agentleFS

CLAUDE.md examples from real projects

How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.

Worked for most · soon
Microsoft AzureCLAUDE.md

ARO-HCP / test

Azure/ARO-HCP/test/CLAUDE.md

Load AGENTS.md for context The metrics/alert pages shown inline on a Prow job's Spyglass page (and browsable under gcsweb at .../artifacts/e2e-parallel/aro-hcp-gather-observability/artifacts/) are produced by the gather-observability subcommand, not by a Grafana dashboard. Source lives in test/cmd/aro-hcp-tests/gather-observability/. The CI step aro-hcp-gather-observability runs aro-hcp-tests gather-observability (cmd.go, Use: "gather-observability") and writes every artifact into the --output dir, which Prow uploads to that GCS path. Each tab's HTML is a full, self-contained page (the existing alerts and metrics panel templates, unchanged) embedded into its…

4031d agoReviewMountCreate a free account to mount
Microsoft AzureCLAUDE.md

ARO-HCP / test-integration

Azure/ARO-HCP/test-integration/claude.md

Artifact-driven integration tests for frontend, backend, and admin services. Tests run against a mock Cosmos DB by default. Tests are declarative: you define a sequence of numbered step directories under an artifacts tree. The framework discovers them automatically via //go:embed artifacts and fs.ReadDir().

4031d agoReviewMountCreate a free account to mount
VercelCLAUDE.md

node-vfs-polyfill

vercel-labs/node-vfs-polyfill/CLAUDE.md

User-land implementation of the Node.js Virtual File System (VFS) based on nodejs/node#61478. This library allows mounting an in-memory filesystem that intercepts standard fs module calls through monkey-patching. Run a single test: We do not modify vendor/vfs-upstream/. The vendor directory contains code based on the upstream Node.js VFS PR. All extensions are layered on top via src/ and index.js. See UPSTREAM.md for details on our extensions.

4010mo agoReviewMountCreate a free account to mount
AWSCLAUDE.md

unified-kg-rag-on-aws

awslabs/unified-kg-rag-on-aws/CLAUDE.md

AWS-native Knowledge Graph RAG framework. Reimplements the Microsoft GraphRAG, LightRAG, HippoRAG 2 and RAPTOR methodologies on Bedrock + Neptune + OpenSearch, with DynamoDB for incremental-indexing state. The package is laid out in explicit hexagonal layers so the four RAG methodologies (see Capabilities & CLIs) share one ingestion/indexing/caching/hybrid-search infrastructure and only differ at the algorithm layer. Dependencies point inward. Layers, outermost first — a module imports its own layer and later ones, never an earlier one, and that includes lazy and…

397d agoReviewMountCreate a free account to mount
ElasticCLAUDE.md

elastic-serverless-forwarder

elastic/elastic-serverless-forwarder/CLAUDE.md

Elastic Serverless Forwarder (ESF) is an AWS Lambda function that ships logs from AWS services (S3 via SQS, Kinesis Data Streams, CloudWatch Logs, SQS) to Elastic Stack (Elasticsearch or Logstash).

387mo agoReviewMountCreate a free account to mount
SentryReads credentialsCLAUDE.md

vanguard

getsentry/vanguard/CLAUDE.md

Vanguard is an internal blog-like platform inspired by PlanetScale's Beam. It's designed for creating permanence around timely internal moments — posts, categories, comments, reactions, and feeds — with Google OAuth (workspace-domain restricted) and basic email/password as fallback, plus role-based access (admin, canPostRestricted). Vanguard runs on a Vercel-native stack:

386mo agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs

microsoft/preflate-rs/CLAUDE.md

Important: This file (and all sub-project CLAUDE.md files) are checked into the repository. Only include information that is valid for any developer or machine: project conventions, architecture, commands, constraints. Do not add machine-specific paths, personal tool preferences, local environment settings, or anything that would not apply to every contributor. The CI runs on windows-latest and builds for multiple targets: wasm32-wasip1, aarch64-unknown-linux-musl, x86_64-pc-windows-msvc, x86_64-unknown-linux-gnu. The release build uses Spectre mitigations (/Qspectre /sdl) and produces preflate_rs_0_8.dll and preflate_util.exe. preflate-rs analyzes DEFLATE-compressed streams,…

3817d agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs / container

microsoft/preflate-rs/container/CLAUDE.md

Scans binary files (ZIP, PNG, JPEG) for DEFLATE streams, orchestrates the preflate + Zstd pipeline, and reassembles the output. Only format version 3 is supported. Versions 1 and 2 are rejected; version 3 uses the incompatible 0.8 corrections format. PreflateContainerConfig holds knobs: min_chunk_size, max_chunk_size, total_plain_text_limit, chunk_plain_text_limit, validate_compression, max_chain_length. All framing bytes (type, varint) are written directly to the output stream — they are never inside the Zstd encoder. Each block type byte encodes two fields: Mask constants (defined in container_processor.rs):

3817d agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs / dll

microsoft/preflate-rs/dll/CLAUDE.md

C-compatible DLL for .NET interop. Exposes a streaming compress/decompress API as extern "C" functions. The version number is baked into the crate name (preflate_rs_0_8) for binary compatibility. flags encoding: - bits 0–4: Zstd compression level - bit 5: test_baseline - bit 6: verify Return value of compress_buffer: 0 = more output available, 1 = done, <0 = error. Magic numbers are validated on every call to catch dangling/wrong pointer bugs. - Uses #[unsafe(no_mangle)] on exported functions — the only place…

3817d agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs / fuzz

microsoft/preflate-rs/fuzz/CLAUDE.md

libfuzzer harnesses for fuzzing the core and container APIs. Not published; requires the fuzzing cargo feature. Feeds arbitrary bytes to preflate_whole_deflate_stream() as a raw DEFLATE stream, then attempts recreate_whole_deflate_stream() on the result. Verifies no crash or panic. Feeds arbitrary bytes (minimum 1 byte) to preflate_whole_into_container(), then recreate_whole_from_container(), and asserts the output matches the original input.

