@swarmcraftai/cli 0.5.1 → 0.6.0

package/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 All notable changes to the SwarmCraft CLI are documented in this file.
 
+## 0.6.0
+
+- Adds Claude Code subscription support to repository bootstrap, Operate, and one-shot, with generated `.claude/skills` and owner-preserving `CLAUDE.md` guidance.
+- Checks local Claude subscription login, preserves macOS login discovery, and rejects API credential injection on that path.
+- Preserves blocked run state after provider failures and supports do/check through human review and resume.
+- Refreshes installation, native Windows, provider setup, permissions, and recovery instructions.
+- Requires the coordinated API update for Claude Operate telemetry; deploy the API before this client.
+
 ## 0.5.1
 
 - Refreshes the npm README around customer installation and common workflows, with native PowerShell commands, Node/npm verification, managed-machine recovery and VS Code restart guidance.

package/README.md

@@ -9,7 +9,7 @@ The CLI brings SwarmCraft workflows to your terminal. Use it to prepare a local
 - Node.js 20.19 or newer, npm, and Git.
 - A SwarmCraft account and a project with tasks ready to implement.
 - A local Git repository with unrelated changes committed or stashed.
-- Codex CLI or GitHub Copilot CLI installed and configured, or SwarmCraft Managed AI credits.
+- Codex CLI, GitHub Copilot CLI, or Claude Code CLI installed and configured, or SwarmCraft Managed AI credits.
 
 On macOS and Windows, start with [SwarmCraft Setup](https://swarmcraft.ai/docs/set-up-and-connect/use-swarmcraft-setup) to prepare your environment.
 
@@ -89,12 +89,13 @@ swarmcraft init --project <project-id> --workspace . --agent-provider codex
 
 ## Choose an agent
 
+- **Claude Code subscription:** use `--agent-provider claude` after local Claude sign-in.
 - **Codex:** use `--agent-provider codex`.
 - **GitHub Copilot:** use `--agent-provider copilot`.
 - **SwarmCraft Managed AI:** use `--agent-provider managed` with `one-shot`. The CLI shows your credit balance and an estimated stage range before starting. If credits run out, add credits and resume the blocked run.
 - **Custom commands and local models:** `--agent-command` overrides the provider command and supports models available through your agent, including local models. The template is executed through a shell, so use only commands you trust. Keep secrets out of command text; use `--agent-env-file` with `--agent-api-key-env-name` for provider credentials.
 
-Codex, Copilot, and custom providers use your own provider setup and are outside the Managed AI fee.
+Codex, Copilot, Claude Code, and custom providers use your own provider setup and are outside the Managed AI fee.
 
 ## Inspect and resume work
 
@@ -148,3 +149,21 @@ Run `swarmcraft auth login` again if your session has expired. For Discovery dia
 Support bundles redact credentials; Discovery bundles exclude source and package content. Review any diagnostic files before sharing them.
 
 See the [one-shot walkthrough](https://swarmcraft.ai/docs/build-and-ship/deliver-with-the-one-shot-cli), [troubleshooting guide](https://swarmcraft.ai/docs/help-and-reference/troubleshoot-swarmcraft), or [contact support](https://swarmcraft.ai/login?next=%2Fapp%2Fsupport).
+
+### Claude Code subscription runs
+
+Select `--agent-provider claude` for bootstrap, Operate, or one-shot. Install the
+standalone Claude Code CLI, run `claude auth login`, and confirm subscription
+usage in `/status`. The VS Code extension alone does not install the terminal
+command. SwarmCraft checks the effective `claude.ai` login without retaining
+its output and rejects provider credential flags on this subscription path.
+
+One-shot invokes `/swarmcraft-do` and `/swarmcraft-check` with `dontAsk`:
+configure the necessary tool permissions in Claude before running; unapproved
+tools are denied. The default never enables permission bypass or API-only bare
+mode. Claude keeps ownership of login storage and sandbox settings. Use
+`--max-agent-requests` to bound invocations; subscription limits still apply.
+Cost telemetry remains unknown unless an explicit adapter supplies it; required
+cost telemetry fails when absent. Dollar estimates are not subscription bills.
+After correcting login, permissions, or a usage limit, resume the recorded run.
+Live subscription/platform verification is tracked in the implementation plan.