[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74XE12P3H77SE0FHVC0GPNC":3,"skill-same:01M74XE12P3H77SE0FHVC0GPNC":43},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M74XE12P3H77SE0FHVC0GPNC","worktree-isolation-guard-refuses-complex-bash",null,"In a Claude worktree-isolated session a guard (e.g. worktree isolation) refuses Bash calls it cannot prove stay inside the worktree ('redirects git to the shared checkout via -C', 'too complex to verify', 'runs a string through .', 'command whose name is computed at runtime'), including heredoc appends and a sqlite3 call inside a construct too complex to verify. Use when a Bash call is refused in a worktree session or when writing commands for a session that runs in .claude\u002Fworktrees.","abhijitbansal\u002Fclaude-skills","abhijitbansal","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F271802621?v=4","01M74XA5M33XYNJ2D2TJDS7W9E","01M74XA5MQ8GMWJW10ZJ4V0NVG",1,"MIT","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcore-workflow\u002Fskills\u002Fworktree-isolation-guard-refuses-complex-bash\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: worktree-isolation-guard-refuses-complex-bash\ndescription: \"In a Claude worktree-isolated session a guard (e.g. worktree isolation) refuses Bash calls it cannot prove stay inside the worktree ('redirects git to the shared checkout via -C', 'too complex to verify', 'runs a string through .', 'command whose name is computed at runtime'), including heredoc appends and a sqlite3 call inside a construct too complex to verify. Use when a Bash call is refused in a worktree session or when writing commands for a session that runs in .claude\u002Fworktrees.\"\n---\n\n# Worktree isolation guard: write commands it can verify\n\n## Symptom\n\nRefusals that end `Refusing to run it`:\n\n- `this command redirects git to the shared checkout via -C`\n- `this command is too complex to verify that it stays inside the worktree`\n- `runs a string through ., which can't be verified to stay inside the worktree`\n- a command whose name is computed at runtime (`$cmd ...`)\n\nTriggers seen: `git -C \u003Cmain checkout>`, `&&` chains, `eval`, `source`,\nheredoc appends (a `KNOWN_ISSUES.md` append), and a `sqlite3` call wrapped\nin a construct too complex to verify. A user's own `!` command also failed\nwith `The command failed and the error text was withheld.`\n\nLater variants:\n\n- a path or `cd` into a directory named `eval` (`runs a string through eval`)\n- a `$VAR`\u002Fcomputed path as a node\u002Fpython argument\n- a `cat > f \u003C\u003CEOF … && python3 …` heredoc chain (`too complex to verify that\n  it stays inside the worktree`)\n- a `for` loop whose arguments contain \"git\" (`names git in a form too complex\n  to verify`)\n\n## Root cause\n\nA worktree isolation hook statically parses each Bash command and rejects anything\nit cannot prove touches only the worktree. Agents reach for habitual\ncompound forms; advice also conflicted across sessions (some said use\n`git -C`, which is exactly what the guard forbids).\n\n## Fix\n\n1. One plain command per call, run from the worktree cwd, literal command\n   names. No pipes, `&&` chains, `eval`, `source` or heredocs.\n2. Never `git -C \u003Cother path>` and never touch the shared checkout.\n3. File content goes through Write\u002FEdit, not shell appends or heredocs.\n4. To act on the main checkout, ask the user to run single commands (one\n   per `!` line), or to use a separate Terminal window. A `cd … && git …`\n   chain failed in practice and contradicts rule 1.\n5. A `!` command that fails with withheld output: have it write a log file\n   inside the worktree, then Read the log.\n   ```bash\n   some-command > .scratch\u002Fout.log 2>&1\n   ```\n6. Use literal absolute paths (no `$VAR`\u002Fcomputed paths as arguments) and\n   no `cd`. Write scripts with the Write tool and run the file. If the\n   guard false-positives on a literal directory named `eval`, a glob avoids\n   the text match while still naming the same directory:\n   `node --test \"\u002Fabs\u002Fpath\u002Fto\u002Fworktree\u002Fplugins\u002F\u003Cpkg>\u002Fev[a]l\u002F…\"`. The quoted\n   glob is expanded by `node --test` itself (Node 21+), not by the shell.\n   For other commands, use the unquoted form so the shell expands it:\n   `ls \u002Fabs\u002Fpath\u002Fto\u002Fworktree\u002Fplugins\u002F\u003Cpkg>\u002Fev[a]l\u002F`.\n7. The guard's pattern match is text-based and inconsistent: the same\n   command can pass in one session and be refused in another. Treat a refusal\n   as a signal to simplify, not as proof the command was unsafe.