
Free Code Claude Cli
- 560 installs
- 66 repo stars
- Updated July 9, 2026
- aradotso/trending-skills
free-code-claude-cli is a Claude agent skill for building and running the free-code fork of Claude Code CLI with telemetry removed and 54 experimental feature flags for developers who need multi-provider terminal agents.
About
free-code is an open-source fork of Anthropic's Claude Code CLI that gives developers a terminal-native AI coding agent without restrictions. It eliminates telemetry, removes injected guardrails, and unlocks every experimental feature flag disabled in the official npm release. The skill provides a one-liner installer that handles Bun, clones the repository, builds with full experimental support, and places the free-code binary on your PATH. It works with Anthropic, OpenAI Codex, AWS Bedrock, Google Vertex AI, and Anthropic Foundry so you can switch providers instantly. Developers use it to gain complete control over their local coding agent, run advanced reasoning modes, and avoid any vendor lock-in or data collection.
- Removes all telemetry and phone-home callbacks from Claude Code CLI
- Strips Anthropic system-prompt guardrails
- Unlocks all 54 experimental feature flags including ultrathink and ultraplan
- Supports five model providers: Anthropic, OpenAI Codex, AWS Bedrock, Google Vertex AI, Anthropic Foundry
- One-command install that builds from source and symlinks free-code on your PATH
Free Code Claude Cli by the numbers
- 560 all-time installs (skills.sh)
- +12 installs in the week ending Jun 23, 2026 (Skillselion tracking)
- Ranked #1,630 of 16,659 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: CRITICAL risk (skills.sh audit)
- Data as of Jul 19, 2026 (Skillselion catalog sync)
npx skills add https://github.com/aradotso/trending-skills --skill free-code-claude-cliAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 560 |
|---|---|
| repo stars | ★ 66 |
| Security audit | 0 / 3 scanners passed |
| Last updated | July 9, 2026 |
| Repository | aradotso/trending-skills ↗ |
How do you run Claude Code CLI without telemetry?
Run a fully unlocked, telemetry-free terminal-native coding agent with support for multiple model providers including OpenAI, Bedrock, and Vertex.
Who is it for?
Developers who want a self-built Claude Code fork with telemetry stripped, multi-provider support, and experimental flags like ULTRATHINK enabled.
Skip if: Developers satisfied with stock Anthropic Claude Code npm installs who do not need provider switching or custom builds.
When should I use this skill?
User asks to set up free-code, build Claude Code from source, strip telemetry, or configure OpenAI, Bedrock, or Vertex providers.
What you get
Built free-code CLI binary, provider configuration, and unlocked experimental feature flags for terminal agent sessions.
- free-code CLI binary
- Provider environment configuration
By the numbers
- Unlocks 54 experimental feature flags in full dev build
- Supports 5 model providers
- Requires Bun ≥ 1.3.11 for manual builds
Files
free-code Claude CLI
Skill by ara.so — Daily 2026 Skills collection.
free-code is a buildable fork of Anthropic's Claude Code CLI — a terminal-native AI coding agent. It removes all telemetry and phone-home callbacks, strips Anthropic's injected system-prompt guardrails, and unlocks 54 experimental feature flags that are disabled in the public npm release. It supports five model providers: Anthropic, OpenAI Codex, AWS Bedrock, Google Vertex AI, and Anthropic Foundry.
---
Installation
One-liner (recommended)
curl -fsSL https://raw.githubusercontent.com/paoloanzn/free-code/main/install.sh | bashThis installs Bun if needed, clones the repo, builds with experimental features, and symlinks free-code on your PATH.
