[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76WW6RWVGXNT6341YXGFNWA":3,"skill-same:01M76WW6RWVGXNT6341YXGFNWA":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M76WW6RWVGXNT6341YXGFNWA","magus-context-audit",null,"egladman\u002Fmagus","egladman","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F8713153?v=4","01M75H42QB5A4X82APZF4H44GM","Eli Gladman","01M75H42R1K59Z7JWAP621J849",3,"GPL-3.0","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-context-audit\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"{{if .Full}}# Auditing the instructions an agent was given{{else}}# Auditing agent instructions{{end}}\n\n{{if .Full}}This is a LENS, like `{{buzz \"history.hotspots\"}}`: it observes and ranks; it does not gate.\nThe output is a findings list a human decides on, never an automatic edit.\n\nIt looks at the text, not code: everything an agent loads as\nauthoritative, from sources magus does not own and cannot read in advance.{{else}}Lens, like `{{buzz \"history.hotspots\"}}`: observes, ranks; does not gate.\nOutput: findings list human decides on, never automatic edit.\nLooks at text, not code: everything agent loads as authoritative, from sources magus does not own and cannot read in advance.\nAgent reads all of it in one window; cannot tell which line newer or which file wins.\nWhen two lines disagree -> agent picks one arbitrarily or stalls.{{end}}{{if .Full}}\n\nAn agent reads all of it in one window, with no way to tell which line is newer,\nwhich file outranks which, or which was written for a version of the tools that\nno longer exists. When two lines disagree, that is not a documentation nit: the\nmodel cannot resolve it from inside, so it picks one arbitrarily, alternates\nacross turns, or spends reasoning budget arbitrating instead of working.{{end}}\n\n## Enumerate before reading\n\n{{if .Full}}You cannot audit what you cannot list. The riskiest source is usually the one\nnobody remembers is loaded.\n\n| source | why it bites |\n| --- | --- |\n| the repo's agent file (`CLAUDE.md`, `AGENTS.md`, ...) | always loaded, whole file, never scoped |\n| installed skills | whole directory; a stale one looks identical to a current one |\n| a local, workspace-owned skill (`magus-local-development`) | loads beside the shipped set, but nothing generates or verifies it |\n| the harness's own memory entries | loaded at session start, and POINT-IN-TIME by nature |\n| a routing index (`MAGUS.md`) | invites being read, only true up to the last time it was regenerated |\n| hook-injected text | fires on every matching tool call, and nothing displays it in one place |\n| a user-level or global instruction file | invisible from inside the repo, and outranks nothing |\n| tool output the agent is told to trust | deny reasons, usage text, doctor hints |{{else}}Cannot audit what you cannot list; riskiest source: one nobody remembers loading.\n- repo agent file (`CLAUDE.md`, `AGENTS.md`, ...): always loaded, whole file, never scoped\n- installed skills: whole directory; stale one looks identical to current\n- local workspace-owned skill (`magus-local-development`): loads beside shipped set; nothing generates or verifies it\n- harness memory entries: loaded at session start; point-in-time by nature\n- routing index (`MAGUS.md`): invites reading; only true up to last regeneration\n- hook-injected text: fires on every matching tool call; nothing displays it in one place\n- user-level or global instruction file: invisible from inside repo; outranks nothing\n- tool output agent trusts: deny reasons, usage text, doctor hints{{end}}{{if .Full}}\n\nThe user-level file is the one to check first precisely because it is not in the\nrepo: nothing about the workspace hints that it exists, and its author may not be\nthe person hitting the conflict.{{end}}\n\n{{if .Full}}## Check claims against the tool, not against the other documents{{else}}## Check claims against tools, not documents{{end}}\n\n{{if .Full}}Two documents agreeing with each other and both being wrong is the common case,\nnot the exception: they were usually written in the same sitting by the same\nperson. Resolve every claim against something that executes.{{else}}Resolve every claim against something that executes.{{end}}\n\n```sh\nmagus shell \"\u003Cthe exact command a document recommends>\"\nmagus describe targets -o name        # does the target a doc names still exist\nmagus describe file \u003Cpath>            # is that file really source \u002F output\n```\n{{if .Full}}\nThen RUN the commands the instructions tell an agent to run. A documented command\nthat errors is worse than an undocumented one: the agent trusts it, tries it,\nfails, and has to invent a recovery nothing sanctioned.\n{{end}}\n{{if .Full}}Work outward from what CHANGED (a diff, a changelog, a recent decision), not by\nreading everything. Conflicting lines cluster around recent edits.{{else}}Then run commands instructions tell agent to run.\nWork outward from what changed (diff, changelog, recent decision), not reading everything; conflicts cluster around recent edits.{{end}}\n\n```sh\ngrep -rn \"\u003Cthe command or rule>\" \u003Cevery source you enumerated>\n```\n\n{{if .Full}}## Rank what you find{{else}}## Rank{{end}}\n{{if .Full}}\nEvery finding carries the command that REPRODUCES it: the exact line a reader\nruns to see the conflict for themselves, not a description of where you saw\nit. A finding nobody can re-run is an opinion about a document, and it gets\nargued with instead of fixed.{{end}}{{if .Full}}\n\nReport findings in this order. Here the order measures \"how badly does this derail a\nsession\", not \"how wrong is the sentence\".\n{{end}}\n{{if .Full}}1. Dead end: A forbids X, B requires X, and no third path exists. The agent must\n   break one of the two or stall. Nothing else on this list is worth\n   reporting before one of these.{{else}}Every finding carries command that reproduces it; finding nobody can re-run is opinion.