[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EPEM89VCV6H63SKYEF3THM":3,"skill-same:01M7EPEM89VCV6H63SKYEF3THM":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":14,"repositoryHtmlUrl":35,"repositoryHomepageUrl":6,"ownerHtmlUrl":36,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":37,"install":38,"resources":51},"01M7EPEM89VCV6H63SKYEF3THM","layered-assurance",null,"A design rule for assurance when you CANNOT fully enforce or inspect what code does — the observation-first answer to \"however sandboxed.\" A cumulative ladder: L1 count-the-cards (diff or re-hash what you declared must-not-change — a weak-but-honest floor); L2 pin the brutally-simple pieces (awk\u002Fsed) to a known-good release and declare your moves out loud; L3 expose every run-level of the real lifecycle (configure \u002F make \u002F install \u002F setup \u002F self-test \u002F enablement) as signals; L4 substitute your own implementation to optimize or test. Use it whenever you can't sandbox something completely and need a real (if weak) guarantee; when proving nothing changed that shouldn't have (diff two trees, re-hash a manifest); when deciding how much assurance to layer on; or when a tool never \"graduates\" toward more assurance — that non-graduation is itself a smell.","inputloop\u002Fgarden","inputloop","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F339507215?v=4","01M7ENYT15EMVBAV30YXPQDYE2","Inputloop","01M7ENYT1SM9WM5PSMQDC9PE2G",0,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Flayered-assurance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: layered-assurance\ndescription: >\n  A design rule for assurance when you CANNOT fully enforce or inspect what code does — the\n  observation-first answer to \"however sandboxed.\" A cumulative ladder: L1 count-the-cards (diff or\n  re-hash what you declared must-not-change — a weak-but-honest floor); L2 pin the brutally-simple\n  pieces (awk\u002Fsed) to a known-good release and declare your moves out loud; L3 expose every run-level\n  of the real lifecycle (configure \u002F make \u002F install \u002F setup \u002F self-test \u002F enablement) as signals;\n  L4 substitute your own implementation to optimize or test. Use it whenever you can't sandbox\n  something completely and need a real (if weak) guarantee; when proving nothing changed that\n  shouldn't have (diff two trees, re-hash a manifest); when deciding how much assurance to layer on;\n  or when a tool never \"graduates\" toward more assurance — that non-graduation is itself a smell.\nmetadata:\n  c4_deck: gf-02-layered-assurance\n  c4_source_deck: decks\u002Fgf-02-layered-assurance.deck.md\n  c4_source_sha256: f176abced170bb5a5668376e4babb1abf9f6f1861312823cf71e7b2b19ea3234\n  c4_minted_by: c4cs v0.1\n  c4_refined_by: skill-creator 2026-07-27\n  c4_status: refined-from-canon\n---\n\n# Layered assurance — the observation-first ladder\n\nWhen you can't put a real jail around code — it ducks into library spaces you don't see, or the\nsandbox is more theater than control — you don't get enforcement, but you're not helpless. You get a\n*ladder* of increasingly strong, increasingly honest observation. This is the answer to \"however\nsandboxed\": stop pretending the sandbox is the control, and instead account for what actually\nhappened, at whatever layer you can reach.\n\n## The ladder (each rung includes the ones below it)\n\n**L1 — count the cards.** Concede you can't syntactically guard the ins and outs of unknown code.\nInstead, *look*: diff what you declared must-not-change against a second copy, or re-hash a manifest.\nIt's a **weak** guarantee — it only proves the shape didn't change in ways you already knew to watch\n— but it's honest, and it's real. (The \"feel for unexpected changes\" path needs a dedicated\nchange-detector; without one, count-the-cards is what you have.)\n\n**L2 — pin, and declare.** Wire the brutally-simple pieces (awk, sed, tiny scripts) to a *known-good\nrelease*, and patch them to declare their moves out loud where your tooling can hear. Now the floor\nhas provenance and the first signals.\n\n**L3 — expose the run-levels.** Not just the abstract 0..4, but the real lifecycle an operator walks:\nconfigure, make, install, personalization\u002Fsetup, self-test, enablement. Emit each as a signal. The\nwhole lifecycle declares itself, so you can see the shape of what ran without reading its contents.\n\n**L4 — substitute to optimize or test.** Because a hook is to knowledge, not unique function, you may\ndrop in your own implementation to make a rung faster or to cross-check it — provided you re-home any\nverification that rode on what you replaced.