[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MENZS95S7PQ9954HFC8A05":3,"skill-same:01M6MENZS95S7PQ9954HFC8A05":123},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":68,"commitSha":69,"skillDirectory":70,"forksCount":71,"repositoryHtmlUrl":72,"repositoryHomepageUrl":73,"ownerHtmlUrl":74,"ownerBlogUrl":75,"ownerDescription":76,"updatedAt":77,"install":78,"resources":90},"01M6MENZS95S7PQ9954HFC8A05","council",null,"Compare independent opinions from models or contexts without inflating agreement. Use when: wanting several opinions or a debate, or summarizing several reviewers' results.","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\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"bounded","second","agreement","when","collect","answer","ideas","domain","evidence","panel","harness","interview","deliberation","canonical","judgment","write","scripts","synthesize","question","design","eval","debate","2026-11-10 10:12:30",false,"---\nname: council\ndescription: 'Compare independent opinions from models or contexts without inflating agreement. Use when: wanting several opinions or a debate, or summarizing several reviewers'' results.'\npractices: [llm-eval-harness, design-by-contract]\nhexagonal_role: domain\nconsumes: [explicit-question, evidence]\nproduces: [council-report.v1]\ncontext_rel: []\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  graph_root: true\n  tier: judgment\n  dependencies: []\n  capabilities: [collect_independent_judgments, synthesize_disagreement, bounded_deliberation, duel_scored_ideas, answer_interview_panel]\n  effects: [write_advisory_council_report]\n  canonical_status: canonical\n  disposition: keep_strategy\noutput_contract: council-report.v1 JSON (schemas\u002Fcouncil-report.v1.schema.json) validated by this skill's scripts\u002Fvalidate-output.sh\n---\n\n# Council\n\nCouncil collects sealed judgments from independent contexts, then synthesizes\nthem so that agreement from one model or one method counts once, dissent and\nthe caller's own decisions survive, and no verdict comes out. Use it when the\ncaller selects several views, or asks you to summarize views already collected,\nand name the uncertainty that makes the extra contexts worth their cost;\nroutine work needs no council.\n\n| Use instead | When |\n|---|---|\n| [Review](..\u002Freview\u002FSKILL.md) | one opinion or look-over |\n| [Premortem](..\u002Fpremortem\u002FSKILL.md) | how a plan could fail |\n| [Idea Genie](..\u002Fidea-genie\u002FSKILL.md) | options to build, or one consequential choice for Plan |\n| [Validate](..\u002Fvalidate\u002FSKILL.md) | an acceptance verdict |\n\n## Rules that decide the synthesis\n\nThey hold for a council you run and for judgments the caller already collected\nelsewhere (several reviews, subagent reads) and asks you to synthesize.\nJudgments made against different revisions are separate subjects, never\nagreement on one.\n\n- **No verdict.** Council returns no `PASS`, `FAIL`, `NOT_PROVEN`, readiness\n  or approval, even when asked to turn agreement into one. Decline, and say\n  that a fresh Validate read owns that judgment. The report goes to the caller\n  as advisory findings, which cannot stand in for it.\n- **Echo consensus weighs as one.** Agreement among judges that share one\n  model or one evidence method counts as one confirmation, however many judges\n  share it: unanimity from identical inputs and one shared method is not\n  independent confirmation. Each consensus point names the `methodologies`\n  (static reading, executing the subject, tracing history) and, where judges\n  record `model_identity`, the `models` of its supporting judges; a point with\n  only one of either sets `weighs_as_one: true`.\n- **The caller's direction stays the default.** A judgment that contradicts\n  what the caller decided becomes a `caller_challenge` entry with all five\n  fields, never a consensus point or a quiet change to the recommendation.\n- **Nothing is dropped.** Initial views are sealed before any is shared, every\n  finding lands in exactly one synthesis bucket, and dissent survives.\n\n## Run a council\n\n| Use | Ask each participant for | Return to the caller |\n|---|---|---|\n| Brainstorm | Distinct options, assumptions, and failure modes | Promising ideas and the objections worth testing |\n| Design or plan | A proposed approach, tradeoffs, and evidence | A recommendation with unresolved decisions visible |\n| Validate | Findings against the same subject and acceptance | Advisory findings; acceptance stays with a fresh Validate read |\n| Duel | Ranked ideas, then scores for every other member's ideas | Ideas ranked by cross-member agreement, score gaps and dissent |\n| Interview panel | An answer to each Interview question | Agreed and open answers the caller accepts or amends |\n\n1. Freeze the question, constraints or acceptance, authorized evidence, and\n   subject digest. Select participants, model pins, and real dispatch bounds;\n   contexts stay in the author's model family unless the caller pins mixed\n   models through [model-dispatch](..