\n8. After a refusal, retry the simple form. Do not reword the same compound\n   command to slip past the guard; the only exception is the literal-name\n   false positive in item 6.\n\n## Evidence\n\nMined from session digests; about 6 sessions across 3 projects found\nindependently: a private-project worktree `e9097288` (the `-C` refusal), a\nprivate document-scanner app `ea9bc432` (string through `.`), a\nprivate-bot worktree `bb35f1a6` (too complex to verify), a private bot\n`c2a681f5` (withheld error text).\n\n## Related skills\n\n- `superpowers:using-git-worktrees` — how worktree sessions are set up.\n- `core-workflow:xcode-license-blocks-git-exit-69` — another git failure\n  that is environmental, not a code problem.\n- `core-workflow:blast-radius-rm-hold-unattended-subagent-stall` — the\n  sibling hook that holds `rm`.\n","# Worktree isolation guard: write commands it can verify\n\n## Symptom\n\nRefusals that end `Refusing to run it`:\n\n- `this command redirects git to the shared checkout via -C`\n- `this command is too complex to verify that it stays inside the worktree`\n- `runs a string through ., which can't be verified to stay inside the worktree`\n- a command whose name is computed at runtime (`$cmd ...`)\n\nTriggers seen: `git -C \u003Cmain checkout>`, `&&` chains, `eval`, `source`,\nheredoc appends (a `KNOWN_ISSUES.md` append), and a `sqlite3` call wrapped\nin a construct too complex to verify. A user's own `!` command also failed\nwith `The command failed and the error text was withheld.`\n\nLater variants:\n\n- a path or `cd` into a directory named `eval` (`runs a string through eval`)\n- a `$VAR`\u002Fcomputed path as a node\u002Fpython argument\n- a `cat > f \u003C\u003CEOF … && python3 …` heredoc chain (`too complex to verify that\n  it stays inside the worktree`)\n- a `for` loop whose arguments contain \"git\" (`names git in a form too complex\n  to verify`)\n\n## Root cause\n\nA worktree isolation hook statically parses each Bash command and rejects anything\nit cannot prove touches only the worktree. Agents reach for habitual\ncompound forms; advice also conflicted across sessions (some said use\n`git -C`, which is exactly what the guard forbids).\n\n## Fix\n\n1. One plain command per call, run from the worktree cwd, literal command\n   names. No pipes, `&&` chains, `eval`, `source` or heredocs.\n2. Never `git -C \u003Cother path>` and never touch the shared checkout.\n3. File content goes through Write\u002FEdit, not shell appends or heredocs.\n4. To act on the main checkout, ask the user to run single commands (one\n   per `!` line), or to use a separate Terminal window. A `cd … && git …`\n   chain failed in practice and contradicts rule 1.\n5. A `!` command that fails with withheld output: have it write a log file\n   inside the worktree, then Read the log.\n   ```bash\n   some-command > .scratch\u002Fout.log 2>&1\n   ```\n6. Use literal absolute paths (no `$VAR`\u002Fcomputed paths as arguments) and\n   no `cd`. Write scripts with the Write tool and run the file. If the\n   guard false-positives on a literal directory named `eval`, a glob avoids\n   the text match while still naming the same directory:\n   `node --test \"\u002Fabs\u002Fpath\u002Fto\u002Fworktree\u002Fplugins\u002F\u003Cpkg>\u002Fev[a]l\u002F…\"`. The quoted\n   glob is expanded by `node --test` itself (Node 21+), not by the shell.\n   For other commands, use the unquoted form so the shell expands it:\n   `ls \u002Fabs\u002Fpath\u002Fto\u002Fworktree\u002Fplugins\u002F\u003Cpkg>\u002Fev[a]l\u002F`.\n7. The guard's pattern match is text-based and inconsistent: the same\n   command can pass in one session and be refused in another. Treat a refusal\n   as a signal to simplify, not as proof the command was unsafe.\n8. After a refusal, retry the simple form. Do not reword the same compound\n   command to slip past the guard; the only exception is the literal-name\n   false positive in item 6.\n\n## Evidence\n\nMined from session digests; about 6 sessions across 3 projects found\nindependently: a private-project worktree `e9097288` (the `-C` refusal), a\nprivate document-scanner app `ea9bc432` (string through `.`), a\nprivate-bot worktree `bb35f1a6` (too complex to verify), a private bot\n`c2a681f5` (withheld error text).\n\n## Related skills\n\n- `superpowers:using-git-worktrees` — how worktree sessions are set up.\n- `core-workflow:xcode-license-blocks-git-exit-69` — another git failure\n  that is environmental, not a code problem.