Manual build
# Requires Bun >= 1.3.11
curl -fsSL https://bun.sh/install | bash
git clone https://github.com/paoloanzn/free-code.git
cd free-code
bun run build
./cli---
Key CLI Commands
# Start interactive REPL
free-code
# One-shot prompt
free-code -p "explain this codebase"
# Specify model
free-code --model claude-opus-4-6
# OAuth login (runs /login slash command)
free-code /login
# Run from source (slower, no build step)
bun run devSlash commands inside the REPL
/login Authenticate with your chosen provider
/help List all available commands
/clear Clear conversation context
/compact Compact context window
/memory View/edit memory files---
Build Variants
| Command | Output | Features |
|---|---|---|
bun run build | ./cli | VOICE_MODE only (production-like) |
bun run build:dev | ./cli-dev | VOICE_MODE only, dev stamp |
bun run build:dev:full | ./cli-dev | All 54 experimental flags unlocked |
bun run compile | ./dist/cli | Alternative output path |
Enable specific feature flags
# Unlock ultrathink + ultraplan only
bun run ./scripts/build.ts --feature=ULTRATHINK --feature=ULTRAPLAN
# Dev build with bridge mode added
bun run ./scripts/build.ts --dev --feature=BRIDGE_MODE
# Full experimental unlock
bun run build:dev:full---
Model Provider Configuration
Switch providers entirely via environment variables — no code changes needed.
Anthropic (default)
export ANTHROPIC_API_KEY="$ANTHROPIC_API_KEY"
free-code --model claude-opus-4-6Available models: claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5
Override model defaults:
export ANTHROPIC_DEFAULT_OPUS_MODEL="claude-opus-4-6"
export ANTHROPIC_DEFAULT_SONNET_MODEL="claude-sonnet-4-6"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="claude-haiku-4-5"
export ANTHROPIC_BASE_URL="https://api.anthropic.com" # custom endpointOpenAI Codex
export CLAUDE_CODE_USE_OPENAI=1
free-code --model gpt-5.3-codexAvailable models: gpt-5.3-codex, gpt-5.4, gpt-5.4-mini
AWS Bedrock
export CLAUDE_CODE_USE_BEDROCK=1
export AWS_REGION="us-east-1"
# Uses standard AWS credential chain: env vars, ~/.aws/config, or IAM role
free-codeAdditional Bedrock variables:
export ANTHROPIC_BEDROCK_BASE_URL="https://..." # custom endpoint
export AWS_BEARER_TOKEN_BEDROCK="$TOKEN" # bearer token auth
export CLAUDE_CODE_SKIP_BEDROCK_AUTH=1 # skip auth (testing only)Google Cloud Vertex AI
# Authenticate first
gcloud auth application-default login
export CLAUDE_CODE_USE_VERTEX=1
free-codeAnthropic Foundry
export CLAUDE_CODE_USE_FOUNDRY=1
export ANTHROPIC_FOUNDRY_API_KEY="$ANTHROPIC_FOUNDRY_API_KEY"
free-code --model my-deployment-id---
Experimental Features Reference
Build with bun run build:dev:full to unlock all 54 flags, or pass --feature=FLAG individually.
High-value flags
| Flag | What it does |
|---|---|
ULTRATHINK | Type "ultrathink" in a prompt to boost reasoning depth |
ULTRAPLAN | Remote multi-agent planning (Opus-class) via Claude Code web |
VOICE_MODE | Push-to-talk voice input and dictation |
TOKEN_BUDGET | Real-time token budget tracking and warnings |
HISTORY_PICKER | Interactive prompt history picker |
EXTRACT_MEMORIES | Auto-extracts memories after each query |
VERIFICATION_AGENT | Validation agent that checks task completion |
AGENT_TRIGGERS | Local cron/trigger tools for background automation |
BRIDGE_MODE | IDE remote-control bridge (VS Code, JetBrains) |
BASH_CLASSIFIER | AI-assisted bash permission decisions |
BUILTIN_EXPLORE_PLAN_AGENTS | Preset explore/plan agent configs |
TEAMMEM | Team-shared memory files with watcher hooks |
COMPACTION_REMINDERS | Smart reminders around context window compaction |
---
Environment Variables Quick Reference
# Authentication
ANTHROPIC_API_KEY # Anthropic API key
ANTHROPIC_AUTH_TOKEN # Alternative auth token
CLAUDE_CODE_OAUTH_TOKEN # OAuth token via env (skips /login)
# Provider selection
CLAUDE_CODE_USE_OPENAI=1 # Switch to OpenAI Codex
CLAUDE_CODE_USE_BEDROCK=1 # Switch to AWS Bedrock
CLAUDE_CODE_USE_VERTEX=1 # Switch to Google Vertex AI
CLAUDE_CODE_USE_FOUNDRY=1 # Switch to Anthropic Foundry
# Model overrides
ANTHROPIC_MODEL # Override default model for session
ANTHROPIC_BASE_URL # Custom API base URL
# Tuning
CLAUDE_CODE_API_KEY_HELPER_TTL_MS # API key helper cache TTL in ms---
Project Structure
scripts/
build.ts # Build script — feature flag injection lives here
src/
entrypoints/cli.tsx # CLI entry — Commander.js setup, arg parsing
commands.ts # Slash command registry
tools.ts # Agent tool registry
QueryEngine.ts # Core LLM query orchestration
screens/REPL.tsx # Interactive terminal UI (React + Ink)
commands/ # /slash command implementations
tools/ # Agent tools: Bash, Read, Edit, Glob, Grep, etc.
