RomanNum3ral
/
claw-code
mirror of https://github.com/instructkr/claw-code.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
Better Harness Tools, not merely storing the archive of leaked Claude Code but also make real things done. Now rewriting in Rust.
844 Commits 190 Branches 0 Tags 49 MiB
Rust 95.2%
Python 4.1%
Shell 0.5%
HTML 0.2%
Go to file
YeonGyu-Kim ad02761918 ROADMAP #115: claw init hardcodes 'defaultMode: dontAsk' alias for danger-full-access; init output zero security signal; JSON wraps prose 
Dogfooded 2026-04-18 on main HEAD ca09b6b from /tmp/cdPP.

Three compounding issues in one finding:

1. claw init generates .claw.json with dangerous default:
   $ claw init && cat .claw.json
   {"permissions":{"defaultMode":"dontAsk"}}

   $ claw status | grep permission_mode
   permission_mode: danger-full-access

2. The 'dontAsk' alias obscures the actual security posture:
   config.rs:858 "dontAsk" | "danger-full-access" =>
     Ok(ResolvedPermissionMode::DangerFullAccess)

   User reads 'dontAsk' as 'skip confirmations I'd otherwise see'
   — NOT 'grant every tool unconditional access'. But the two
   parse identically. Alias name dilutes severity.

3. claw init --output-format json wraps prose in message field:
   {
     "kind": "init",
     "message": "Init\n  Project  /private/tmp/cdPP\n
        .claw/  created\n..."
   }
   Claws orchestrating setup must string-parse \n-prose to
   know what got created. No files_created[], no
   resolved_permission_mode, no security_posture.

Zero mention of 'danger', 'permission', or 'access' anywhere
in init output. The init report says 'Review and tailor the
generated guidance' — implying there's something benign to tailor.

Trace:
  rusty-claude-cli/src/init.rs:4-9 STARTER_CLAW_JSON constant:
    hardcoded {"permissions":{"defaultMode":"dontAsk"}}
  runtime/src/config.rs:858 alias resolution:
    "dontAsk" | "danger-full-access" => DangerFullAccess
  rusty-claude-cli/src/init.rs:370 JSON-output also emits
    'defaultMode': 'dontAsk' literal.
  grep 'dontAsk' rust/crates/ → 4 matches. None explain that
    dontAsk == danger-full-access anywhere user-facing.

Fix shape (~60 lines):
- STARTER_CLAW_JSON default → 'default' (explicit safe). Users
  wanting danger-full-access opt in. ~5 lines.
- init output warns when effective mode is DangerFullAccess:
  'security: danger-full-access (unconditional tool approval).'
  ~15 lines.
- Structure the init JSON:
  {kind, files:[{path,action}], resolved_permission_mode,
   permission_mode_source, security_warnings:[]}
  ~30 lines.
- Deprecate 'dontAsk' alias OR log warning at parse: 'alias for
  danger-full-access; grants unconditional tool access'. ~8 lines.
- Regression tests per outcome.

Builds on #87 and amplifies it:
  #87: absence-of-config default = danger-full-access
  #101: fail-OPEN on bad RUSTY_CLAUDE_PERMISSION_MODE env var
  #115: init actively generates the dangerous default

Three sequential compounding permission-posture failures.

Joins Permission-audit/tool-allow-list (#94, #97, #101, #106)
as 5th member — init-time anchor of the permission problem.
Joins Silent-flag/documented-but-unenforced on silent-setting
axis. Cross-cluster with Reporting-surface/config-hygiene
(prose-wrapped JSON) and Truth-audit (misleading 'Next step'
phrasing).

Natural bundle: #87 + #101 + #115 — 'permission drift at every
boundary': absence default + env-var bypass + init-generated.

Flagship permission-audit sweep grows 7-way:
  #50 + #87 + #91 + #94 + #97 + #101 + #115

Filed in response to Clawhip pinpoint nudge 1494917922076889139
in #clawcode-building-in-public.
 		2026-04-18 13:32:46 +09:00
.claude/sessions fix: tool input {} prefix bug, tool display after accumulation, max_iterations unlimited 2026-04-01 02:24:18 +00:00
.github Close the clawability backlog with deterministic CLI output and lane lineage 2026-04-05 18:41:02 +00:00
assets Refresh docs to match ultraworkers/claw-code source of truth 2026-04-05 18:11:25 +00:00
docs US-010: Add model compatibility documentation 2026-04-16 10:55:58 +00:00
rust US-024: Add token limit metadata for kimi models 2026-04-17 04:15:38 +00:00
src chore: additional AI slop cleanup and enforcer wiring from sessions 1/5 2026-04-03 18:35:27 +09:00
tests Rewriting Project Claw Code - Python port with Rust on the way 2026-03-31 08:16:20 -07:00
.claude.json feat: default OAuth config for API endpoint, merge UI polish rendering 2026-04-01 03:20:26 +00:00
.gitignore Keep local clawhip artifacts from tripping routine repo work 2026-04-12 14:47:40 +00:00
CLAUDE.md feat: default OAuth config for API endpoint, merge UI polish rendering 2026-04-01 03:20:26 +00:00
Containerfile Document a repeatable container workflow for the Rust workspace 2026-04-05 18:11:25 +00:00
PARITY.md docs(PARITY.md): comprehensive status update — all 9 lanes merged, stubs replaced 2026-04-03 19:39:28 +09:00
PHILOSOPHY.md docs: add philosophy document for autonomous claw development 2026-04-04 16:51:51 +00:00
README.md Make ACP/Zed status obvious before users go source-diving 2026-04-16 03:13:50 +00:00
ROADMAP.md ROADMAP #115: claw init hardcodes 'defaultMode: dontAsk' alias for danger-full-access; init output zero security signal; JSON wraps prose 2026-04-18 13:32:46 +09:00
USAGE.md Align auth docs with the removed login/logout surface 2026-04-11 17:28:47 +00:00
install.sh feat: b6-codex-session — batch 6 2026-04-07 15:52:30 +09:00
prd.json US-024: Add token limit metadata for kimi models 2026-04-17 04:15:38 +00:00
progress.txt US-011: Performance optimization for API request serialization 2026-04-16 11:11:45 +00:00

