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/chrischall/compass-mcp/compassnpx skills add chrischall/compass-mcp --skill compassgit clone --depth 1 https://github.com/chrischall/compass-mcpWrote 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/chrischall/compass-mcp/compass)<a href="https://agentmods.dev/skills/chrischall/compass-mcp/compass"><img src="https://agentmods.dev/badge/skills/chrischall/compass-mcp/compass.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 | $0.00106 | $0.01739 |
| Opus 5 | $0.00053 | $0.00870 |
| Sonnet 5 | $0.00021 | $0.00348 |
| Haiku 4.5 | $0.00011 | $0.00174 |
Grade A, and why
compass 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 4d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
compass-mcp
MCP server for Compass — natural-language access to listings, property records, photos, price history, and address resolution. Routes every request through your signed-in compass.com tab via the fetchproxy browser extension, so AWS WAF sees a real browser session instead of a Node process.
⚠️ Compass does not publish a public consumer API. Unlike portals with a JSON API surface, compass.com is a server-rendered React app — there are no
/api/...data endpoints to call. Every tool extracts state from the inline scripts each page server-renders (global.uc.sharedReactAppProps.initialResultsfor search,window.__INITIAL_DATA__.props.listingRelation.listingfor homedetails). Requests are dispatched through your own signed-in browser tab via the fetchproxy extension. Use at your own discretion.
Setup
1. Install compass-mcp
.mcp.json (project) or ~/.claude/mcp.json (global):
{
"mcpServers": {
"compass": {
"command": "npx",
"args": ["-y", "compass-mcp"]
}
}
}
2. Install the fetchproxy extension (one-time, shared across all fetchproxy-based MCPs)
git clone https://github.com/chrischall/fetchproxy
cd fetchproxy
npm ci
npm --workspace=@fetchproxy/extension-chrome run build
Then in Chrome: chrome://extensions → Developer mode → Load unpacked → pick packages/extension-chrome/dist/.
3. Open compass.com and sign in.
That's it. No API keys, no env vars.
Tools
Listing data (public)
compass_search_properties— Search by location + filters (price band, beds/baths min, home type). Slugifies free-text into Compass's/homes-for-sale/<slug>/<filters>/URL routing and extracts the SSR listings array. Returns matching listings with price, beds/baths, sqft, address, and the Compass home URL.compass_get_property— Full record byurl(a Compass homedetails URL or path) orlisting_id_shaalone. When only the sha is supplied, the tool resolves the canonical path internally via the WAF-immune omnisuggest typeahead, then fetches the/homedetails/<slug>/<sha>_lid/page. Returns address, neighborhood, beds/baths, sqft, lot size, price + $/sqft, monthly charges, MLS status, amenities, schools, parcel number, listing agent, andextracted_featuresparsed from the description.compass_get_property_photos— Full photo gallery fromlisting.media[]— original + thumbnail URLs and pixel dimensions. Floorplans/other media gated behindinclude_all_categories.compass_get_price_history— Listing-history events (Listed / Sold / Pending / Price Change / Delisted) with date, price, status, MLS attribution. Returns both this-listing and prior-listing aggregates.compass_get_comparable_rentals— Nearby rental listings for a property: lifts the target's city/state/zip, then searches rentals in the same locality. Returnsrentals: [](with target context) when none come back.compass_get_agent_listings— Other listings by the same agent, from/agents/<slug>/(active by default; closed deals viainclude_closed).
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.
- 4d ago First seen · 96 lines · 106 tokens per session scan A 776d1430ec6c
compass is a skill published in the GitHub repository chrischall/compass-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 1,739 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…