Answer: In SDK sessions, you can pre-approve tools for a project or personal skill with the skill's `allowed-tools` frontmatter or with the `allowedTools` option (`allowed_tools` in Python) in your query configuration. The example pre-approves `Read`, `Grep`, and `Glob` with `allowedTools`. Status: Confirmed Entry: tool/claude-code/permissions-and-security/pre-approve-tools-for-skills Revision: 3 Digest: sha256:75f50ad48fa68318 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:02:59Z Last changed: 2026-11-20T12:17:20Z (managed setting that overrides: — → allowManagedPermissionRulesOnly) Last verified: 2026-11-20T12:17:20Z Next check: 2026-11-21T12:17:20Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of frontmatter option | allowed-tools | [1] | 2026-11-20 query configuration option | allowedTools | [1] | 2026-11-20 Python option name | allowed_tools | [1] | 2026-11-20 example pre-approved tools | Read | [1] | 2026-11-20 managed setting that overrides | allowManagedPermissionRulesOnly | [1] | 2026-11-20 Sources: [1] Anthropic. "Extend agents with skills". https://code.claude.com/docs/en/agent-sdk/skills.md Role: primary. Accessed: 2026-11-20T12:17:20Z Quote: "pre-approve tools for a project or personal skill with the skill's [`allowed-tools`]" (Supports: frontmatter option) Quote: "or with the `allowedTools` option (`allowed_tools` in Python) in your query configuration" (Supports: query configuration option) Quote: "(`allowed_tools` in Python)" (Supports: Python option name) Quote: "allowed_tools=["Read", "Grep", "Glob"]" (Supports: example pre-approved tools) Quote: "If your organization sets [`allowManagedPermissionRulesOnly`](https://code.claude.com/docs/en/settings-reference#allowmanagedpermissionrulesonly) in managed settings, Claude Code ignores both." (Supports: managed setting that overrides) Published: 2026-11-20T03:26:04Z Snapshot SHA-256: 2f354b9ef0092b59ee87feb47048d185030bfbc566e323d84643dc68dc061cbe (captured 2026-11-20T12:17:17Z) 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]. Cross-check: not-available at 2026-11-20T12:17:20Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:17:20Z Last attempt: 2026-11-20T12:17:20Z Notes and limitations: Extracted automatically from a single official source (section "Pre-approve tools for skills"). Related: https://latestn.com/tool/claude-code/permissions-and-security/prompt-injection-protections How does Claude Code protect against prompt injection? https://latestn.com/tool/claude-code/permissions-and-security/relay-permission-prompts How do I relay permission prompts so I can approve or deny tool use remotely in Claude Code? https://latestn.com/tool/claude-code/permissions-and-security/remove-untrusted-plugin How do I remove a Claude Code plugin I no longer trust? https://latestn.com/tool/claude-code/permissions-and-security/permission-modes What permission modes does Claude Code support and what does each one do? https://latestn.com/tool/claude-code/permissions-and-security/pin-permission-mode-self-hosted How do I pin a permission mode or pre-approve specific tools for Claude Code self-hosted sessions? https://latestn.com/tool/claude-code/permissions-and-security/plugin-capabilities What can a Claude Code plugin do on my machine? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T12:17:20Z | changed | managed setting that overrides: — → allowManagedPermissionRulesOnly | [1] 2026-11-20T12:17:20Z | changed | example pre-approved tools: — → Read | [1] 2026-11-20T12:17:20Z | changed | Python option name: — → allowed_tools | [1] 2026-11-20T12:17:20Z | changed | query configuration option: — → allowedTools | [1] 2026-11-20T12:17:20Z | changed | frontmatter option: — → allowed-tools | [1] 2026-11-20T12:17:20Z | changed | managed setting that disables both: allowManagedPermissionRulesOnly → — | [1] 2026-11-20T12:17:20Z | changed | query config option (Python): allowed_tools → — | [1] 2026-11-20T12:17:20Z | changed | query config option (TypeScript): allowedTools → — | [1] 2026-11-20T12:17:20Z | changed | frontmatter method: allowed-tools → — | [1] 2026-11-18T12:13:06Z | changed | managed setting that disables both: — → allowManagedPermissionRulesOnly | [1] 2026-11-18T12:13:06Z | changed | query config option (Python): — → allowed_tools | [1] 2026-11-18T12:13:06Z | changed | query config option (TypeScript): — → allowedTools | [1] 2026-11-18T12:13:06Z | changed | frontmatter method: — → allowed-tools | [1] 2026-11-18T12:13:06Z | changed | managed setting that overrides: allowManagedPermissionRulesOnly → — | [1] 2026-11-18T12:13:06Z | changed | Python option: allowed_tools → — | [1] 2026-11-18T12:13:06Z | changed | SDK option: allowedTools → — | [1] 2026-11-18T12:13:06Z | changed | frontmatter option: allowed-tools → — | [1] 2026-11-13T03:02:59Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/permissions-and-security/pre-approve-tools-for-skills/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/permissions-and-security/pre-approve-tools-for-skills POST: https://latestn.com/dispute/tool/claude-code/permissions-and-security/pre-approve-tools-for-skills with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/permissions-and-security/pre-approve-tools-for-skills?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I pre-approve tools for skills in Claude Agent SDK? Revision 3, last verified 2026-11-20T12:17:20Z. https://latestn.com/tool/claude-code/permissions-and-security/pre-approve-tools-for-skills (accessed 2026-11-21T10:07:47Z). @misc{LatestN_tool_claude_code_permissions_and_security_pre_approve_tools_for_skills_r3, title = {How do I pre-approve tools for skills in Claude Agent SDK?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/permissions-and-security/pre-approve-tools-for-skills}}, note = {Revision 3; digest sha256:75f50ad48fa68318; last verified 2026-11-20T12:17:20Z; accessed 2026-11-21T10:07:47Z} } 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/permissions-and-security/pre-approve-tools-for-skills