CLAUDE.md examples from real projects

Shelf-nuReads credentialsCLAUDE.md

shelf.nu

Shelf-nu/shelf.nu/CLAUDE.md

IDORs, missing `requirePermission` gates, open redirects, missing Zod validation, audit-trail gaps — before code reaches review. - Interactive subagent: `.claude/agents/shelf-security-reviewer.md` (full toolset — for manual `claude --agent shelf-security-reviewer ...` use with

stanford-cs336CLAUDE.md

assignment1-basics

stanford-cs336/assignment1-basics/CLAUDE.md

themselves * Point students to relevant lecture materials (cs336.stanford.edu), handouts, official documentation, and profiling/debugging tools. * Review code that students have written and suggest improvements, edge cases, invariants, or debugging checks. Feedback

apptensionCLAUDE.md

saas-boilerplate

apptension/saas-boilerplate/CLAUDE.md

master` | | Branching model | GitHub flow — feature branches off `master`, pull requests based on `master` | | Code host | GitHub | | CI provider | GitHub Actions (a legacy `bitbucket-pipelines.yml` is still in the tree) | | Issue

tobychuiCLAUDE.md

arozos

tobychui/arozos/CLAUDE.md

touch them. ### 1. Use the managed logger, never the standard `log` package New code must send log output through the system logger so it lands in the managed, rotated system

rlaopeDeletes or force-pushesCLAUDE.md

oh-my-hermes

rlaope/oh-my-hermes/CLAUDE.md

move makes the next tracker run re-evaluate a range already reviewed. The receipt schema, the reason codes, and the baseline enrolment for rows that predate the contract

No other project uses it yet

ispcCLAUDE.md

ispc

ispc/ispc/CLAUDE.md

tests` skill) and/or functional tests in `tests/func-tests/` 8. Verify the fix 9. Run `code-review` agent to review the changes and address its feedback 10. Run precommit checks (see Precommit

ax-llmReads credentialsCLAUDE.md

ax

ax-llm/ax/docs/CLAUDE.md

types** | `field:image/audio/file/url` | `photo:image "Profile picture"` | | **Code** | `field:code "description"` | `script:code "Python code"` | ### Advanced Field Usage ```typescript // Optional fields with string syntax const optionalSig = s(` userInput:string -> response

No other project uses it yet

marketcallsReads credentialsCLAUDE.md

openalgo

marketcalls/openalgo/CLAUDE.md

test suite of 150 had missed, because every test changed the state *before* the code's last check, where the check rightly refused. A race lives between the last check

projenCLAUDE.md

projen

projen/projen/CLAUDE.md

running tests - `node ./projen.js test` - Runs tests only - `node ./projen.js compile` - Compiles the source code only ### File Modifications - **DO NOT manually edit generated files**: Files marked with a comment like

No other project uses it yet

MacPawCLAUDE.md

OpenAI

MacPaw/OpenAI/CLAUDE.md

code change only once that change is pushed, so the reply points to code the reviewer can see. Until then, draft the reply if it helps, and post it after

bghiraCLAUDE.md

SimpleTuner

bghira/SimpleTuner/CLAUDE.md

existing code to avoid bloat and duplication - in general, our codebase should be kept as minimal as possible, so that it is easy to maintain, review, and understand for newcomers

kaitrannttCLAUDE.md

ccs

kaitranntt/ccs/CLAUDE.md

this file. ## Scope CCS is a TypeScript/Bun CLI and dashboard for managing Claude Code, Codex, Factory Droid, CLIProxy, and compatible provider profiles. ## Non-Negotiables - Default branch is `dev`. Feature/fix branches

compozyCLAUDE.md

compozy

compozy/compozy/CLAUDE.md

procedure resolves a task-specific need; start with the owning skill. - Go conventions: `eng-code-guidelines`; Go tests: `eng-test-conventions`. Use `eng-consolidate-test-suites` when placement is unclear

No other project uses it yet

dataplatCLAUDE.md

dbatools

dataplat/dbatools/CLAUDE.md

newer than SQL 2008 - Do not add SQL 2000 (8) or SQL 2005 (9) code paths; the existing ones are unreachable ## SMO vs T-SQL USAGE **Default

VRSENReads credentialsCLAUDE.md

OpenSwarm

VRSEN/OpenSwarm/CLAUDE.md

servers to an agent - `.cursor/commands/mcp-code-exec.md` - how to convert an MCP server into the Code Execution Pattern (progressive tool disclosure, 98% token reduction) - `.cursor/commands/write-instructions.md` - how to write effective instructions

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

No other project uses it yet

HarleyCoopsCLAUDE.md

Math-To-Manim

HarleyCoops/Math-To-Manim/CLAUDE.md

hard a problem you can hand the model unsupervised. Taste covers UI/UX, code quality, API design, and copy. | model | cost | intelligence | taste | |-----------|------|--------------|-------| | gpt-5.5 | 9 | 8 | 5 | | sonnet

Hugging FaceCLAUDE.md

OpenEnv

huggingface/OpenEnv/CLAUDE.md

claude/skills/` and run inline: **Review & Validation Skills:** | Skill | Trigger | Definition | |-------|---------|------------| | [`alignment-review`](.claude/skills/alignment-review/SKILL.md) | "review this code" | Two-tier review (bugs + alignment flags) | | [`pre-submit-pr`](.claude/skills/pre-submit-pr/SKILL.md) | "ready for PR?" | Comprehensive

jgravelleReads credentialsCLAUDE.md

jcodemunch-mcp

jgravelle/jcodemunch-mcp/CLAUDE.md

findings-row`), and a typed number is a review finding. ⚠⚠ **A competitor's README figure is never a measurement and competitor code runs only in the sandbox**; a release title

No other project uses it yet

tradermontyReads credentialsCLAUDE.md

claude-trading-skills

tradermonty/claude-trading-skills/CLAUDE.md

export ALPACA_PAPER="true" # or "false" for live trading # Configure Alpaca MCP Server in Claude Code settings # See portfolio-manager/references/alpaca-mcp-setup.md for detailed setup guide ``` #### API Pricing and Access **Financial Modeling

No other project uses it yet