{"version":"2.1.271","anchor":"skill-inline-shell-commands-can-be-handed-off-to-the-model-i","canonical_anchor":"skill-inline-shell-commands-can-be-handed-off-to-the-model-i","heading":"Skill inline shell commands can be handed off to the model instead of auto-run","tier":"notice","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271\/e\/skill-inline-shell-commands-can-be-handed-off-to-the-model-i","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.271","markdown":"### Skill inline shell commands can be handed off to the model instead of auto-run\n\nInline shell commands in a skill's instructions can now be handed to the model to run explicitly instead of executing silently\n\n**Unclear.** Whether this behavior is active depends on gates (`tengu_iterative_falcon`, `tengu_prompt_shell_permission`) that have not been read, and `tengu_glowing_orbit`, which this site's account currently reads as on but has not yet been read under this release.\n\n**What**\n\nSkills are packaged instructions written in markdown, and some embed inline shell commands (written as `!command` or in fenced `!` blocks) that run automatically. When the permission decision for one of these commands is 'ask' (meaning Claude Code would normally prompt before running it), or a deny that's tied to an async-agent reason, a new code path can replace the command with a placeholder and instead tell the model to run it explicitly, exactly as written, and use its output. This turns what used to be an invisible side effect into a visible, explicit step in the conversation.\n\n**Why**\n\nThis gives more visibility and control over shell commands embedded in skills, so a command that needs permission or was previously denied doesn't just silently fail or run without the user noticing.\n\n- Flag `tengu_iterative_falcon`: Not enough to say (read for one account on one subscription tier against v2.1.271; this account: no value returned, anonymous baseline: no value returned, compiled default: on) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Flag `tengu_glowing_orbit`: On for this account, and not off by default (read for one account on one subscription tier against v2.1.271; this account: on, anonymous baseline: on, compiled default: on) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: Skills\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5"}