\n- `core-workflow:blast-radius-rm-hold-unattended-subagent-stall` — the\n  sibling hook that holds `rm`.\n",{"name":5,"description":7},"main","153711dd9432743d97f0b33b080ada5798ea623c","plugins\u002Fcore-workflow\u002Fskills\u002Fworktree-isolation-guard-refuses-complex-bash","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills","https:\u002F\u002Fgithub.com\u002Fabhijitbansal","2026-11-07 12:59:51",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add abhijitbansal\u002Fclaude-skills --skill worktree-isolation-guard-refuses-complex-bash",{"tool":35,"command":36},"bunx","bunx skills add abhijitbansal\u002Fclaude-skills --skill worktree-isolation-guard-refuses-complex-bash",{"tool":38,"command":39},"pnpm","pnpm dlx skills add abhijitbansal\u002Fclaude-skills --skill worktree-isolation-guard-refuses-complex-bash","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fcore-workflow\u002Fskills\u002Fworktree-isolation-guard-refuses-complex-bash\u002FSKILL.md",true,[],[44,51,58,65,72,79],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"publishedAt":18},"01M74XTV2V7GZM8FDBXQZZ74VX","second-wind","Orchestrate long unattended Claude Code runs across multiple repos with the wind CLI. Use when the user wants to run Claude Code overnight, resume sessions after the 5-hour usage limit, run Claude in many repos at once via tmux, or says \"set up second wind\", \"wind up\", \"overnight run\", \"resume after limit\", \"usage limit orchestrator\".","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fsecond-wind\u002Fskills\u002Fsecond-wind\u002FSKILL.md",[],[],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M74XTPGN1HDQSKGCZZX0AZPC","structured-output-adaptive-thinking-token-bloat","A Claude API call using output_config.format (json_schema structured outputs) with thinking:{type:\"adaptive\"} burns most of its output budget on thinking (observed ~21k of ~24k tokens) without improving JSON quality, making the run up to ~5x more expensive than the same call with thinking omitted — use when calling the Messages API with a json_schema output format for extraction, ranking, classification, or summarization tasks, or when a schema-constrained call's usage.output_tokens is far larger than the returned JSON.","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprompt-craft\u002Fskills\u002Fstructured-output-adaptive-thinking-token-bloat\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M74XTKTRHAMC2JFHQ1P1E6GR","review","Apply a code-review lens to a diff, branch, or file — find correctness bugs, security issues, and quality problems, ranked by severity, with a concrete fix for each. Use when the user says \"review this\", \"review my diff\", \"check this PR\", \"look this over before I commit\", or \"is this safe\". Skip when the user wants the code written, not reviewed.","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprompt-craft\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M74XTGGCW7GWDDHPEMJQC7Y1","refresh","Rebuild the prompt-craft command registry and usage profile, and print a summary of installed commands and your personalized recommendations. Use when you install or update plugins and want the advisor to pick them up immediately, or say \"refresh prompt-craft\", \"rebuild the command registry\".","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprompt-craft\u002Fskills\u002Frefresh\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M74XTCNGNR4G19P3Z95KTHQJ","refactor","Apply a refactoring lens — restructure code without changing behavior, guarded by tests that pass before and after. Use when the user says \"refactor\", \"clean this up\", \"extract this\", \"simplify this\", \"reduce duplication\", or \"make this readable\" on existing working code. Skip when the change is meant to alter behavior (that's a feature or a fix).","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprompt-craft\u002Fskills\u002Frefactor\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M74XT9FKXN3N106G7Q3X56XR","plan","Decompose a non-trivial task into an explicit, tracked plan with goals and per-step acceptance criteria before writing code. Use when the user says \"plan this\", \"break this down\", \"what's the plan\", or asks for a multi-step feature\u002Frefactor that touches more than one file. Pairs with plan mode. Skip for single-edit changes that need no decomposition.","https:\u002F\u002Fgithub.com\u002Fabhijitbansal\u002Fclaude-skills\u002Fblob\u002Fmain\u002Fplugins\u002Fprompt-craft\u002Fskills\u002Fplan\u002FSKILL.md",[],[]]