components/ # Ink/React terminal UI components
services/
api/ # Anthropic + Codex API clients
oauth/ # OAuth flows (Anthropic, OpenAI)
state/ # Global app state store
utils/model/ # Model config, provider routing, validation
bridge/ # IDE bridge (BRIDGE_MODE)
voice/ # Voice input (VOICE_MODE)
skills/ # Skill system
plugins/ # Plugin system
tasks/ # Background task management---
Common Patterns
Use ultrathink for hard problems
After building with --feature=ULTRATHINK:
> ultrathink refactor this authentication module to use JWTsThe keyword ultrathink in your prompt triggers extended reasoning mode.
Pipe files into one-shot mode
cat src/auth.ts | free-code -p "find security issues in this file"
free-code -p "write tests for $(cat src/utils.ts)"Run with a specific provider per session
# One-off Bedrock session without changing env permanently
CLAUDE_CODE_USE_BEDROCK=1 AWS_REGION=eu-west-1 free-code
# One-off Vertex session
CLAUDE_CODE_USE_VERTEX=1 free-code -p "review this PR diff"Custom build for CI with minimal features
// scripts/build.ts accepts --feature flags
// Build only what you need for a headless CI agent:
// bun run ./scripts/build.ts --feature=VERIFICATION_AGENT --feature=AGENT_TRIGGERS---
Troubleshooting
bun: command not found
curl -fsSL https://bun.sh/install | bash
source ~/.bashrc # or ~/.zshrcfree-code: command not found after install
The install script symlinks to your PATH. If it's missing:
cd free-code
ln -sf "$(pwd)/cli" /usr/local/bin/free-codeBuild fails on experimental flags
Some of the 88 flags don't compile cleanly. Use build:dev:full which only enables the 54 working flags. For broken flags, check FEATURES.md for reconstruction notes:
# Safe full-unlock build (54 working flags only)
bun run build:dev:fullAuthentication errors with Bedrock
Verify your AWS credential chain is working independently:
aws sts get-caller-identity
# If this fails, fix AWS credentials before setting CLAUDE_CODE_USE_BEDROCK=1Vertex AI auth errors
gcloud auth application-default login
gcloud auth application-default print-access-token # verify it works
export CLAUDE_CODE_USE_VERTEX=1
free-codeContext window fills up quickly
Enable compaction reminders and use the /compact command:
bun run ./scripts/build.ts --feature=COMPACTION_REMINDERS
# Inside REPL when warned:
/compact---
IPFS Fallback
If the GitHub repo is unavailable, the full source is permanently mirrored:
CID: bafybeiegvef3dt24n2znnnmzcud2vxat7y7rl5ikz7y7yoglxappim54bm
URL: https://w3s.link/ipfs/bafybeiegvef3dt24n2znnnmzcud2vxat7y7rl5ikz7y7yoglxappim54bmRelated skills
FAQ
How many experimental flags does free-code unlock?
free-code unlocks 54 experimental feature flags when built with bun run build:dev:full, or individual flags via bun run ./scripts/build.ts --feature=ULTRATHINK --feature=ULTRAPLAN.
Which model providers does free-code support?
free-code supports five providers: Anthropic (default), OpenAI Codex via CLAUDE_CODE_USE_OPENAI=1, AWS Bedrock, Google Vertex AI, and Anthropic Foundry—each configured with environment variables.
What runtime is required to build free-code?
free-code requires Bun ≥ 1.3.11. Manual build clones paoloanzn/free-code, runs bun run build, and symlinks the free-code binary to PATH via the install.sh one-liner.
Is Free Code Claude Cli safe to install?
skills.sh reports 0 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.