askClaude() passed the full multi-line prompt as a claude
Fix: keep only the short, safe flags (--model, -p) as args and send the prompt over stdin via spawnSync input. The prompt never touches the shell command line, so multi-line/special-char prompts arrive intact. claude -p reads stdin on macOS/Linux too, so behavior is unchanged there.
Verified on Windows 11 (Node 24, claude CLI via npm): real turns now return correct responses, and node tests/scripts/claw.test.js passes 19/19.
Co-authored-by: skausage-ops <268783127+skausage-ops@users.noreply.github.com>
Fixes#1469.
On Windows the `claude` binary installed via `npm i -g @anthropic-ai/claude-code`
is `claude.cmd`, and Node's spawn() cannot resolve .cmd wrappers via PATH
without shell: true. The call failed with `spawn claude ENOENT` and claw.js
returned an error string to the caller.
Mirrors the fix pattern applied in PR #1456 for the MCP health-check hook.
'claude' is a hardcoded literal (not user input), so enabling shell on Windows
only is safe.
- Swap loadHistory/appendTurn order to prevent user message appearing
twice in the prompt (once in history, once as USER MESSAGE)
- Calculate actual loaded skill count via fs.existsSync instead of
counting requested skill names (banner now reflects reality)
- Add err.stack to test harness error output for better debugging
Implements a barebones agent loop that delegates to `claude -p` with
markdown-as-database session persistence and ECC skill context loading.
Zero external dependencies, ~264 lines of pure Node.js CommonJS.
- scripts/claw.js: core module (storage, context, delegation, REPL)
- commands/claw.md: slash command definition with usage docs
- tests/scripts/claw.test.js: 14 unit tests covering all modules
- package.json: add claw script and files entry
- tests/run-all.js: register claw tests in test manifest