README.md

Claw Code

ultraworkers/claw-code · Usage · Rust workspace · Parity · Roadmap · UltraWorkers Discord

Star history for ultraworkers/claw-code

Claw Code

Claw Code is the public Rust implementation of the claw CLI agent harness. The canonical implementation lives in rust/, and the current source of truth for this repository is ultraworkers/claw-code.

[!IMPORTANT] Start with USAGE.md for build, auth, CLI, session, and parity-harness workflows. Make claw doctor your first health check after building, use rust/README.md for crate-level details, read PARITY.md for the current Rust-port checkpoint, and see docs/container.md for the container-first workflow.

ACP / Zed status: claw-code does not ship an ACP/Zed daemon entrypoint yet. Run claw acp (or claw --acp) for the current status instead of guessing from source layout; claw acp serve is currently a discoverability alias only, and real ACP support remains tracked separately in ROADMAP.md.

Current repository shape

  • rust/ — canonical Rust workspace and the claw CLI binary
  • USAGE.md — task-oriented usage guide for the current product surface
  • PARITY.md — Rust-port parity status and migration notes
  • ROADMAP.md — active roadmap and cleanup backlog
  • PHILOSOPHY.md — project intent and system-design framing
  • src/ + tests/ — companion Python/reference workspace and audit helpers; not the primary runtime surface

Quick start

[!NOTE] [!WARNING] cargo install claw-code installs the wrong thing. The claw-code crate on crates.io is a deprecated stub that places claw-code-deprecated.exe — not claw. Running it only prints "claw-code has been renamed to agent-code". Do not use cargo install claw-code. Either build from source (this repo) or install the upstream binary:

cargo install agent-code   # upstream binary — installs 'agent.exe' (Windows) / 'agent' (Unix), NOT 'agent-code'

This repo (ultraworkers/claw-code) is build-from-source only — follow the steps below.

# 1. Clone and build
git clone https://github.com/ultraworkers/claw-code
cd claw-code/rust
cargo build --workspace

# 2. Set your API key (Anthropic API key — not a Claude subscription)
export ANTHROPIC_API_KEY="sk-ant-..."

# 3. Verify everything is wired correctly
./target/debug/claw doctor

# 4. Run a prompt
./target/debug/claw prompt "say hello"

[!NOTE] Windows (PowerShell): the binary is claw.exe, not claw. Use .\target\debug\claw.exe or run cargo run -- prompt "say hello" to skip the path lookup.

Windows setup

PowerShell is a supported Windows path. Use whichever shell works for you. The common onboarding issues on Windows are:

  1. Install Rust first — download from https://rustup.rs/ and run the installer. Close and reopen your terminal when it finishes.
  2. Verify Rust is on PATH: 
    cargo --version
    If this fails, reopen your terminal or run the PATH setup from the Rust installer output, then retry.
  3. Clone and build (works in PowerShell, Git Bash, or WSL): 
    git clone https://github.com/ultraworkers/claw-code
cd claw-code/rust
cargo build --workspace
  4. Run (PowerShell — note .exe and backslash): 
    $env:ANTHROPIC_API_KEY = "sk-ant-..."
.\target\debug\claw.exe prompt "say hello"

Git Bash / WSL are optional alternatives, not requirements. If you prefer bash-style paths (/c/Users/you/... instead of C:\Users\you\...), Git Bash (ships with Git for Windows) works well. In Git Bash, the MINGW64 prompt is expected and normal — not a broken install.

[!NOTE] Auth: claw requires an API key (ANTHROPIC_API_KEY, OPENAI_API_KEY, etc.) — Claude subscription login is not a supported auth path.

Run the workspace test suite:

cd rust
cargo test --workspace

Documentation map

Ecosystem

Claw Code is built in the open alongside the broader UltraWorkers toolchain:

Ownership / affiliation disclaimer

  • This repository does not claim ownership of the original Claude Code source material.
  • This repository is not affiliated with, endorsed by, or maintained by Anthropic.