agentleFS

CLAUDE.md examples from real projects

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

Best matches · from page 20Worked for most · soon
RelaticleReads credentialsCLAUDE.md

relaticle

Relaticle/relaticle/CLAUDE.md

=== .ai/relaticle/architecture rules === # Architecture Relaticle is a modular monolith: the CRM core lives in `app

1.8k2d agoReviewMountCreate a free account to mount
SupabaseCLAUDE.md

postgres

supabase/postgres/CLAUDE.md

style compliance specs run against built images | | `.claude/skills/pg-security-release-analysis/` | Skill for triaging upstream PG quarterly security releases into a CVE/impact catalog — see below | ## Building and testing Exact commands verified against `nix/docs/build-postgres.md

1.8k5mo agoReviewMountCreate a free account to mount
kenn-ioCLAUDE.md

roborev

kenn-io/roborev/CLAUDE.md

prompt), `compact` (consolidated multi-agent), `fix` (background worktree fix) ### Review types Empty/`"review"` (standard), `"security"`, `"design"` — changes the system prompt ### Migrations SQLite schema changes are numbered migrations in `internal/storage/migrations.go`, recorded

1.8k1d agoReviewMountCreate a free account to mount
security-unionCLAUDE.md

videocall-rs

security-union/videocall-rs/CLAUDE.md

Before making any recommendation or assessment about transport protocols (WebTransport, WebSocket, QUIC, datagrams, reliability), security design, or performance trade-offs, delegate to the relevant specialist agent first. Do not reason

1.8k3mo agoReviewMountCreate a free account to mount
DialmasterOrgCLAUDE.md

Youtarr

DialmasterOrg/Youtarr/CLAUDE.md

# CLAUDE.md This file provides guidance to Claude Code (claude.ai/code) when working with code

1.8k13d agoReviewMountCreate a free account to mount
lane711Deletes or force-pushesCLAUDE.md

sonicjs

lane711/sonicjs/CLAUDE.md

Routes: `packages/core/src/routes/admin.ts`, `admin-content.ts` Use `codegraph_explore` to inspect current patterns before building new pages. ## Security - Never expose secrets in code or tests. - Validate all user input at the boundary

1.8k7d agoReviewMountCreate a free account to mount
relaticleReads credentialsCLAUDE.md

relaticle

relaticle/relaticle/CLAUDE.md

=== .ai/relaticle/architecture rules === # Architecture Relaticle is a modular monolith: the CRM core lives in `app

Steady5 mentions in 2 weeks

No other project uses it yet

1.8k25d agoReviewMountCreate a free account to mount
RackulaLivesCLAUDE.md

Rackula

RackulaLives/Rackula/CLAUDE.md

release approval gate; it runs `versions deploy` only, so it never touches routes. Security headers come from `scripts/gen-headers.mjs`, which transcribes `deploy/security-headers.conf` by value and is parity-checked in CI. They

1.8k30d agoReviewMountCreate a free account to mount
leonvanzylReads credentialsCLAUDE.md

autocoder

leonvanzyl/autocoder/CLAUDE.md

directory. ## Testing ### Python ```bash ruff check . # Lint mypy . # Type check python test_security.py # Security unit tests (12 tests) python test_security_integration.py # Integration tests (9 tests) python -m pytest test_client.py # Client tests

1.8k9mo agoReviewMountCreate a free account to mount
bohanwoodCLAUDE.md

debi

bohanwood/debi/CLAUDE.md

remote monitoring - `in_target()`: Executes commands within the target installation environment - `prompt_password()`: Securely handles password input with validation ## Important Configuration Variables The script uses 80+ configuration options. Key ones

1.8k15mo agoReviewMountCreate a free account to mount
OpenBankProjectCLAUDE.md

OBP-API

OpenBankProject/OBP-API/CLAUDE.md

deliberately left alone pending a contract decision). Personal notes, working memos and security findings live in `_DO_NOT_COMMIT_/`, which is gitignored but still visible to you on disk — treat

1.7k18d agoReviewMountCreate a free account to mount
dsd2077CLAUDE.md

CyberVerse

dsd2077/CyberVerse/claude.md

real root cause. - Reject fixes that only patch symptoms. - Reject changes that damage architecture, security, performance, maintainability, or type safety. - Prefer minimal correct fixes over large unnecessary rewrites. - Explain

1.7k5mo agoReviewMountCreate a free account to mount
Macro-Deck-AppCLAUDE.md

Macro-Deck

Macro-Deck-App/Macro-Deck/CLAUDE.md

documentation. Comment only for a reason the code cannot express: a security or trust assumption, a compatibility or protocol constraint, a platform workaround, an ordering or race requirement, deliberately surprising

1.7k38d agoReviewMountCreate a free account to mount
sachaosCLAUDE.md

todoist

sachaos/todoist/CLAUDE.md

Directory compliant) - Contains API token, color preferences, date formats - Permissions enforced to 0600 for security - **Cache**: Stored in `$HOME/.cache/todoist/cache.json` - Full sync from Todoist API using sync token - Enables offline browsing

1.7k6mo agoReviewMountCreate a free account to mount
trailofbitsCLAUDE.md

buttercup

trailofbits/buttercup/CLAUDE.md

scheduler --tail=-1 --prefix | grep "WAIT_PATCH_PASS -> SUBMIT_BUNDLE" ``` ## Security Considerations - All untrusted code execution happens in isolated Docker containers - DinD (Docker-in-Docker) provides additional isolation - Redis queues

1.7k3mo agoReviewMountCreate a free account to mount
tinyfish-ioReads credentialsCLAUDE.md

bigset / backend

tinyfish-io/bigset/backend/CLAUDE.md

other datasets; `authContext` (Clerk userId + workflow run id) is captured for caller-attribution in security logs and the `CAPABILITY_VIOLATION` PostHog event. See the security note

1.7k6mo agoReviewMountCreate a free account to mount
fynnflueggeCLAUDE.md

agtx

fynnfluegge/agtx/CLAUDE.md

paths exactly (agtx seeds each worktree into `trustedWorkspaces` when the root is trusted). **`AgentDialog::security` splits the table** — trust/bypass prompts are the user's decision: with `auto_trust = false` (default

1.7k6mo agoReviewMountCreate a free account to mount
userdocsCLAUDE.md

qbittorrent-nox-static

userdocs/qbittorrent-nox-static/CLAUDE.md

technical expert in Bash scripting. Follow the guidelines in CLAUDE.md exactly. Prioritize secure, robust, and efficient code using proper quoting, error handling, and the "do one thing well" philosophy. Never

No other project uses it yet

1.7k14mo agoReviewMountCreate a free account to mount
FOGProjectCLAUDE.md

fogproject

FOGProject/fogproject/CLAUDE.md

landing new capability there first keeps it from falling further behind. See the Secure Boot signing work (`fogproject#961`, later ported to `working-1.6` in `8226cd9`) for what happens when

1.7k4y agoReviewMountCreate a free account to mount
easysoftCLAUDE.md

zentaopms

easysoft/zentaopms/CLAUDE.md

Uses strict types declaration in newer files - Extensive use of custom framework classes ### Security - Custom authentication and authorization system - Input filtering via `lib/filter/` - SQL injection protection through DAO layer ### Performance

1.7k13mo 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.