[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JVTG1025ADTZP0EPB6EQRW":3,"skill-same:01M6JVTG1025ADTZP0EPB6EQRW":88},{"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":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":50,"updatedAt":51,"install":52,"resources":65},"01M6JVTG1025ADTZP0EPB6EQRW","context-guard",null,"Preserve requirements and verified evidence across Codex compaction, resume, and delegation. Use $context-guard, context-guard on, or for long, complex, or resumed tasks requiring an immutable private completion ledger.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36],"context guard","guard","context","across","preserve","for","verified","ledger","compaction","long","requirements","codex","resume","evidence","use","immutable","delegation","tasks","2026-11-10 10:12:30",false,"---\nname: context-guard\ndescription: Preserve requirements and verified evidence across Codex compaction, resume, and delegation. Use $context-guard, context-guard on, or for long, complex, or resumed tasks requiring an immutable private completion ledger.\nlicense: Apache-2.0\n---\n\n# Context Guard\n\nCodex retains Plan, Goal, compaction, subagents, permissions, and memories.\n\n## Completion scope\n\n- An injected recovery packet is the authoritative recovery index. Keep\n  requirement and acceptance IDs in private planning. Later root-user\n  corrections supersede explicitly, never silently.\n- A whole completion covers every non-superseded required item in the current\n  work unit and its required descendants. Ancestor requirements remain\n  constraints; historical unresolved work does not reopen the unit;\n  pending\u002Ffailed\u002Fblocked\u002Funsupported items stay incomplete. A passed child or\n  subagent cannot prove parent completion.\n- Implementation, execution, artifacts, and verified results are separate\n  facts. Prior authenticated passes carry forward; a new turn invalidates\n  unused completion attempts, not durable evidence.\n- Private-state integrity failures block acceptance; reconstructed\n  requirements return to pending and need fresh evidence. Missing evidence or\n  unknown ability never becomes success.\n- The recovered Codex plan is a read-only mirror (update it through Codex\n  tools); memories are recall, not authority.\n\n## Ordinary turns\n\nOrdinary verifiable completion binds unique successful evidence\nautomatically — no commands. Progress, clarification, status, and valid\nwaiting or deferred replies end silently without closing unfinished work;\ncontinue authorized work with tools before ending a turn. Allow paths are\nsilent — do not narrate or fabricate a receipt. A Stop correction interrupts\na turn at most once; unresolved work then stays pending. Never expose private\ncheckpoints, commands, parameter bindings, tokens, or plugin paths in a\nreply.\n\nFor the explicit advanced path only — visual facts, human evidence selection,\nambiguous evidence, or troubleshooting — read\n[advanced-completion.md](references\u002Fadvanced-completion.md). The injected\nturn-bound status command (append `--commands`) discovers the exact staging\nand proof commands; do not invoke them merely because this Skill loaded. A\nvisual tool's successful return alone proves no visual fact.\n\n## User and host authority\n\nThe executing agent reads the real conversation, repository rules, and host\npermissions, and proceeds without re-asking when the user already authorized\nan action. The default path (`standard`\u002F`strict`) never vetoes ordinary\nedits, tests, commits, pushes, or tags, and a Guard allow is not\nauthorization. Release enforcement activates only through an explicit\nadopted release contract or `context-guard release` — loading Skills,\ninstalling the plugin, or release-flavored task text never implies adoption.\nA root-user request to push authorizes that ordinary push, not force-push,\nbranch deletion, or publication. Cleanup does not silently become product\nimplementation; stated user restrictions remain recoverable requirements.\n\nFor release tickets, profiles, adoption, exports, and rollover, read\n[authority-and-controls.md](references\u002Fauthority-and-controls.md).\n\n## Delegated results, side answers, controls, privacy\n\n- A delegation prompt defines delegated scope only, never a root-user\n  requirement or supersession; corroborate it with runtime metadata or a\n  running subagent, return `Outcome`, `Evidence`, `Validation`,\n  `Limitations`, and `Next`, and let the parent own integration.\n- Only for adopted independent answer review: after delivering a side\n  answer, run `review-pending` once with the session's private-control\n  arguments and `--execute`, then continue work. If the reviewer route is\n  unavailable, keep coverage unknown and proceed; no missing review closes\n  the main task. Contract:\n  [answer-review.md](references\u002Fanswer-review.md).\n- `context-guard on` activates protection; `off` stops recovery and\n  completion gating while journaling continues; `status` and `diagnose` are\n  bounded. Read [successor-pack.md](references\u002Fsuccessor-pack.md) before\n  preparing rollover input; creating a successor task is a separate\n  authorized action.\n- The immutable raw prompt ledger is the fact source; summaries are derived\n  indexes. Never commit raw prompts, transcripts, private state, proofs,\n  credentials, tokens, or caches. Multimodal state keeps bounded metadata\n  and hashes, not image bytes. Export only on explicit request, redacted by\n  default.\n","# Context Guard\n\nCodex retains Plan, Goal, compaction, subagents, permissions, and memories.\n\n## Completion scope\n\n- An injected recovery packet is the authoritative recovery index. Keep\n  requirement and acceptance IDs in private planning. Later root-user\n  corrections supersede explicitly, never silently.