\u002Fvalidate\u002Freferences\u002Fmodel-dispatch.md).\n   The caller may give each participant its own model, effort and perspective\n   (for example architect, reliability, security or simplicity); the same model\n   in separate contexts counts as separate participants on the roster, but their\n   agreement still weighs as one. A requested profile or required leg with no\n   authorized live adapter is listed by name in `diversity_unsatisfied`;\n   available views may still return with that limit, but a missing required\n   leg prevents convergence and no agreement substitutes for it.\n2. Give each participant a fresh independent context and the same bounded\n   packet, never the author's preferred conclusion; a perspective steers what a\n   member examines, never what evidence it gets. Collect proposals or judgments\n   before revealing any peer response. Reused or colliding context IDs make a\n   view non-independent: repair the isolation within bounds or disclose it.\n   Admit facts tied to a cited source and the caller's stated need and stakes;\n   keep your own rankings, option-grading labels and summaries of files a\n   participant can open itself out until synthesis. Word options you drafted\n   with equal care, and say a participant may reject all of them or the\n   question as posed. Show peer work in debate or duel scoring under neutral\n   labels (A, B, C), not member or model names; the report keeps the mapping\n   in each judge's `judgment`.\n3. Require evidence, reasoning, and omissions. For brainstorming, distinguish\n   new hypotheses from supported claims; novelty is not proof.\n4. Synthesize the sealed initial views, or run a caller-selected mode below.\n   Preserve dissent and changes of position. `subject_digest` covers what\n   Validate's [Subject](..\u002Fvalidate\u002FSKILL.md#subject) binds: the\n   `canonical_manifest_digest` of `ao provenance manifest`, or else\n   `shasum -a 256 \u003Cfiles> | LC_ALL=C sort | shasum -a 256` over the subject's\n   repo-relative paths, or the sha256 of a subject supplied only as text.\n   Recompute it the same way before each later round and before synthesis; if\n   it changed, name the change and rerun every participant on the new subject\n   or return the incomplete outcome, never folding views of the old subject in.\n   With nothing to bind (a brainstorm, an open design question, an interview\n   panel), it is the sha256 of `question` as recorded, computed once; a\n   reworded question is a new subject.\n5. Return `council-report.v1` with its limits and, when the use produces one\n   (design or plan does), its optional `recommendation`. Prefer one option\n   only for a reason in the evidence; when options stay close, say either\n   would serve and name the tradeoffs that separate them. Outside a\n   caller-selected voting rule, a count of pros, cons or supporters breaks no\n   tie. Council neither changes the subject nor grants implementation or\n   delivery authority.\n\nIndependent comparison is the default. Multiple models can broaden the\nperspectives offered; agreement alone proves no improvement.\n\n## Optional modes\n\nLoad only the mode the caller selected:\n\n- Bounded debate or a majority rule: [debate](references\u002Fdebate.md). Replies\n  that saw earlier answers are peer-informed, never new independent views, and\n  a majority cannot establish truth or acceptance.\n- Members scoring each other's ideas: [duel](references\u002Fduel.md).\n- A council answering an Interview: [interview panel](references\u002Finterview-panel.md).\n- A disagreement between the legs of one validation read:\n  [judge split](references\u002Fjudge-split.md).\n\n## Caller challenge\n\nWhen judgments recommend a change to something the caller specified (merging\nwhat they separated, cutting what they asked for, reversing a declared\ndirection), record it in `synthesis.caller_challenge`. Independent agreement\nagainst the caller is a strong signal and still not authority: the caller\nholds context no judge was given. Each entry has five fields:\n\n- `caller_stated`: their direction, in their words, not paraphrased.