agentleFS
Sign inStart free
qf-studioqf-studio/navigator/templates/CLAUDE.md

navigator / templates

CLAUDE.md355 starsChanged 13 months agoMITView on GitHub

[Brief project description - explain what this project does] Tech Stack: [List your technologies, e.g., Next.js, TypeScript, PostgreSQL] Core Principle: [Key architectural principle, e.g., "API-first design with type safety"] Last Updated: 2026-11-01 Navigator Version: 8.4.12 Navigator runtime: workflow enforcement (session context, workflow gating, read guarding, intent briefs, completion gating, compact markers) lives in the hook runtime, not in prose in this file. Off-switches live in .agent/.nav-config.json: every hook block has enabled (e.g. workflow_enforcer_hook.enabled: false), gating blocks also take strict_block: false…

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Create a free account to mount
Files
CLAUDE.md

[Project Name] - Claude Code Configuration

Context

[Brief project description - explain what this project does]

Tech Stack: [List your technologies, e.g., Next.js, TypeScript, PostgreSQL]

Core Principle: [Key architectural principle, e.g., "API-first design with type safety"]

Last Updated: 2026-11-01 Navigator Version: 8.4.12

Navigator

Navigator runtime: workflow enforcement (session context, workflow gating, read guarding, intent briefs, completion gating, compact markers) lives in the hook runtime, not in prose in this file. Off-switches live in .agent/.nav-config.json: every hook block has enabled (e.g. workflow_enforcer_hook.enabled: false), gating blocks also take strict_block: false to warn instead of block, Tier-1 instant answers toggle per rule under tier1.rules (feature-wide: tier1.enabled), and forced continuation stays off unless stop_completion.continue_enabled: true. Setting the PILOT_EXECUTOR environment variable disables interactive/blocking hook behavior for non-interactive executors. Project docs live in .agent/ — start from .agent/DEVELOPMENT-README.md and load task/system/SOP docs on demand, not upfront.

Project-Specific Code Standards

[Customize for your project's framework and patterns]

  • Architecture: KISS, DRY, SOLID principles
  • TypeScript: Strict mode, no any without justification
  • Line Length: Max 100 characters
  • Testing: High coverage (backend 90%+, frontend 85%+)

Forbidden Actions

  • ❌ No Claude Code mentions in commits/code
  • ❌ No package.json modifications without approval
  • ❌ Never commit secrets/API keys/.env files
  • ❌ Don't delete tests without replacement

[Add project-specific violations here]

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free