{"name":"readOnly","slug":"readonly","family":"setting","title":"Settings keys","noun":"settings key","description":"Skill results now flag when a skill was only read rather than actually run.","description_source":"entry","described_by":{"version":"2.1.238","anchor":"skill-results-say-when-the-skill-was-only-read"},"presence":{"first_seen":null,"removed_in":null,"in_current_build":false,"newest_mined":"2.1.309","builds":0,"mined_builds":150,"first_cited":null},"aliases":["readonly"],"entries":[{"version":"2.1.290","anchor":"heredocpipeline-and-redirect-parsing-in-the-bash-static-ana","heading":"Bash permission checks handle heredocs, fd redirects and export prefixes differently","line":"Claude Code's Bash command checker now treats text after a heredoc, `{fd}>` redirects and variables set before export differently","released_at":"2026-10-05 18:12:44","reason":"found in this entry's text"},{"version":"2.1.281","anchor":"auto-mode-can-hold-locally-auto-allowed-shell-commands-for-a","heading":"Auto mode can hold locally auto-allowed shell commands for a server-side classifier","line":"In auto mode, shell commands allowed locally by sandbox or read-only rules can now be held for a server-side classifier to review","released_at":"2026-09-23 17:01:17","reason":"found in this entry's text"},{"version":"2.1.277","anchor":"read-only-agent-memory-mode-added-to-memory-system-prompt-bu","heading":"Read-only agent memory mode added to memory system prompt builder","line":"Persistent memory can now be loaded in a read-only mode that tells the model it can't save new memories this session","released_at":"2026-09-18 16:22:26","reason":"found in this entry's text"},{"version":"2.1.273","anchor":"shell-safety-analyzer-new-differential-detection-for-array","heading":"Shell-safety analyzer: new differential detection for array-assignment-shaped flags","line":"Shell-safety checker now flags export\/readonly commands whose flags look like an array assignment","released_at":"2026-09-15 18:06:34","reason":"named in this entry, found in this entry's text"},{"version":"2.1.271","anchor":"shell-command-safety-check-expanded-for-declaretypesetloca","heading":"Shell command safety check expanded for declare\/typeset\/local flags","line":"Shell command safety check now catches more declare\/typeset\/local flag combinations, and drops a narrower older check","released_at":"2026-09-14 19:45:19","reason":"found in this entry's text"},{"version":"2.1.248","anchor":"skill-results-describe-read-only-loading-and-background-sub-","heading":"Skill results describe read-only loading and background sub-agents","line":"Skill results now say when instructions were only loaded, or when a background sub-agent was launched.","released_at":"2026-08-27 20:35:36","reason":"found in this entry's text"},{"version":"2.1.246","anchor":"tool-inputs-with-untyped-schemas-are-parsed-instead-of-arriv","heading":"Tool inputs with untyped schemas are parsed instead of arriving as text","line":"MCP and plugin tools with loose input schemas now get real data instead of stringified JSON.","released_at":"2026-08-25 19:17:34","reason":"found in this entry's text"},{"version":"2.1.238","anchor":"skill-results-say-when-the-skill-was-only-read","heading":"Skill results say when the skill was only read","line":"Skill results now flag when a skill was only read rather than actually run.","released_at":"2026-08-20 18:01:54","reason":"named in this entry, found in this entry's text"},{"version":"2.1.238","anchor":"read-only-skill-loads-tell-the-model-to-hand-execution-to-a-","heading":"Read-only skill loads tell the model to hand execution to a worker","line":"Read-only skill loads now return a note saying nothing ran and a worker should execute it.","released_at":"2026-08-20 18:01:54","reason":"found in this entry's text"}],"entries_total":9,"docs":[{"source":"api","path":"about-claude\/use-case-guides\/content-moderation","title":"content-moderation","documented":false},{"source":"api","path":"about-claude\/use-case-guides\/customer-support-chat","title":"customer-support-chat","documented":false},{"source":"api","path":"about-claude\/use-case-guides\/legal-summarization","title":"legal-summarization","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/advisor-tool","title":"advisor-tool","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/browser-use-tool","title":"browser-use-tool","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/computer-use-tool","title":"computer-use-tool","documented":false},{"source":"api","path":"agents-and-tools\/tool-use\/text-editor-tool","title":"text-editor-tool","documented":false},{"source":"api","path":"api\/claude-platform-on-aws-iam-actions","title":"claude-platform-on-aws-iam-actions","documented":false},{"source":"api","path":"build-with-claude\/claude-platform-on-aws","title":"claude-platform-on-aws","documented":false},{"source":"api","path":"build-with-claude\/mid-conversation-effort-example","title":"mid-conversation-effort-example","documented":false}],"docs_total":12,"gates":[],"related":[],"url":"https:\/\/changelogs.core-directive.com\/reference\/setting\/readonly","family_url":"https:\/\/changelogs.core-directive.com\/reference\/setting.json"}