\n\n## The smell: non-graduation\n\nWhen an important tool — or someone's use bound to a tool — sits at a layer and shows no sign of\nclimbing toward the others, treat that as a **signal**, not neutral. A thing that never earns more\nassurance, when it could, is telling you something.\n\n## It complements enforcement, doesn't compete\n\nWhere a real jail exists, use it (that's the enforcement-first answer). This ladder is what you stack\n*around* that core — and what you rely on entirely when no real jail is available. Weak-but-honest at\nthe bottom beats strong-but-absent.\n\n*Refined from the C4 canon deck `gf-02-layered-assurance.deck.md` (see `metadata`; `c4_source_sha256`\nnames the exact canon version, re-hash to vouch). Candidate canon (Corwin's theory T2).*\n\n\u003C!-- footer: minted by bin\u002Fft1mt from conventions\u002Fhouse.env and conventions\u002FFOOTERS.org; edit those, not this -->\n*Version 1.0.1: edition revised from 1.0.0 on 2026-10-04; spine: 2026-07-27.*\n\nCopyright 2026 Corwin Brust \u003Ccorwin@bru.st> and Contributors; CC-BY-SA4: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F (scripts GPL-3.0-or-later); Mentat (for Corwin; claude-opus-5-5)\n\u003C!-- \u002Ffooter -->\n","# Layered assurance — the observation-first ladder\n\nWhen you can't put a real jail around code — it ducks into library spaces you don't see, or the\nsandbox is more theater than control — you don't get enforcement, but you're not helpless. You get a\n*ladder* of increasingly strong, increasingly honest observation. This is the answer to \"however\nsandboxed\": stop pretending the sandbox is the control, and instead account for what actually\nhappened, at whatever layer you can reach.\n\n## The ladder (each rung includes the ones below it)\n\n**L1 — count the cards.** Concede you can't syntactically guard the ins and outs of unknown code.\nInstead, *look*: diff what you declared must-not-change against a second copy, or re-hash a manifest.\nIt's a **weak** guarantee — it only proves the shape didn't change in ways you already knew to watch\n— but it's honest, and it's real. (The \"feel for unexpected changes\" path needs a dedicated\nchange-detector; without one, count-the-cards is what you have.)\n\n**L2 — pin, and declare.** Wire the brutally-simple pieces (awk, sed, tiny scripts) to a *known-good\nrelease*, and patch them to declare their moves out loud where your tooling can hear. Now the floor\nhas provenance and the first signals.\n\n**L3 — expose the run-levels.** Not just the abstract 0..4, but the real lifecycle an operator walks:\nconfigure, make, install, personalization\u002Fsetup, self-test, enablement. Emit each as a signal. The\nwhole lifecycle declares itself, so you can see the shape of what ran without reading its contents.\n\n**L4 — substitute to optimize or test.** Because a hook is to knowledge, not unique function, you may\ndrop in your own implementation to make a rung faster or to cross-check it — provided you re-home any\nverification that rode on what you replaced.\n\n## The smell: non-graduation\n\nWhen an important tool — or someone's use bound to a tool — sits at a layer and shows no sign of\nclimbing toward the others, treat that as a **signal**, not neutral. A thing that never earns more\nassurance, when it could, is telling you something.\n\n## It complements enforcement, doesn't compete\n\nWhere a real jail exists, use it (that's the enforcement-first answer). This ladder is what you stack\n*around* that core — and what you rely on entirely when no real jail is available. Weak-but-honest at\nthe bottom beats strong-but-absent.\n\n*Refined from the C4 canon deck `gf-02-layered-assurance.deck.md` (see `metadata`; `c4_source_sha256`\nnames the exact canon version, re-hash to vouch). Candidate canon (Corwin's theory T2).*\n\n\u003C!-- footer: minted by bin\u002Fft1mt from conventions\u002Fhouse.env and conventions\u002FFOOTERS.org; edit those, not this -->\n*Version 1.0.1: edition revised from 1.0.0 on 2026-10-04; spine: 2026-07-27.*\n\nCopyright 2026 Corwin Brust \u003Ccorwin@bru.st> and Contributors; CC-BY-SA4: https:\u002F\u002Fcreativecommons.org\u002Flicenses\u002Fby-sa\u002F4.0\u002F (scripts GPL-3.0-or-later); Mentat (for Corwin; claude-opus-5-5)\n\u003C!-- \u002Ffooter -->\n",{"name":5,"metadata":24,"description":31},{"c4_deck":25,"c4_status":26,"c4_minted_by":27,"c4_refined_by":28,"c4_source_deck":29,"c4_source_sha256":30},"gf-02-layered-assurance","refined-from-canon","c4cs v0.1","skill-creator 2026-07-27","decks\u002Fgf-02-layered-assurance.deck.md","f176abced170bb5a5668376e4babb1abf9f6f1861312823cf71e7b2b19ea3234","A design rule for assurance when you CANNOT fully enforce or inspect what code does — the observation-first answer to \"however sandboxed.