Borrowing it
Nothing to install: this file belongs to db-lyon/ue-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/db-lyon/ue-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/db-lyon/ue-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/db-lyon/ue-mcp/claude-md)<a href="https://agentmods.dev/instructions/db-lyon/ue-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/db-lyon/ue-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 | $0.04463 | $0.04463 |
| Opus 5 | $0.02232 | $0.02232 |
| Sonnet 5 | $0.00893 | $0.00893 |
| Haiku 4.5 | $0.00446 | $0.00446 |
Grade A, and why
ue-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 today.
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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Operating guide for Claude Code (and any AI agent) working in this repo. Shared team knowledge - checked into the repo so every contributor gets the same rulebook.
Repo at a glance
- TS server (
src/) - the MCP server. Wraps the UE bridge over WebSocket, exposes 24 category tools with 1090+ actions. The numbers between those markers are stamped byscripts/generate-tool-metadata.tsfromALL_TOOLS; do not hand-edit them, and do not remove the markers, because a hand-written count here is the first thing every agent reads and the last thing anyone remembers to update. - C++ plugin (
plugin/ue_mcp_bridge/) - the editor-side bridge. Lives inPrivate/Handlers/*.cpp, registers actions withFMCPHandlerRegistry. - Test project (
tests/ue_mcp/) - the dedicated UE project used for smoke testing. The plugin is deployed here fromplugin/via the deployer. This is the only safe target for live tests. - Docs (
docs/) - MkDocs site.docs/release-notes-X.Y.Z.mdis the canonical release body.
Edit only under plugin/ue_mcp_bridge/. The deployer syncs to tests/ue_mcp/Plugins/UE_MCP_Bridge/ - never hand-copy.
Development workflow
Git and commits
- Atomic commits per logical change. One fix or feature per commit with a clear message explaining the why. Don't batch unrelated changes.
- No batching "housekeeping" commits that sweep up everything at once. If you wrote five fixes, write five commits.
- Claude owns git. Stage, commit, push when ready. Don't push the user into running git commands.
Squash or merge commit
The merge style follows the commit count, and writing five commits only to squash them back into one throws the work away.
- One logical change in the PR: squash-merge.
gh pr merge <n> --squash --delete-branch. Review fixups and typo passes are noise on main. - Several independently meaningful commits: merge commit.
gh pr merge <n> --merge. Each fix keeps its own SHA, which is what issue comments cite when they say which commit closed the issue. Squashing seven fixes leaves seven issues pointing at one SHA whose message describes something else. - Never rewrite a SHA that has already been cited in an issue, a release note, or a comment. The citation is a promise that the commit exists.
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.
- today Changed · +7 lines · +233 tokens per session 78174dc7b146
- 7d ago First seen · 189 lines · 4,230 tokens per session scan A 602d92b1b664
ue-mcp CLAUDE.md is an instructions file published in the GitHub repository db-lyon/ue-mcp (306 stars, last pushed yesterday), licensed MIT. It adds 4,463 tokens to every session, about $0.0223 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 2026-08-30.
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.
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.