Answer: Set a case's max_turns, timeout_seconds, model, tags, and allowed_tools in prompt.md frontmatter; the prompt.md frontmatter reference lists every field and its default. Status: Confirmed Entry: tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools Revision: 3 Digest: sha256:df83229a796b159d (changes whenever the content changes) Timeline: Created: 2026-11-13T03:04:54Z Last changed: 2026-11-20T12:22:43Z (fields to set: — → max_turns) Last verified: 2026-11-20T12:22:43Z Next check: 2026-11-21T12:22:43Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of fields to set | max_turns | [1] | 2026-11-20 allowed tools field | allowed_tools | [1] | 2026-11-20 Sources: [1] Anthropic. "Test plugins with evals". https://code.claude.com/docs/en/plugin-evals.md Role: primary. Accessed: 2026-11-20T12:22:43Z Quote: "Set a case's `max_turns`, `timeout_seconds`, `model`, `tags`, and the `allowed_tools` it may use in `prompt.md` frontmatter" (Supports: fields to set) Quote: "grant a tool for it in `allowed_tools`" (Supports: allowed tools field) Published: 2026-11-20T03:14:09Z Snapshot SHA-256: f612b7a35aa589f2beeeded25d8143492fde96a41688bf016856679a58211a98 (captured 2026-11-19T12:18:12Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-19T12:18:12Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:22:43Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:22:43Z Last attempt: 2026-11-20T12:22:43Z Notes and limitations: Extracted automatically from a single official source (section "Set run limits and tools in prompt.md"). Related: https://latestn.com/tool/claude-code/agents-and-automation/set-up-first-hook How do I set up a hook in Claude Code to run a shell command automatically? https://latestn.com/tool/claude-code/agents-and-automation/setting-sources-not-controlled Which settings does settingSources in the Claude Code SDK not control? https://latestn.com/tool/claude-code/agents-and-automation/single-message-input-limitations What are the limitations of single message input in the Claude Agent SDK? https://latestn.com/tool/claude-code/agents-and-automation/sessionstore-interface-methods What methods does the Claude Code SessionStore interface require and which are optional? https://latestn.com/tool/claude-code/agents-and-automation/set-claude-code-preset-system-prompt How do I set the claude_code preset as the system prompt in the Claude Code Agent SDK? https://latestn.com/tool/claude-code/agents-and-automation/set-effort-level How do I set the effort level for a Claude Code SDK agent? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T12:22:43Z | changed | fields to set: — → max_turns | [1] 2026-11-20T12:22:43Z | changed | file access note: @path → — | [1] 2026-11-20T12:22:43Z | changed | reference for fields and defaults: prompt.md frontmatter → — | [1] 2026-11-20T12:22:43Z | changed | tags field: tags → — | [1] 2026-11-20T12:22:43Z | changed | model field: model → — | [1] 2026-11-20T12:22:43Z | changed | timeout field: timeout_seconds → — | [1] 2026-11-20T12:22:43Z | changed | fields to set in prompt.md frontmatter: max_turns → — | [1] 2026-11-18T12:18:02Z | changed | file access note: — → @path | [1] 2026-11-18T12:18:02Z | changed | reference for fields and defaults: — → prompt.md frontmatter | [1] 2026-11-18T12:18:02Z | changed | tags field: — → tags | [1] 2026-11-18T12:18:02Z | changed | model field: — → model | [1] 2026-11-18T12:18:02Z | changed | timeout field: — → timeout_seconds | [1] 2026-11-13T03:04:54Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools POST: https://latestn.com/dispute/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I set run limits and allowed tools for a Claude Code eval case in prompt.md? Revision 3, last verified 2026-11-20T12:22:43Z. https://latestn.com/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools (accessed 2026-11-21T10:03:33Z). @misc{LatestN_tool_claude_code_agents_and_automation_set_eval_run_limits_and_tools_r3, title = {How do I set run limits and allowed tools for a Claude Code eval case in prompt.md?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools}}, note = {Revision 3; digest sha256:df83229a796b159d; last verified 2026-11-20T12:22:43Z; accessed 2026-11-21T10:03:33Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/agents-and-automation/set-eval-run-limits-and-tools