\" A cumulative ladder: L1 count-the-cards (diff or re-hash what you declared must-not-change — a weak-but-honest floor); L2 pin the brutally-simple pieces (awk\u002Fsed) to a known-good release and declare your moves out loud; L3 expose every run-level of the real lifecycle (configure \u002F make \u002F install \u002F setup \u002F self-test \u002F enablement) as signals; L4 substitute your own implementation to optimize or test. Use it whenever you can't sandbox something completely and need a real (if weak) guarantee; when proving nothing changed that shouldn't have (diff two trees, re-hash a manifest); when deciding how much assurance to layer on; or when a tool never \"graduates\" toward more assurance — that non-graduation is itself a smell.\n","main","0b0a0f665f67605c3bc1d43500eea26ef3079a97","skills\u002Flayered-assurance","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden","https:\u002F\u002Fgithub.com\u002Finputloop","2026-10-14 18:29:39",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add inputloop\u002Fgarden --skill layered-assurance",{"tool":44,"command":45},"bunx","bunx skills add inputloop\u002Fgarden --skill layered-assurance",{"tool":47,"command":48},"pnpm","pnpm dlx skills add inputloop\u002Fgarden --skill layered-assurance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Flayered-assurance\u002FSKILL.md",true,[52,58,64],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},".arc\u002F2026-10\u002FSKILL-2026-10-04_pre-no-advert.md","REFERENCE","参考文档",3788,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Flayered-assurance\u002F.arc\u002F2026-10\u002FSKILL-2026-10-04_pre-no-advert.md",{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},".signature.asc","OTHER","其他",659,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Flayered-assurance\u002F.signature.asc",{"path":65,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":66,"sourceHtmlUrl":67},".skill-manifest",77,"https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Flayered-assurance\u002F.skill-manifest",[69,75,81,88,95,102],{"skillNo":70,"name":71,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7EPTX6X52ZPGVQZHKVJ7FAZ","alpha","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002Fskills\u002Falpha\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7EPTWCTS80QHFQ2ND3A1CW1","gamma","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-d\u002Fbr1in\u002Fours\u002FSOFT-SKILLS\u002Fgamma\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7EPTV3K3SCTRP0DR6BMMKR0","quiet","A fixture skill that declares no preferences, so skill.quiet.* has no reader.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-a\u002Fdeclared\u002Fsoft\u002Fquiet\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7EPTSG0VE67F6PFAC0XJDQ4","demo","A fixture skill for tests\u002Fprefs-declared-spec.rb; it declares two preferences inline.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Flane-a\u002Fdeclared\u002Fsoft\u002Fdemo\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7EPTP0PM5WPTFBHPXBCFM5C","concise","Synthesized by polygram from memory tag 'concise'. explicitly flagged. Review and tighten this description before relying on it for triggering.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fconcise\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7EPTAETQ62DJA8ZFEEBBZF0","writing-forms","Which writing form a dated deliverable takes in the shop, and the five techniques every form shares. Use whenever someone is about to write a dated deliverable — \"which form is this?\", \"write it up\", \"land a note \u002F card \u002F model \u002F lens\", \"what shape does a … take\", \"is there a form for this\", or when a new PREFIX-date-slug filename is about to be minted. Carries the rule that a deliverable picks ONE form and says so in its filename, points at the register c\u002Fwf (columns d\u002Fc\u002Fwf) as the source of truth, names the most-used forms, the five cross-cutting techniques (two piles · cite at the act · a falsifier on every concern · the pair rule · his words), how a new form is born, and the fence on notes other sessions wrote. Not rolls (report kinds and their guards), not reformat-prompt (the REFORMAT pair), not run-card (the RUNCARD), not skill-creator (skills). Owns the FORM, not the content.","https:\u002F\u002Fgithub.com\u002Finputloop\u002Fgarden\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-forms\u002FSKILL.md",[],[]]