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 instructions/chrischall/compass-mcp/claude-mdgit 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/instructions/chrischall/compass-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/compass-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/compass-mcp/claude-md.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 5.1 | $0.03345 | $0.03345 |
| Opus 5 | $0.01673 | $0.01673 |
| Sonnet 5 | $0.00669 | $0.00669 |
| Haiku 4.5 | $0.00334 | $0.00334 |
Grade A, and why
compass-mcp CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Don't add IP-rotation or TLS-impersonation libraries. The whole design is "every request rides the user's own browser session via fetchproxy." Adding cycletls / curl-impersonate / Playwright would replace that with a s How it starts
The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — compass-mcp
Guidance for Claude working in this repo.
TL;DR
Compass MCP server. Default and only transport: localhost WebSocket via @fetchproxy/server — the companion browser extension is installed separately rather than embedded. Every HTTP call to compass.com is dispatched through the user's signed-in Chrome tab — each request rides their existing session (cookies, TLS, JS context) exactly as if they'd clicked it themselves.
This is a "Pattern A" fetchproxy MCP (every call rides through fetchproxy), not "Pattern B" (one bootstrap call then direct fetch). Compass validates each request at the session level, so the in-session routing has to be per-call.
Tool surface
| Tool | File | Endpoint | Kind |
|---|---|---|---|
compass_search_properties |
tools/search.ts |
GET /homes-for-sale/<slug>/<filters>/ SSR — extract global.uc.sharedReactAppProps.initialResults.lolResults.data[] |
read |
compass_get_property |
tools/properties.ts |
GET /homedetails/<slug>/<listingIdSHA>_lid/ SSR — extract window.__INITIAL_DATA__.props.listingRelation.listing |
read |
compass_get_property_photos |
tools/photos.ts |
Same SSR page as get_property — listing.media[] |
read |
compass_get_price_history |
tools/history.ts |
Same SSR page — listing.events[] + listing.history[] |
read |
compass_compare_properties |
tools/compare.ts |
Concurrent get_property calls across N targets |
read |
compass_bulk_get |
tools/bulk-get.ts |
Concurrent get_property calls across up to 200 targets (by url or listing_id_sha); one row per target, no summary |
read |
compass_get_comparable_rentals |
tools/comparable-rentals.ts |
Lift target locality from homedetails, then GET /homes-for-sale/<slug>/type-rental/ SSR for nearby rentals |
read |
compass_get_saved_homes |
tools/saved.ts |
Not yet supported — placeholder that throws a clear error | read (auth, todo) |
compass_get_saved_searches |
tools/saved.ts |
Not yet supported — placeholder that throws a clear error | read (auth, todo) |
compass_calculate_mortgage |
tools/mortgage.ts |
(local; no network) — delegates to realty-core calculateMortgage |
read |
compass_calculate_affordability |
tools/affordability.ts |
(local; no network) — delegates to realty-core calculateAffordability |
read |
compass_get_by_address |
tools/by-address.ts |
POST /api/v3/omnisuggest/autocomplete (WAF-immune typeahead, primary) → SSR /homes-for-sale/?q= / <slug>/ fallbacks; verifies each candidate |
read |
compass_resolve_addresses |
tools/resolve-addresses.ts |
Bulk get_by_address — concurrent server-side resolution of many addresses, one round trip, shared rung walker + per-row error contract |
read |
compass_get_agent_listings |
tools/agent-listings.ts |
GET /agents/<slug>/ SSR — extract window.__AGENT_PROFILE__.data.agentProfileProps.activeListingsProps.initialSales[] (+ closedDealsProps.initialSales[].listing when include_closed) |
read |
compass_healthcheck |
tools/healthcheck.ts |
Round-trips a no-op GET /robots.txt through the bridge to confirm bridge + extension + tab are responsive |
read |
compass_get_session_context |
tools/session.ts |
(local; shared session registry) — list all registered logical sessions + active_session_id |
read |
compass_register_session |
tools/session.ts |
(local; shared session registry) — register/refresh a session keyed by account_identity (required); optional auth_expires_at; mark_active (default false) registers-and-activates |
write (registry) |
compass_set_active_session |
tools/session.ts |
(local; shared session registry) — switch the active logical session by session_id |
write (registry) |
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 · 176 lines · 3,345 tokens per session scan A 3aadcce9ea01
compass-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/compass-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 3,345 tokens to every session, about $0.0167 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.