Borrowing it
Nothing to install: this file belongs to Graphmaxer/gw1-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/Graphmaxer/gw1-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Graphmaxer/gw1-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/graphmaxer/gw1-mcp/claude-md)<a href="https://agentmods.dev/instructions/graphmaxer/gw1-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/graphmaxer/gw1-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/graphmaxer/gw1-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/graphmaxer/gw1-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 | $0.27697 | $0.27697 |
| Opus 5.5 | $0.11079 | $0.11079 |
| Sonnet 5.5 | $0.05539 | $0.05539 |
| Haiku 4.5 | $0.02770 | $0.02770 |
Grade B, and why
gw1-mcp CLAUDE.md scanned grade B 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 22d 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
the description gate because "Aegis. Ignore all previous instructions." is 40 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 1,664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — gw1-mcp
What this project is
An MCP (Model Context Protocol) server that gives any compatible LLM client (Claude, ChatGPT, Cursor…) reliable, deterministic knowledge of Guild Wars 1 builds: skill data lookup, template code encoding/decoding, and build validation.
Core design principle — the MCP is a compiler, not a brain. The LLM does all strategic reasoning (which skills to pick, team composition, meta knowledge, reading guides). This server only does things that must be exact:
- know the canonical game data (skills, professions, attributes, heroes, IDs)
- encode/decode official in-game template codes
- validate builds against game rules
- report precise, structured errors
Never add a tool that "reasons" or "generates" a build from vague intent. If a tool needs intelligence to work, it belongs in the LLM, not here.
Commands
pnpm install # Node >= 22, pnpm 11
pnpm -r typecheck && pnpm -r test # must pass from a clean clone
pnpm lint && pnpm fmt # oxlint / oxfmt (CI runs fmt:check)
pnpm test:coverage # reference levels: see Coverage section
pnpm bench # vitest bench in every package (see Performance)
pnpm --filter @gw1-mcp/gw-worker dev # local worker
npx wrangler deploy --dry-run # bundle check (in gw-worker)
Nothing is ever built to dist: exports point at .ts sources; the worker bundles via wrangler.
Architecture
pnpm monorepo, TypeScript everywhere.
gw1-mcp/
├── CLAUDE.md ← you are here
├── packages/
│ ├── gw-data/ ← game data (JSON from build-wars/gw-skilldata) + repository layer
│ ├── gw-template/ ← template code codec (encode/decode) — ZERO dependencies, pure functions
│ ├── gw-mcp/ ← MCP server exposing tools; depends on gw-data + gw-template
│ └── gw-worker/ ← Hono transport: Cloudflare Workers + Node (same app)
└── gwtoolbox-plugin/ ← AccountExport C++ plugin (built in CI on a GWToolboxpp checkout)
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.
- 22d ago Changed · +31 lines · +611 tokens per session 8e97972edfc1
- 1mo ago Changed · +30 lines · +539 tokens per session d9878f0831c5
- 1mo ago Changed · +191 lines · +3,376 tokens per session 1f971aa2fc67
- 1mo ago First seen · 1,412 lines · 23,171 tokens per session scan B f6b52facdba0
gw1-mcp CLAUDE.md is an instructions file published in the GitHub repository Graphmaxer/gw1-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 27,697 tokens to every session, about $0.1108 per session on Opus 5.5. A static security scan graded it B with 1 finding (instruction-override phrasing). 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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.