\n- `judges_recommend`: the change, who supports it, and whether their views were\n  independent or peer-informed; never describe debate votes as independent.\n- `reasoning`: the case at its strongest.\n- `context_possibly_missing`: what the judges provably were not given; an\n  entry without it is majority laundering wearing a new label.\n- `cost_if_wrong`: what breaks if the caller's direction was right.\n\nOptional `judge_count` needs at least two supporters; optional\n`disagreement_kind` says whether the objection is a `preference`, `security`\nor `feasibility` defect. The caller's direction stays the default and the\nburden of argument is on the judges; the caller decides, knowing the kind of\ndisagreement. Stop condition: every judgment that contradicts a caller-stated\ndirection appears in `caller_challenge` with all five fields and in no other\nsynthesis bucket. Whether the challenged decision can be undone belongs in\n[Plan](..\u002Fplan\u002FSKILL.md), with actual undo cost and existing authority; the\ncouncil must not assume either.\n\n## Synthesis section\n\nThe report ends with an explicit consensus\u002Fdivergence synthesis: consensus\npoints with their methodology spread, divergence points with each side's\ncited evidence and whether the split is an evidence gap (name the fact or check\nthat would settle it) or a judgment call the caller owns, minority findings\npreserved in their own words, unresolved assumptions, and any\n`caller_challenge` entries. Synthesis is complete when every judge finding\nlands in exactly one of those buckets; a finding silently dropped from\nsynthesis is majority laundering. Run facts (bounds, roster, threshold, tally,\nstop reason, non-returning judges) go in `synthesis.notes`.\n\nTwo judges' defect findings are one point only when a single fix would resolve\nboth, judged by reading each defect and its fix, not the wording or a shared\nlocation; proposals or answers are one point only when they recommend the same\nchange. Findings on the same lines with different failure modes stay\nseparate, opposing recommendations are divergence, and when unsure keep them\napart, since a wrong merge inflates agreement. A merged point keeps each\njudge's own evidence.\n\n## Output\n\n`\u003Cskill-dir>` is the directory that contains this SKILL.md. Claude Code shows\nit as \"Base directory for this skill\"; Codex lists this skill's SKILL.md path;\nin an AgentOps source checkout it is `skills\u002Fcouncil`. Replace `\u003Cskill-dir>`\nwith that absolute path before running a command. The working directory stays\nthe user's repository. If the host did not show where this skill is installed,\nuse the directory of the SKILL.md you read. If you cannot determine it, do not\nguess a path or run a same-named script from the current repository; say the\nbundled script is unavailable and check the report's fields by hand against\nits [schema](schemas\u002Fcouncil-report.v1.schema.json).\n\n- **Destination:** caller-selected protected external non-Git storage;\n  preserve existing legacy evidence. Missing routing is not a workspace\n  fallback: when no destination is supplied, return the report inline in the\n  conversation and write no file.\n- **Filename:** `council-report.json`.\n- **Format:** `council-report.v1` JSON ([schema](schemas\u002Fcouncil-report.v1.schema.json)):\n  the frozen `question` and `subject_digest`, any `recommendation`, every judge's\n  `context_id`, `methodology`, cited `evidence` and `omissions`, and the\n  synthesis buckets above. Record mode, round and candidate digest in each\n  `judgment`. It carries no `verdict` or `readiness` field, and a `judgment`\n  or `recommendation` that is only a verdict word is rejected.\n- **Validation command:**\n  `bash \"\u003Cskill-dir>\u002Fscripts\u002Fvalidate-output.sh\" \u003Ccouncil-report.json>`, or\n  `bash \"\u003Cskill-dir>\u002Fscripts\u002Fvalidate-output.sh\" -` with an inline report on stdin.\n  It needs `jq`; exit 2 means the report was not checked, so check its fields\n  by hand against the schema and say the validator did not run.\n\nA judge that times out, errors, or returns an evidence-free judgment is excluded\nfrom agreement counting and listed as non-returning in `synthesis.notes` with\nits context ID and reason, never as a `judges` entry. If fewer than two\neligible initial judgments remain, report insufficient independent coverage\nrather than synthesize a thin consensus; when no valid report can be formed,\nreturn the incomplete outcome and available receipts without fabricating judge\nrecords.