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 rehab-estimatorgit 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/rehab-estimator)<a href="https://agentmods.dev/skills/datasift-ty-personal/siftstack/rehab-estimator"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/rehab-estimator/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/rehab-estimator"><img src="https://agentmods.dev/badge/skills/datasift-ty-personal/siftstack/rehab-estimator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 527 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00110 | $0.13524 |
| Opus 5 | $0.00055 | $0.06762 |
| Sonnet 5 | $0.00022 | $0.02705 |
| Haiku 4.5 | $0.00011 | $0.01352 |
Grade A, and why
rehab-estimator 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 9d 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 — 937 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rehab Cost Estimator
Produces professional, itemized renovation cost estimates for investment properties. Two exit strategies analyzed side-by-side: Full Rehab (investor flip to retail) and Wholetail (light cosmetic for quick sale to another investor or retail-lite buyer).
All pricing is calibrated to the local market where the property sits — not national averages.
Single-Estimate Approach
This skill produces ONE cost estimate per line item — not a Low/Mid/High range. The estimate targets the low-to-mid range of real-world contractor pricing (roughly the 35th percentile between Low and Mid reference prices in rehab-categories.md). This keeps estimates conservative and closer to what actual contractor bids come back at, based on real deal calibration data showing that Low/Mid/High ranges led to over-estimation. When in doubt, lean toward the lower end — real contractors tend to come in closer to low than mid on most line items.
When to Read Reference Files
This skill uses progressive disclosure. Read these files at the specific steps indicated:
| File | When to Read | What It Contains |
|---|---|---|
references/real-deal-calibration.md |
Step 2 (FIRST — before scoping) | CRITICAL: Verified unit prices from a real contractor SOW, scoping rules, and the 60-65% Rule sanity check. This file overrides all other pricing when there's a conflict. |
references/rehab-categories.md |
Step 3 (Scope of Work) | Complete line-item categories with calibrated $/unit for every repair item |
references/local-pricing-guide.md |
Step 4 (Local Pricing) | How to research and apply local labor/material adjustments by market |
references/finish-tiers.md |
Step 3 (Scope of Work) | Defines 4 finish tiers (Minimum Viable, Builder Grade, Mid-Range Upgrade, Premium/Custom) with material specs |
references/wholetail-vs-rehab.md |
Step 3 (Scope of Work) | Exactly which items differ between wholetail and full rehab scopes |
data/master_material_list_37914.csv |
Steps 3-4, when the property is in Knoxville / Knox County / Blount County, TN | LOCKED master material list: exact Home Depot prices (Budget/Standard/Upgrade grades) for 88 materials + 12 allowances, local to zip 37914. The material source for the vast majority of items on Knox-market deals. |
scripts/generate_rehab_excel.py |
Step 6 (Deliverables) | Generates the Excel workbook with all sheets |
What ships with it
7 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.
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.
- 9d ago First seen · 937 lines · 110 tokens per session scan A 97564a051f47
rehab-estimator is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 5d ago), licensed MIT. It adds 110 tokens to every session and 13,524 once invoked, about $0.0006 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
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
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…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
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.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.