Answer: Run evals from the command line with `agent-sdk eval --dir . --tag smoke` to filter by tag (use `agent-sdk eval --dir . --list` to list cases). Status: Confirmed Entry: tool/cursor/agents-and-automation/run-evals-cli-tag Revision: 1 Digest: sha256:448891d7d07132cb (changes whenever the content changes) Timeline: Created: 2026-11-13T03:08:26Z Last changed: 2026-11-13T03:08:26Z Last verified: 2026-11-20T12:32:38Z Next check: 2026-11-21T12:32:38Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of tag filter command | agent-sdk eval --dir . --tag smoke | [1] | 2026-11-20 list command | agent-sdk eval --dir . --list | [1] | 2026-11-20 tag used in example | smoke | [1] | 2026-11-20 evals directory | evals/ | [1] | 2026-11-20 Sources: [1] Anysphere. "cursor.com/docs/agent-sdk/evals.md". https://cursor.com/docs/agent-sdk/evals.md Role: primary. Accessed: 2026-11-20T12:32:38Z Quote: "agent-sdk eval --dir . --tag smoke" (Supports: tag filter command) Quote: "agent-sdk eval --dir . --list" (Supports: list command) Quote: "tags: ["smoke"]," (Supports: tag used in example) Quote: "Evals live in `evals/` beside `bot/`." (Supports: evals directory) Snapshot SHA-256: 582c4d2c88f54719b10b46b027c5bd4b4de34bb4e6b57d84dc80bd00a1c00a5b (captured 2026-11-13T03:08:26Z) 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 2026-11-13T03:08:26Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:32:38Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:32:38Z Last attempt: 2026-11-20T12:32:38Z Notes and limitations: Extracted automatically from a single official source (section "Protect a tool decision"). Related: https://latestn.com/tool/cursor/agents-and-automation/run-one-measured-round How do I run one measured round of hillclimbing in Cursor? https://latestn.com/tool/cursor/agents-and-automation/scaffold-run-owners-agent How do I scaffold and run the Cursor agentic-owners pull request review agent? https://latestn.com/tool/cursor/agents-and-automation/schedule-cron-cadence What cron format and timezone do Cursor schedules use, and what cadence options do reminders support? https://latestn.com/tool/cursor/agents-and-automation/reviewer-assignment How does Cursor PR Routing & Approval assign reviewers to pull requests? https://latestn.com/tool/cursor/agents-and-automation/risk-based-approval How does risk-based approval work in Cursor PR Routing & Approval? https://latestn.com/tool/cursor/agents-and-automation/run-agent-review How do I run a Cursor Agent Review on my changes? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:08:26Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/cursor/agents-and-automation/run-evals-cli-tag/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/cursor/agents-and-automation/run-evals-cli-tag POST: https://latestn.com/dispute/tool/cursor/agents-and-automation/run-evals-cli-tag with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/cursor/agents-and-automation/run-evals-cli-tag?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I run Cursor agent evals from the command line and filter by tag? Revision 1, last verified 2026-11-20T12:32:38Z. https://latestn.com/tool/cursor/agents-and-automation/run-evals-cli-tag (accessed 2026-11-21T10:02:24Z). @misc{LatestN_tool_cursor_agents_and_automation_run_evals_cli_tag_r1, title = {How do I run Cursor agent evals from the command line and filter by tag?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/cursor/agents-and-automation/run-evals-cli-tag}}, note = {Revision 1; digest sha256:448891d7d07132cb; last verified 2026-11-20T12:32:38Z; accessed 2026-11-21T10:02:24Z} } 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/cursor/agents-and-automation/run-evals-cli-tag