# Claude Code Unrecognized Model

> Detect a fatal Claude Code harness model-configuration fault and abort early. Trigger when a run's stderr contains `claude-code:unrecognized_model` or the configured `model` field names an ID the CLI does not recognize (e.g. `deepseek-flash`), so the run would otherwise stall to its full timeout with no task artifacts.

- Skill: `ruc-nlpir/claude-code-unrecognized-model` (Agent Skill)
- Install (CLI): `npx get-skill add ruc-nlpir/claude-code-unrecognized-model`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ruc-nlpir/claude-code-unrecognized-model/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: ruc-nlpir (https://skillmd.com/u/ruc-nlpir)
- Updated: 2026-11-16
- Page: https://skillmd.com/skills/ruc-nlpir/claude-code-unrecognized-model

---

An `unrecognized_model` error is an environment/configuration fault, not a defect
in the task implementation. When the session's `model` field names an ID the
Claude Code CLI does not recognize (e.g. `deepseek-flash`), API calls fail and
the run stalls to its full timeout (e.g. 900s) without producing the requested
files.

Do:
- Confirm the configured `model` early. If it is not a recognized Claude model,
  surface the mismatch and stop instead of spending the time budget.
- If `claude-code:unrecognized_model` appears in stderr — it can surface on an
  auxiliary query such as `generate_session_title` — abort the run and report
  the configuration failure.
- When a run times out, inspect stderr before judging the implementation: an
  `unrecognized_model` timeout is a configuration fault, not evidence about the
  task's implementation quality.

