[{"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",1571,"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 Later root-user\n  corrections supersede explicitly, never silently.\n- A whole completion covers every non-superseded required item in the current\n  work unit and its required descendants.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",490,"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 02:12:02",{"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",[89,97,104,111,138,163],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":96},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":96},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":96},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":37},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","when","you","done","reviewer","io","change","cli","merge","past",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":37},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[145,146,147,133,148,149,150,151,152,153,154,155,156,157,123,158,159,160,161,162],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":180,"publishedAt":37},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[169,174,177],{"categoryNo":170,"categoryName":171,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":175,"categoryName":176,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":178,"categoryName":179,"taxonomyType":172,"taxonomyTypeDesc":173},"01JBSEEDCAT000000000000010","后端与接口",[165,181,182,183,184,185,186,159,187,124,188,189,190,191,129,192,193,194,195,196],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]