Answer: You name the scan effort in your request at the Claude Code prompt, such as `/claude-security scan my public API code at high`. The options are `low` (a quick first look), `medium` (the default), and `high` (what `medium` does, plus more hunting for vulnerabilities in the same code). Status: Confirmed Entry: tool/claude-code/features/choose-scan-effort Revision: 1 Digest: sha256:f0ba50f3fef62ba5 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:03:36Z Last changed: 2026-11-13T03:03:36Z Last verified: 2026-11-20T12:19:05Z Next check: 2026-11-21T12:19:05Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of How to choose | Name the scan effort in your request at the Claude Code prompt | [1] | 2026-11-20 Example command | /claude-security scan my public API code at high | [1] | 2026-11-20 Low effort | a quick first look | [1] | 2026-11-20 Medium effort | the default | [1] | 2026-11-20 High effort | what `medium` does, plus more hunting for vulnerabilities in the same code | [1] | 2026-11-20 Large repository advice | choose `high` scan effort, scan a second time, or do both | [1] | 2026-11-20 Sources: [1] Anthropic. "Scan your codebase for vulnerabilities". https://code.claude.com/docs/en/claude-security.md Role: primary. Accessed: 2026-11-20T12:19:05Z Quote: "Name the scan effort in your request at the Claude Code prompt" (Supports: How to choose) Quote: "such as `/claude-security scan my public API code at high`" (Supports: Example command) Quote: "**`low`**: a quick first look." (Supports: Low effort) Quote: "**`medium`**: the default." (Supports: Medium effort) Quote: "**`high`**: what `medium` does, plus more hunting for vulnerabilities in the same code." (Supports: High effort) Quote: "If a scan of a large repository finds less than you expect, choose `high` scan effort, scan a second time, or do both." (Supports: Large repository advice) Published: 2026-11-20T03:10:57Z Snapshot SHA-256: 066e0c992efe84f483e98caecd1b0d9166cffbb694fd8ad1d02bf49031aa4fc3 (captured 2026-11-13T03:03:36Z) 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 2026-11-13T03:03:36Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:19:05Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:19:05Z Last attempt: 2026-11-20T12:19:05Z Notes and limitations: Extracted automatically from a single official source (section "Choose a scan effort"). Related: https://latestn.com/tool/claude-code/features/clean-up-worktrees How do I clean up worktrees that Claude Code created? https://latestn.com/tool/claude-code/features/code-mode-requirements-limits What are the requirements and limitations of Code Mode in Claude Code? https://latestn.com/tool/claude-code/features/code-review-levels What review levels does Claude Code Code Review offer? https://latestn.com/tool/claude-code/features/checkpoint-retention-limit How many checkpoints does Claude Code keep for rewinding a session? https://latestn.com/tool/claude-code/features/checkpointing-limitations What are the limitations of Claude Code file checkpointing, such as Bash commands or subagent edits not being tracked? https://latestn.com/tool/claude-code/features/choose-extension-by-goal Which Claude Code extension should I use for a given goal, such as adding persistent context, connecting external services, or automating workflows? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:03:36Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/features/choose-scan-effort/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/features/choose-scan-effort POST: https://latestn.com/dispute/tool/claude-code/features/choose-scan-effort with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/features/choose-scan-effort?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I choose the scan effort level for a Claude Security scan in Claude Code? Revision 1, last verified 2026-11-20T12:19:05Z. https://latestn.com/tool/claude-code/features/choose-scan-effort (accessed 2026-11-21T09:59:35Z). @misc{LatestN_tool_claude_code_features_choose_scan_effort_r1, title = {How do I choose the scan effort level for a Claude Security scan in Claude Code?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/features/choose-scan-effort}}, note = {Revision 1; digest sha256:f0ba50f3fef62ba5; last verified 2026-11-20T12:19:05Z; accessed 2026-11-21T09:59:35Z} } 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/features/choose-scan-effort