Borrowing it
Nothing to install: this file belongs to MaxWilk/poe2-build-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MaxWilk/poe2-build-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/MaxWilk/poe2-build-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/maxwilk/poe2-build-mcp/claude-md)<a href="https://agentmods.dev/instructions/maxwilk/poe2-build-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maxwilk/poe2-build-mcp/claude-md/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/instructions/maxwilk/poe2-build-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/maxwilk/poe2-build-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02098 | $0.02098 |
| Opus 5 | $0.01049 | $0.01049 |
| Sonnet 5 | $0.00420 | $0.00420 |
| Haiku 4.5 | $0.00210 | $0.00210 |
Grade A, and why
poe2-build-mcp CLAUDE.md 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 8d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — engineering conventions for poe2-build-mcp
This file is the working agreement for anyone (human or AI) building on this repo. For what we're building and why, read PLAN.md. This file is how we build it.
What this project is (one paragraph)
An .mcpb-installable MCP server that gives an LLM a queryable Path of Exile 2 corpus
(bundled SQLite, knowledge layer) plus a Path-of-Building–faithful calculation engine
(headless LuaJIT subprocess, compute layer). It answers build questions, imports a
user's PoB build, and helps create/tweak builds against natural-language goals — with every
number computed by PoB, never invented.
Non-negotiable invariants
These are the rules that keep the project trustworthy. Don't violate them without changing this file first.
- The engine is the source of truth for numbers. Never hand-compute, approximate, or
hard-code PoE2 damage/defense math in server code, and never let an answer state a number
the engine didn't produce. If PoB can't model something, surface that via
validate_build— do not fake a value. - The server is a substrate, not a build AI. Expose composable primitives (query, mutate, compute, validate, price). Creative synthesis is the LLM's job. Resist adding "smart" heuristics to the server that belong in the model's reasoning.
- Knowledge is offline-first and deterministic. The corpus is a bundled, read-only
SQLite file. The only network calls at runtime are the live-ops tools (
get_prices,get_meta_builds,check_data_version,update_corpus, andlookup_mechanic).lookup_mechanicis a deliberate, narrow exception: a single user-triggered, read-only wiki lookup for the long tail not in the corpus. It returns a targeted slice (not a dump), degrades to "unavailable", and never alters the corpus — it is not bundled redistribution and not scraping (see #4). The deterministic corpus remains the default; live lookup is the fallback when the corpus lacks a topic. - Scraping happens only at build time, never at runtime. poe2db/RePoE/wiki ingestion lives
in
pipeline/and runs in CI. The runtime never scrapes (bulk-fetches to store); it downloads vetted artifacts. The single on-demandlookup_mechanicread (#3) is not scraping: it fetches one page for immediate display and stores nothing. - Generated builds are always verified before being presented. The norm is
create → validate → cost → present. A build that failsvalidate_buildis flagged, not recommended. - No in-game interaction, ever. No overlay, automation, memory reading, or live-screen parsing. It's out of scope and against GGG's ToS. Reject features that head this way.
- PoB is pinned and bumped deliberately. The PoB-PoE2 submodule is pinned to a release tag. Updating it is a conscious change gated by the golden-build tests (§ Testing).
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.
- 8d ago First seen · 149 lines · 2,098 tokens per session scan A bfa2164cd0ef
poe2-build-mcp CLAUDE.md is an instructions file published in the GitHub repository MaxWilk/poe2-build-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,098 tokens to every session, about $0.0105 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 instructions, from other repositories
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.
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 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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.