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/comp-packagenpx skills add DataSift-Ty-Personal/SiftStack --skill comp-packagegit clone --depth 1 https://github.com/DataSift-Ty-Personal/SiftStackWhat 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 | $0.00143 | $0.01403 |
| Opus 5 | $0.00072 | $0.00701 |
| Sonnet 5 | $0.00029 | $0.00281 |
| Haiku 4.5 | $0.00014 | $0.00140 |
Grade A, and why
comp-package 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 2d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comp Package Builder
Build a complete boundary-filtered comp package for a single subject property: sold comps + actives pulled live from the Zillow data API, condition bucketing, a dual-track ARV, 4-tier rehab scenarios, wholesale MAO math, and buyer targeting, delivered as one Excel workbook.
Use this skill when someone says "run comps on this property", "what's the ARV", "build a comp package", or shares a map with a drawn boundary and an address.
Requirements
- Python 3.10+ with
requestsandopenpyxl - An OpenWeb Ninja "Real-Time Zillow Data" API key in the
OPENWEBNINJA_API_KEYenvironment variable (free tier available at openwebninja.com)
Workflow
Step 1: Establish subject truth from the county, not aggregators
Pull the county assessor card first (beds, baths, living sqft, year built, condition grade, sale history). Aggregator sites routinely report the wrong bedroom count (a Knox County card said 2/1 where aggregators said 5 bed). The county card also reveals the seller story: forced-sale deed types (Master's deed = tax sale, Trustee's deed = foreclosure), purchase price, and current tax delinquency are your negotiation leverage.
Step 2: Map the drawn boundary
Convert the user's drawn boundary into two machine filters:
- A lat/lon bounding box (read corner coordinates off the map's landmarks)
- A street-name whitelist regex (every street visibly inside the loop)
Apply BOTH: the bbox catches street-name misses, the street list catches bbox bleed across a highway or interstate edge. When a comp sits near the line, verify it against the map before keeping it.
Step 3: Pull sold + active comps via the API
Run scripts/zillow_market_pull.py (see references/api_contract.md for the endpoint contract and its traps). Key trap: a single sold search returns at most 41 rows (about 5 weeks in an active zip), so the script partitions by min_price/max_price bands and recursively splits any saturated band. Pull 12-24 months.
The API only sees MLS activity. Auction, wholesale, and off-market transfers will NOT appear; pull those from county records when they matter.
What ships with it
4 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.
- 2d ago First seen · 85 lines · 143 tokens per session scan A 11199d71bea9
comp-package is a skill published in the GitHub repository DataSift-Ty-Personal/SiftStack (21 stars, last pushed 4d ago), licensed MIT. It adds 143 tokens to every session and 1,403 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.