\n","# Council\n\nCouncil collects sealed judgments from independent contexts, then synthesizes\nthem so that agreement from one model or one method counts once, dissent and\nthe caller's own decisions survive, and no verdict comes out. Use it when the\ncaller selects several views, or asks you to summarize views already collected,\nand name the uncertainty that makes the extra contexts worth their cost;\nroutine work needs no council.\n\n| Use instead | When |\n|---|---|\n| [Review](..\u002Freview\u002FSKILL.md) | one opinion or look-over |\n| [Premortem](..\u002Fpremortem\u002FSKILL.md) | how a plan could fail |\n| [Idea Genie](..\u002Fidea-genie\u002FSKILL.md) | options to build, or one consequential choice for Plan |\n| [Validate](..\u002Fvalidate\u002FSKILL.md) | an acceptance verdict |\n\n## Rules that decide the synthesis\n\nThey hold for a council you run and for judgments the caller already collected\nelsewhere (several reviews, subagent reads) and asks you to synthesize.\nJudgments made against different revisions are separate subjects, never\nagreement on one.\n\n- **No verdict.** Council returns no `PASS`, `FAIL`, `NOT_PROVEN`, readiness\n  or approval, even when asked to turn agreement into one. Decline, and say\n  that a fresh Validate read owns that judgment. The report goes to the caller\n  as advisory findings, which cannot stand in for it.\n- **Echo consensus weighs as one.** Agreement among judges that share one\n  model or one evidence method counts as one confirmation, however many judges\n  share it: unanimity from identical inputs and one shared method is not\n  independent confirmation. Each consensus point names the `methodologies`\n  (static reading, executing the subject, tracing history) and, where judges\n  record `model_identity`, the `models` of its supporting judges; a point with\n  only one of either sets `weighs_as_one: true`.\n- **The caller's direction stays the default.** A judgment that contradicts\n  what the caller decided becomes a `caller_challenge` entry with all five\n  fields, never a consensus point or a quiet change to the recommendation.\n- **Nothing is dropped.** Initial views are sealed before any is shared, every\n  finding lands in exactly one synthesis bucket, and dissent survives.\n\n## Run a council\n\n| Use | Ask each participant for | Return to the caller |\n|---|---|---|\n| Brainstorm | Distinct options, assumptions, and failure modes | Promising ideas and the objections worth testing |\n| Design or plan | A proposed approach, tradeoffs, and evidence | A recommendation with unresolved decisions visible |\n| Validate | Findings against the same subject and acceptance | Advisory findings; acceptance stays with a fresh Validate read |\n| Duel | Ranked ideas, then scores for every other member's ideas | Ideas ranked by cross-member agreement, score gaps and dissent |\n| Interview panel | An answer to each Interview question | Agreed and open answers the caller accepts or amends |\n\n1. Freeze the question, constraints or acceptance, authorized evidence, and\n   subject digest. Select participants, model pins, and real dispatch bounds;\n   contexts stay in the author's model family unless the caller pins mixed\n   models through [model-dispatch](..\u002Fvalidate\u002Freferences\u002Fmodel-dispatch.md).\n   The caller may give each participant its own model, effort and perspective\n   (for example architect, reliability, security or simplicity); the same model\n   in separate contexts counts as separate participants on the roster, but their\n   agreement still weighs as one. A requested profile or required leg with no\n   authorized live adapter is listed by name in `diversity_unsatisfied`;\n   available views may still return with that limit, but a missing required\n   leg prevents convergence and no agreement substitutes for it.\n2. Give each participant a fresh independent context and the same bounded\n   packet, never the author's preferred conclusion; a perspective steers what a\n   member examines, never what evidence it gets. Collect proposals or judgments\n   before revealing any peer response. Reused or colliding context IDs make a\n   view non-independent: repair the isolation within bounds or disclose it.\n   Admit facts tied to a cited source and the caller's stated need and stakes;\n   keep your own rankings, option-grading labels and summaries of files a\n   participant can open itself out until synthesis. Word options you drafted\n   with equal care, and say a participant may reject all of them or the\n   question as posed. Show peer work in debate or duel scoring under neutral\n   labels (A, B, C), not member or model names; the report keeps the mapping\n   in each judge's `judgment`.