKILL.md and follow its pipeline:
-
Intake — Gather property details from the argument, uploaded photos, and any context the user has provided. If only an address is given, research the property online (Zillow, Redfin, county records) to get GLA, bed/bath, year built, and any available photos.
-
Photo Analysis — If the user has uploaded property photos, analyze them room-by-room following the condition assessment checklist. If no photos are available, note this and widen contingency.
-
Comp Analysis — Execute the full comping workflow using the real-estate-comping skill methodology. Generate comp Excel workbook.
-
Rehab Estimate — Execute the full rehab estimation using the rehab-estimator skill methodology. Feed in comp findings (Bucket B finishes, renovation premium). Generate rehab Excel workbook.
-
Deal Math — Calculate all-in costs for both flip and wholetail exits including financing, holding, buying, and selling costs. Use default cost assumptions from SKILL.md unless the user provides specific numbers. Calculate hold time dynamically: Rehab Duration + Bucket B median DOM + 30 days closing.
-
Offer Strategy — Calculate MAO using both the 75% Rule and 70% Rule. Compare exits using the Profit Per Month tiebreaker: if both exits are profitable, recommend whichever has higher profit/month (with $20K absolute profit override for full rehab). Present both options — the investor decides.
-
Deliverables — Present the in-context summary (including ARV confidence level with every ARV figure), then link all generated files. The output MUST end with the disclaimer: "This analysis is for educational and estimation purposes only. It does not constitute investment, financial, or legal advice. Actual costs, values, and returns may differ materially. Verify all assumptions with local professionals before making investment decisions."
If the user hasn't provided a purchase price, ask for it before running deal math. If they don't have one yet, still run comping + rehab and provide both MAO figures (75% and 70%) as their target offer range.
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 · 26 lines · 8 tokens per session scan A 03607d5a1a05
analyze-deal is a command published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 524 once invoked, about $0.0000 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 commands, from other repositories
merit-reconcile
Preview or check the status of Stripe → Merit payout reconciliation (read-only).
audit-checklist
Perform an internal audit, review controls, or prepare for an external financial audit.
valuation-methods
Valuation methods analysis — multiples, DCF inputs, PEG integration, valuation assumption extraction.
scan
Scan AWS account for cost optimization.
finops-status
Orientation — say where an opportunity or assignment sits in the five-step FinOps lifecycle and what unlocks next. Useful when a record has no active stage: an opportunity while its assignments do the work, an assignment whose plan has not been approved yet, or a rejected or archived assignment. Read-only; mutates…
archive-ledger
../../../shared/commands/archive-ledger.md.