fix-all-issues workflow, and prints a manual fallback when mcp add fails. The rest is documentation: the home page and human guide were rewritten, ClaudeCodeAgent authentication is documented, and stale model IDs in the examples were refreshed. There are no breaking changes and no public API symbols were removed.
One-command onboarding
bunx smithers-orchestrator init now does the whole setup in one step.
initauto-installs the curatedsmithersskill into the coding agents it detects on your machine, so there is no more manualmkdirorcurl.- It seeds an editable
helloworkflow (.smithers/workflows/hello.tsxwith its prompt in.smithers/prompts/hello.mdx) as the smallest end-to-end example to run and tweak. - The home page and the For Humans guide were rewritten around this one-command flow.
Workflows
- New
fix-all-issuesworkflow: it decomposes every open issue, drives a Codex test-first implementation, runs dual review, and opens a PR. AnexcludeNumbersfilter lets you skip specific issues.
Agents
- Fixed a Codex regression where native structured output was always on, which removed tool access from agentic tasks. Native structured output is now opt-in, so agentic Codex tasks keep their tools.
- Documented
ClaudeCodeAgentauthentication: subscription billing by default (the agent clearsANTHROPIC_API_KEYso theclaudeCLI bills your Pro/Max subscription), per-directory subscription login viaconfigDir(CLAUDE_CONFIG_DIR), and API billing viaapiKey. - Refreshed stale model IDs in the AI SDK examples and integration docs (
claude-sonnet-4-5-20250929toclaude-sonnet-4-6,gpt-5.2-codextogpt-5.5).
CLI
bunx smithers-orchestrator mcp addnow prints a copy-paste manual fallback command when the underlying agent’smcp addfails, so registration is recoverable without leaving the terminal.
Quality
- Added an agent-fluency eval suite: a weak-model, one-shot regression suite that exercises every Smithers feature.