\n3. Require evidence, reasoning, and omissions. For brainstorming, distinguish\n   new hypotheses from supported claims; novelty is not proof.\n4. Synthesize the sealed initial views, or run a caller-selected mode below.\n   Preserve dissent and changes of position. `subject_digest` covers what\n   Validate's [Subject](..\u002Fvalidate\u002FSKILL.md#subject) binds: the\n   `canonical_manifest_digest` of `ao provenance manifest`, or else\n   `shasum -a 256 \u003Cfiles> | LC_ALL=C sort | shasum -a 256` over the subject's\n   repo-relative paths, or the sha256 of a subject supplied only as text.\n   Recompute it the same way before each later round and before synthesis; if\n   it changed, name the change and rerun every participant on the new subject\n   or return the incomplete outcome, never folding views of the old subject in.\n   With nothing to bind (a brainstorm, an open design question, an interview\n   panel), it is the sha256 of `question` as recorded, computed once; a\n   reworded question is a new subject.\n5. Return `council-report.v1` with its limits and, when the use produces one\n   (design or plan does), its optional `recommendation`. Prefer one option\n   only for a reason in the evidence; when options stay close, say either\n   would serve and name the tradeoffs that separate them. Outside a\n   caller-selected voting rule, a count of pros, cons or supporters breaks no\n   tie. Council neither changes the subject nor grants implementation or\n   delivery authority.\n\nIndependent comparison is the default. Multiple models can broaden the\nperspectives offered; agreement alone proves no improvement.\n\n## Optional modes\n\nLoad only the mode the caller selected:\n\n- Bounded debate or a majority rule: [debate](references\u002Fdebate.md). Replies\n  that saw earlier answers are peer-informed, never new independent views, and\n  a majority cannot establish truth or acceptance.\n- Members scoring each other's ideas: [duel](references\u002Fduel.md).\n- A council answering an Interview: [interview panel](references\u002Finterview-panel.md).\n- A disagreement between the legs of one validation read:\n  [judge split](references\u002Fjudge-split.md).\n\n## Caller challenge\n\nWhen judgments recommend a change to something the caller specified (merging\nwhat they separated, cutting what they asked for, reversing a declared\ndirection), record it in `synthesis.caller_challenge`. Independent agreement\nagainst the caller is a strong signal and still not authority: the caller\nholds context no judge was given. Each entry has five fields:\n\n- `caller_stated`: their direction, in their words, not paraphrased.\n- `judges_recommend`: the change, who supports it, and whether their views were\n  independent or peer-informed; never describe debate votes as independent.\n- `reasoning`: the case at its strongest.\n- `context_possibly_missing`: what the judges provably were not given; an\n  entry without it is majority laundering wearing a new label.\n- `cost_if_wrong`: what breaks if the caller's direction was right.\n\nOptional `judge_count` needs at least two supporters; optional\n`disagreement_kind` says whether the objection is a `preference`, `security`\nor `feasibility` defect. The caller's direction stays the default and the\nburden of argument is on the judges; the caller decides, knowing the kind of\ndisagreement. Stop condition: every judgment that contradicts a caller-stated\ndirection appears in `caller_challenge` with all five fields and in no other\nsynthesis bucket. Whether the challenged decision can be undone belongs in\n[Plan](..\u002Fplan\u002FSKILL.md), with actual undo cost and existing authority; the\ncouncil must not assume either.\n\n## Synthesis section\n\nThe report ends with an explicit consensus\u002Fdivergence synthesis: consensus\npoints with their methodology spread, divergence points with each side's\ncited evidence and whether the split is an evidence gap (name the fact or check\nthat would settle it) or a judgment call the caller owns, minority findings\npreserved in their own words, unresolved assumptions, and any\n`caller_challenge` entries. Synthesis is complete when every judge finding\nlands in exactly one of those buckets; a finding silently dropped from\nsynthesis is majority laundering. Run facts (bounds, roster, threshold, tally,\nstop reason, non-returning judges) go in `synthesis.notes`.