3817d agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs / preflate

microsoft/preflate-rs/preflate/CLAUDE.md

Core DEFLATE analysis and reconstruction. Analyzes a DEFLATE bitstream, extracts the uncompressed plaintext plus a compact set of reconstruction parameters, and later recreates the bit-exact original bitstream. PreflateConfig controls max_chain_length, plain_text_limit, and verify_compression. Reconstruction runs the same pipeline in reverse.

3817d agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs / tests

microsoft/preflate-rs/tests/CLAUDE.md

End-to-end round-trip tests against real sample files in samples/. - Core round-trip: decompress a .deflate file with preflate_whole_deflate_stream, recompress with recreate_whole_deflate_stream, assert bitwise identical output. - Container round-trip: compress a ZIP / PNG / DOCX / PDF through PreflateContainerProcessor, decompress with RecreateContainerProcessor, assert the output matches the original file byte-for-byte. The samples/ directory contains real-world compressed files used as test fixtures: deflate streams, zlib streams, PNGs, ZIPs, PDFs, DOCX, JPEG, WebP, and binary blobs from various compressors (zlib, zlib-ng, libdeflate,…

3817d agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

preflate-rs / util

microsoft/preflate-rs/util/CLAUDE.md

CLI tool for manually testing preflate compression on files and directories. <PATH> may be a single file or a directory (scanned recursively). Single file: src/main.rs (~193 lines). Helper assert_eq_array<T>() provides detailed positional diff output for debugging mismatches during verification.

3817d agoReviewMountCreate a free account to mount
Hugging FaceCLAUDE.md

hub-tutorials

huggingface/hub-tutorials/.claude/CLAUDE.md

AI agent tutorial repository with scripts, notebooks, and presentation materials.

3710mo agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

open-kosmos

microsoft/open-kosmos/CLAUDE.md

Tech Stack: Electron 35 + React 18 + TypeScript 5, Webpack 5, TailwindCSS 4, lucide-react icons, Vercel AI SDK 5.x (streaming), @modelcontextprotocol/sdk, better-sqlite3 (local persistence), Monaco Editor, Playwright (browser automation). Architecture: Electron multi-process model — main process (Node.js: auth, chat engine, MCP runtime, data persistence, voice) + renderer process (React SPA: chat UI, agent editor, settings) + preload scripts (type-safe IPC bridge). The app is built as OpenKosmos-only. A list of useful package.json scripts: After entering a module directory, check…

354mo agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

recipe-tool

microsoft/recipe-tool/CLAUDE.md

This section outlines the core implementation philosophy and guidelines for software development projects. It serves as a central reference for decision-making and development approach throughout the project. Embodies a Zen-like minimalism that values simplicity and clarity above all. This approach reflects: This development philosophy values clear documentation, readable code, and belief that good architecture emerges from simplicity rather than being imposed through complexity.

3518mo agoReviewMountCreate a free account to mount
NVIDIACLAUDE.md

ai-cloud-validation

NVIDIA/ai-cloud-validation/CLAUDE.md

@AGENTS.md @.cursor/rules/karpathy-guidelines.mdc @.cursor/rules/python-standards.mdc

357mo agoReviewMountCreate a free account to mount
MicrosoftCLAUDE.md

ShadowFrog

microsoft/ShadowFrog/claude.md

ShadowFrog is a suite of AI coding agent skills that build and maintain shadow knowledge bases for any codebase. It consists of 7 skills (shadow-frog, shadow-frog-init, shadow-frog-update, shadow-frog-dream, shadow-frog-nap, shadow-frog-meditate, shadow-frog-viewer) and associated hooks. Nap's proposals remain separate from .shadow/ discoveries. This is a distributable skills package — users install it into their own projects via install.sh or install.ps1.

3312d agoReviewMountCreate a free account to mount
NVIDIADeletes or force-pushesCLAUDE.md

NuRec / nurec-onboard

NVIDIA/NuRec/skills/nurec-onboard/CLAUDE.md

Project-level conventions for autonomous workflow execution. Never use system python3 (or python) to import ncore. The converter repos pin nvidia-ncore via Bazel; system Python does not have access to this version. Any python3 -c "import ncore ..." or python3 <script> that imports ncore will silently pick up the wrong version or fail. Use bazel run targets inside the converter repo for all NCore operations. Both have the same fix: write the command body to /tmp/claude/<name>.sh (or .py for Python) and…

3316d agoReviewMountCreate a free account to mount
ElasticCLAUDE.md

elastic-otel-dotnet

elastic/elastic-otel-dotnet/CLAUDE.md

Elastic Distribution of OpenTelemetry .NET (EDOT .NET) — an Elastic-sponsored distribution extending the OpenTelemetry SDK for .NET. Provides Elastic-specific processors, opinionated defaults, OTLP exporter, automatic instrumentation assembly scanning, and OpAmp (Open Agent Management Protocol) support for central configuration. The build system uses F# with Bullseye. Entry points are build.sh (Unix) and build.bat (Windows). Underlying dotnet commands for quick iteration: Required SDK: .NET 10.0.100 (see global.json) Source projects (src/): Key architectural pattern: Core, OpAmp, and OpAmp.Abstractions are source-linked into the main…

328mo agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About CLAUDE.md

What is CLAUDE.md?

A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.

Where does it go?

At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.

What should it contain?

Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.

CLAUDE.md or AGENTS.md?

Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.