\nOrder:\n1. Dead end: A forbids X, B requires X, no third path. Agent must break one or stall.{{end}}\n{{if .Full}}2. Stale claim: it names a command that no longer exists, no longer works,\n   or is now denied. It is indistinguishable from a dead end until the agent tries it.{{else}}2. Stale claim: names command that no longer exists, no longer works, or now denied.{{end}}\n{{if .Full}}3. Split verdict: two sources describe one decision differently (one\n   \"advised\", the other \"denied\"), and the agent cannot tell which is current.\n   A workspace-local statement contradicting a shipped skill is always this finding:\n   local text overrides nothing, so the two are in conflict. Check each\n   local statement's `retire-when` while here; the retire-when may already be true.{{else}}3. Split verdict: two sources describe one decision differently (one \"advised\", other \"denied\"); agent cannot tell which current. Local statement contradicting shipped skill: always this. Check each local statement's `retire-when` while here; retire-when may already be true.{{end}}\n{{if .Full}}4. Orphaned successor: a denial or a deprecated command names a tool no statement\n   documents.{{else}}4. Orphaned successor: denial or deprecated command names tool no statement documents.{{end}}\n{{if .Full}}5. Silent copies: one statement restated in several places. It is not yet a\n   conflict; it is where the next one is born, because an edit updates\n   some of them.{{else}}5. Silent copies: one statement restated in several places.{{end}}\n\n{{if .Full}}## Do not report these{{else}}## Do not report{{end}}\n{{if .Full}}\nA lens that cries wolf gets switched off, taking the real findings with it.\n{{end}}\n{{if .Full}}- **Different altitudes.** A skill giving the full ladder and a hook injection\n  giving one line are one statement at two lengths. That is the design.{{else}}- Different altitudes: skill with full ladder, hook injection with one line: one statement, two lengths; by design.{{end}}\n{{if .Full}}- **A record of history.** \"Verified on \u003Cdate> by doing X\" describes what happened,\n  not what to do now. Journal entries are point-in-time by nature.{{else}}- Record of history: \"Verified on \u003Cdate> by doing X\" describes what happened, not what to do now; journal entries point-in-time by nature.{{end}}\n{{if .Full}}- **A stated exception.** \"Never pipe output, EXCEPT \u003Ccase>\" looks like a conflict\n  to grep and is one statement with a carve-out.{{else}}- Stated exception: \"Never pipe output, EXCEPT \u003Ccase>\" looks like conflict to grep; one statement with carve-out.{{end}}\n{{if .Full}}- **A labeled note** that describes old behavior on purpose.{{else}}- Labeled note describing old behavior on purpose.{{end}}\n\n{{if .Full}}## Recommend, then verify the fix landed{{else}}## Recommend, then verify fix landed{{end}}\n\n{{if .Full}}Fix at the SOURCE and let the generator propagate it; editing an installed copy is\ndrift a verify step flags anyway. For magus's own skills that is\n`internal\u002Fagent\u002Fskills\u002F*\u002FSKILL.md`, then reinstall.\n\nReinstall with a binary built from the EDITED source, and confirm the content\ndigest moved:{{else}}Fix at source; generator propagates.\nmagus's own skills: `internal\u002Fagent\u002Fskills\u002F*\u002FSKILL.md`, then reinstall.\nReinstall with binary built from edited source; confirm content digest moved:{{end}}\n\n```sh\nmagus doctor    # the agent skills check must report a CHANGED digest, or the install did nothing\n```\n\n{{if .Full}}A stale binary re-installs the OLD body and reports success, which is the single\nmost common way an applied fix silently does not apply.\n\nPrefer DELETING a conflicting line over reconciling it. Two reconciled\nstatements are still two statements to keep in sync; one statement cannot\ncontradict itself. When a statement must appear twice, make one the source and have\nthe other name it, not restate it.{{else}}Stale binary re-installs old body, reports success.\nPrefer deleting conflicting line over reconciling.\nWhen statement must appear twice -> one is source, other names it, not restates it.{{end}}\n",{},"main","5f0df014d9eaf4aea1a930b0bd13c3338e2642de","internal\u002Fagent\u002Fskills\u002Fmagus-context-audit",0,"https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus","http:\u002F\u002Feli.gladman.cc\u002Fmagus\u002F","https:\u002F\u002Fgithub.com\u002Fegladman","eli.gladman.cc","2026-11-14 12:23:44",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add egladman\u002Fmagus --skill magus-context-audit",{"tool":37,"command":38},"bunx","bunx skills add egladman\u002Fmagus --skill magus-context-audit",{"tool":40,"command":41},"pnpm","pnpm dlx skills add egladman\u002Fmagus --skill magus-context-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-context-audit\u002FSKILL.md",true,[],[46,52,58,64,70,76],{"skillNo":47,"name":48,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M76WWZ75J70NCG0TR23XDDE6","magus-workspace-rules","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-workspace-rules\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M76WWX72SY78KG03AVYFE768","magus-vcs-hygiene","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-vcs-hygiene\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M76WWTJYGRCKKXH948KN6RR3","magus-upstream-source","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-upstream-source\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M76WWRTBBAPNKM0PA2NG5Q3N","magus-upstream-docs","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-upstream-docs\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":18},"01M76WWNTF03H9S5CN22QBX5ZK","magus-test-design","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-test-design\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M76WWJX1FPSWYD1RB8JXNF3C","magus-sdk","https:\u002F\u002Fgithub.com\u002Fegladman\u002Fmagus\u002Fblob\u002Fmain\u002Finternal\u002Fagent\u002Fskills\u002Fmagus-sdk\u002FSKILL.md",[],[]]