\n- A whole completion covers every non-superseded required item in the current\n  work unit and its required descendants. Ancestor requirements remain\n  constraints; historical unresolved work does not reopen the unit;\n  pending\u002Ffailed\u002Fblocked\u002Funsupported items stay incomplete. A passed child or\n  subagent cannot prove parent completion.\n- Implementation, execution, artifacts, and verified results are separate\n  facts. Prior authenticated passes carry forward; a new turn invalidates\n  unused completion attempts, not durable evidence.\n- Private-state integrity failures block acceptance; reconstructed\n  requirements return to pending and need fresh evidence. Missing evidence or\n  unknown ability never becomes success.\n- The recovered Codex plan is a read-only mirror (update it through Codex\n  tools); memories are recall, not authority.\n\n## Ordinary turns\n\nOrdinary verifiable completion binds unique successful evidence\nautomatically — no commands. Progress, clarification, status, and valid\nwaiting or deferred replies end silently without closing unfinished work;\ncontinue authorized work with tools before ending a turn. Allow paths are\nsilent — do not narrate or fabricate a receipt. A Stop correction interrupts\na turn at most once; unresolved work then stays pending. Never expose private\ncheckpoints, commands, parameter bindings, tokens, or plugin paths in a\nreply.\n\nFor the explicit advanced path only — visual facts, human evidence selection,\nambiguous evidence, or troubleshooting — read\n[advanced-completion.md](references\u002Fadvanced-completion.md). The injected\nturn-bound status command (append `--commands`) discovers the exact staging\nand proof commands; do not invoke them merely because this Skill loaded. A\nvisual tool's successful return alone proves no visual fact.\n\n## User and host authority\n\nThe executing agent reads the real conversation, repository rules, and host\npermissions, and proceeds without re-asking when the user already authorized\nan action. The default path (`standard`\u002F`strict`) never vetoes ordinary\nedits, tests, commits, pushes, or tags, and a Guard allow is not\nauthorization. Release enforcement activates only through an explicit\nadopted release contract or `context-guard release` — loading Skills,\ninstalling the plugin, or release-flavored task text never implies adoption.\nA root-user request to push authorizes that ordinary push, not force-push,\nbranch deletion, or publication. Cleanup does not silently become product\nimplementation; stated user restrictions remain recoverable requirements.\n\nFor release tickets, profiles, adoption, exports, and rollover, read\n[authority-and-controls.md](references\u002Fauthority-and-controls.md).\n\n## Delegated results, side answers, controls, privacy\n\n- A delegation prompt defines delegated scope only, never a root-user\n  requirement or supersession; corroborate it with runtime metadata or a\n  running subagent, return `Outcome`, `Evidence`, `Validation`,\n  `Limitations`, and `Next`, and let the parent own integration.\n- Only for adopted independent answer review: after delivering a side\n  answer, run `review-pending` once with the session's private-control\n  arguments and `--execute`, then continue work. If the reviewer route is\n  unavailable, keep coverage unknown and proceed; no missing review closes\n  the main task. Contract:\n  [answer-review.md](references\u002Fanswer-review.md).\n- `context-guard on` activates protection; `off` stops recovery and\n  completion gating while journaling continues; `status` and `diagnose` are\n  bounded. Read [successor-pack.md](references\u002Fsuccessor-pack.md) before\n  preparing rollover input; creating a successor task is a separate\n  authorized action.\n- The immutable raw prompt ledger is the fact source; summaries are derived\n  indexes. Never commit raw prompts, transcripts, private state, proofs,\n  credentials, tokens, or caches. Multimodal state keeps bounded metadata\n  and hashes, not image bytes. Export only on explicit request, redacted by\n  default.\n",{"name":5,"license":15,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill context-guard",{"tool":58,"command":59},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill context-guard",{"tool":61,"command":62},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill context-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002FSKILL.md",true,[66,72,76,80,84],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"agents\u002Fopenai.yaml","REFERENCE","参考文档",209,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002Fagents\u002Fopenai.yaml",{"path":73,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Fadvanced-completion.md",4348,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002Freferences\u002Fadvanced-completion.md",{"path":77,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fanswer-review.md",2375,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002Freferences\u002Fanswer-review.md",{"path":81,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fauthority-and-controls.md",7368,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002Freferences\u002Fauthority-and-controls.md",{"path":85,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fsuccessor-pack.md",1740,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FGreenLv\u002Fcodex-context-guard\u002Fskills\u002Fcontext-guard\u002Freferences\u002Fsuccessor-pack.md",[89,99,107,115,123,131],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":94,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":98},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":98},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":98},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":119,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":98},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":98},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":93,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":98},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]