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/booli-mcp/claude-mdgit clone --depth 1 https://github.com/chrischall/booli-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/booli-mcp/claude-md)<a href="https://agentmods.dev/instructions/chrischall/booli-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/booli-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 | $0.01401 | $0.01401 |
| Opus 5 | $0.00700 | $0.00700 |
| Sonnet 5 | $0.00280 | $0.00280 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
booli-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 yesterday.
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.
every non-browser client (Node/curl), and Cloudflare fingerprints the HTTP How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — booli-mcp
Guidance for Claude working in this repo.
TL;DR
MCP server for booli.se, a Swedish property portal. Reads active
for-sale listings, sold prices (slutpriser), area lookups, single-property
detail, and computes market statistics. stdio transport. All tools are
read-only — nothing is confirm-gated.
Data access is Booli's consumer GraphQL API via the fetchproxy browser
bridge. Booli fronts the whole www.booli.se zone — including /graphql —
with a Cloudflare managed challenge (cf-mitigated: challenge) that 403s
every non-browser client (Node/curl), and Cloudflare fingerprints the HTTP
client itself, so no header/cookie replay durably clears it. The identical
query returns 200 from a fetch inside a real tab. So requests ride the
user's own signed-in (Cloudflare-cleared) www.booli.se tab via
@fetchproxy/server + the Transporter extension. No Booli login needed —
just a cleared Cloudflare session (any normal page view). Verified live
2026-07-13; full API in docs/BOOLI-API.md.
History: an earlier iteration targeted the classic signed REST API at
api.booli.se(HMACcallerId/apiKey). Booli no longer issues those credentials to new users, so that surface is unusable — we pivoted to the consumer GraphQL + browser bridge. See docs/BOOLI-API.md §2.
Transport (mirrors hemnet-mcp's fetchproxy pattern)
src/transport.ts— theBooliTransportinterface (graphql(query, variables), plus optionalstatus()→TransportStatusandbridgeTransport()→ the bridge'srunProbe/statusslice). Every tool is written against it so tests drive them through an in-memory fake (tests/helpers.ts) with zero network.src/transport-direct.ts— direct Nodefetchto www.booli.se/graphql; throws a typedCloudflareChallengeErroron the bot wall (detected bycf-mitigated: challenge/_cf_chl_opt/ "Just a moment" only).src/transport-fetchproxy.ts— the browser bridge: each GraphQL POST runs as a same-origin fetch in the signed-in tab viacreateFetchproxyTransport(@chrischall/mcp-utils/fetchproxy).src/transport-fallback.ts—createDefaultTransport: direct-first with sticky fallback to the bridge onCloudflareChallengeError.BOOLI_TRANSPORT=direct|fetchproxy|auto(default). Shared fleet WS port 37149 (BOOLI_WS_PORT). Itsstatus()reports the leg the next call rides (mode: 'auto'), andbridgeTransport()the bridge once the fallback has built it.src/tools/healthcheck.ts—booli_healthcheckis the fleet's sharedregisterBridgeHealthcheckTool(@chrischall/mcp-utils/fetchproxy) in its direct-first (path) mode:probeFnisclient.healthcheck(),pathreadsclient.transportStatus()andtransportreadsclient.bridgeTransport()AFTER the probe (the probe may be what flips the fallback). Output:ok,transport({transport, mode}— the leg and theBOOLI_TRANSPORTpin, nothing else),bridge(role, port,session_state,pending_pair_code,extension_connected, epoch-mslast_extension_message_at— the ONE bridge block, projected by the shared tool frombridgeTransport().status(); present only once a bridge exists),probe,error(kind—cloudflare_challengefor the direct leg'sCloudflareChallengeError, else the fetchproxy vocabularysession_not_ready/bridge_down/timeout/ …),hint. The fetchproxy transport wraps typed bridge errors with the original ascauseso the classification survives the wrapper.@fetchproxy/serveris bundled in (no esbuild--external), so the fetchproxy imports are eager static imports — safe because nothing is externalized. If you ever externalize it, make those imports lazyawait import()behind the fetchproxy/auto path.
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.
- yesterday Changed · +19 lines · +346 tokens per session 091bfbfc8f9e
- 5d ago First seen · 78 lines · 1,055 tokens per session scan A df4f88d3cf22
booli-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/booli-mcp (4 stars, last pushed yesterday), licensed MIT. It adds 1,401 tokens to every session, about $0.0070 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.