CLAUDE.md examples from real projects

postgres-aiCLAUDE.md

database-lab-engine

postgres-ai/database-lab-engine/CLAUDE.md

pnpm start:platform` ## Code Style Guidelines - Go code follows "Effective Go" and "Go Code Review Comments" guidelines - Use present tense and imperative mood in commit messages - Limit first commit line

fuergaosi233CLAUDE.md

claude-code-proxy

fuergaosi233/claude-code-proxy/CLAUDE.md

successful software development tasks. ## Task Management For complex or multi-step tasks, Claude Code will use: * **TodoWrite**: To create a structured task list, breaking down the work into manageable steps

mas-bandwidthCLAUDE.md

yojimbo

mas-bandwidth/yojimbo/CLAUDE.md

test_address_classification now covers the range boundaries. # CLAUDE.md — Audit of yojimbo *An honest code audit written by Claude (July 2026), covering the yojimbo library proper (`include/`, `source/`), its vendored

mattermostCLAUDE.md

mattermost-mobile / detox

mattermost/mattermost-mobile/detox/CLAUDE.md

foo.js \` followed by `RC=$?` | The trailing backslash makes `RC=$?` an *argument*, so the exit code is never captured and the failure gate below always passes. | | A job running `tsio-report-status.js` / `tsio-channel-notify-rollup.js

quicCLAUDE.md

aimet

quic/aimet/CLAUDE.md

indent ### Pre-commit Hooks ```bash pip install pre-commit pre-commit run --all-files ``` ## Code Architecture ### Main Python Packages **aimet_torch** (`TrainingExtensions/torch/src/python/aimet_torch/`) - Core PyTorch quantization simulation and QAT - `v2/` - Latest

addyosmaniCLAUDE.md

web-quality-skills

addyosmani/web-quality-skills/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code when working with this repository. ## Project summary Web Quality Skills is a measurement-first collection of Agent Skills for Google Lighthouse, Chrome

No other project uses it yet

jeremylongshoreReads credentialsCLAUDE.md

tons-of-skills-marketplace

jeremylongshore/tons-of-skills-marketplace/CLAUDE.md

gitleaks` + `skill-conform`** (GitHub Actions app; `strict:false`, `enforce_admins:false`, 0 required approving reviews, code-owner reviews not required). CODEOWNERS routes ownership and optional review

No other project uses it yet

bcgitCLAUDE.md

bc-java

bcgit/bc-java/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. The detailed guidance is split across the files below (imported automatically

maypok86CLAUDE.md

otter

maypok86/otter/CLAUDE.md

AGENTS.md ## Claude Code - Audit skills (`/audit-*`) run in a forked context with the `auditor` agent (`.claude/agents/auditor.md`). They are invoked manually only. - Use `general-purpose` agents, not `auditor`, to verify

No other project uses it yet

puaclawCLAUDE.md

PUAClaw

puaclaw/PUAClaw/CLAUDE.md

paragraph academic summary 3. **Description** — Detailed explanation of the technique 4. **Canonical Prompt Template** — Code block with the prompt example 5. **Mechanism of Action** — Pseudo-scientific explanation

chrisbenincasaCLAUDE.md

tunarr

chrisbenincasa/tunarr/CLAUDE.md

pushes new commits to an `approved` PR removes the label, because nobody has reviewed the new code. - An author who addresses the findings removes `changes requested` so the PR returns

CrossPasteCLAUDE.md

crosspaste-desktop

CrossPaste/crosspaste-desktop/CLAUDE.md

stylistic and semantically equivalent to the original code — do not treat reformatted code as something that needs review or further modification. ## Commit Message Convention Format: ` ` Types: - :sparkles: new feature

module-federationCLAUDE.md

core

module-federation/core/CLAUDE.md

Multiple hypotheses to investigate simultaneously 9. **Feature implementation** - Core logic, tests, integration, configuration 10. **Code review** - Architecture, performance, security, maintainability 11. **Migration tasks** - Old code analysis, new implementation, testing

No other project uses it yet

fabio-rovaiCLAUDE.md

open-ontologies

fabio-rovai/open-ontologies/CLAUDE.md

path. | | `onto_map` | To generate a mapping config from data schema + loaded ontology for review | | `onto_ossie_import` | To compile an Apache Ossie (incubating, formerly Open Semantic Interchange) ontology document

alexbelgiumReads credentialsCLAUDE.md

hassio-addons

alexbelgium/hassio-addons/CLAUDE.md

CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. ## Repository Overview This is a Home Assistant add-on repository containing 120+ Docker

oxsecurityCLAUDE.md

megalinter

oxsecurity/megalinter/CLAUDE.md

Diagnoses and fixes failing linter tests - **build-runner** - Runs and troubleshoots the build system - **code-reviewer** - Reviews Python code for MegaLinter conventions ## Claude Code Skills Skills in `.claude/skills/` invocable

No other project uses it yet

yorgaiCLAUDE.md

ORG2

yorgai/ORG2/.claude/CLAUDE.md

same hit. - **Don't modify source code in an audit-only PR.** Audit and fix are separate concerns; mixing them makes review impossible. --- ## When You're Unsure

tldevDeletes or force-pushesCLAUDE.md

dorso

tldev/dorso/CLAUDE.md

Review ### Auto-Update (Sparkle) GitHub builds auto-update via Sparkle. App Store builds contain no trace of Sparkle (the `APP_STORE` flag compiles the code out and `-dead_strip_dylibs

laude-instituteCLAUDE.md

terminal-bench

laude-institute/terminal-bench/CLAUDE.md

requests are required for changes - GitHub Actions run tests and linting on PRs - Claude Code review workflow is configured ## Notes - Docker is required for running the terminal sandbox - The project

man-groupCLAUDE.md

ArcticDB

man-group/ArcticDB/CLAUDE.md

/man-group/ArcticDB/wiki/Dev:-ASV-Benchmarks). Each time you change an ASV benchmark you must run this script `python/utils/asv_checks.py` ## Code Review Guidelines When writing or modifying code, follow the standards in [`docs/claude/PR_REVIEW_GUIDELINES.md`](docs/claude/PR_REVIEW_GUIDELINES.md). These cover