\n\nTwo judges' defect findings are one point only when a single fix would resolve\nboth, judged by reading each defect and its fix, not the wording or a shared\nlocation; proposals or answers are one point only when they recommend the same\nchange. Findings on the same lines with different failure modes stay\nseparate, opposing recommendations are divergence, and when unsure keep them\napart, since a wrong merge inflates agreement. A merged point keeps each\njudge's own evidence.\n\n## Output\n\n`\u003Cskill-dir>` is the directory that contains this SKILL.md. Claude Code shows\nit as \"Base directory for this skill\"; Codex lists this skill's SKILL.md path;\nin an AgentOps source checkout it is `skills\u002Fcouncil`. Replace `\u003Cskill-dir>`\nwith that absolute path before running a command. The working directory stays\nthe user's repository. If the host did not show where this skill is installed,\nuse the directory of the SKILL.md you read. If you cannot determine it, do not\nguess a path or run a same-named script from the current repository; say the\nbundled script is unavailable and check the report's fields by hand against\nits [schema](schemas\u002Fcouncil-report.v1.schema.json).\n\n- **Destination:** caller-selected protected external non-Git storage;\n  preserve existing legacy evidence. Missing routing is not a workspace\n  fallback: when no destination is supplied, return the report inline in the\n  conversation and write no file.\n- **Filename:** `council-report.json`.\n- **Format:** `council-report.v1` JSON ([schema](schemas\u002Fcouncil-report.v1.schema.json)):\n  the frozen `question` and `subject_digest`, any `recommendation`, every judge's\n  `context_id`, `methodology`, cited `evidence` and `omissions`, and the\n  synthesis buckets above. Record mode, round and candidate digest in each\n  `judgment`. It carries no `verdict` or `readiness` field, and a `judgment`\n  or `recommendation` that is only a verdict word is rejected.\n- **Validation command:**\n  `bash \"\u003Cskill-dir>\u002Fscripts\u002Fvalidate-output.sh\" \u003Ccouncil-report.json>`, or\n  `bash \"\u003Cskill-dir>\u002Fscripts\u002Fvalidate-output.sh\" -` with an inline report on stdin.\n  It needs `jq`; exit 2 means the report was not checked, so check its fields\n  by hand against the schema and say the validator did not run.\n\nA judge that times out, errors, or returns an evidence-free judgment is excluded\nfrom agreement counting and listed as non-returning in `synthesis.notes` with\nits context ID and reason, never as a `judges` entry. If fewer than two\neligible initial judgments remain, report insufficient independent coverage\nrather than synthesize a thin consensus; when no valid report can be formed,\nreturn the incomplete outcome and available receipts without fabricating judge\nrecords.\n",{"name":5,"consumes":46,"metadata":48,"produces":60,"practices":62,"context_rel":65,"description":7,"hexagonal_role":26,"user-invocable":51,"output_contract":66,"skill_api_version":67},[47,27],"explicit-question",{"tier":33,"effects":49,"graph_root":51,"disposition":52,"capabilities":53,"dependencies":59,"canonical_status":32},[50],"write_advisory_council_report",true,"keep_strategy",[54,55,56,57,58],"collect_independent_judgments","synthesize_disagreement","bounded_deliberation","duel_scored_ideas","answer_interview_panel",[],[61],"council-report.v1",[63,64],"llm-eval-harness","design-by-contract",[],"council-report.v1 JSON (schemas\u002Fcouncil-report.v1.schema.json) validated by this skill's scripts\u002Fvalidate-output.sh",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil",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":79,"prompt":89,"zipAvailable":51},[80,83,86],{"tool":81,"command":82},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill council",{"tool":84,"command":85},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill council",{"tool":87,"command":88},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill council","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002FSKILL.md",[91,97,101,105,109,113,119],{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fdebate.md","REFERENCE","参考文档",3942,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Freferences\u002Fdebate.md",{"path":98,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fduel.md",1277,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Freferences\u002Fduel.md",{"path":102,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Finterview-panel.md",1420,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Freferences\u002Finterview-panel.md",{"path":106,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fjudge-split.md",1444,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Freferences\u002Fjudge-split.md",{"path":110,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":111,"sourceHtmlUrl":112},"schemas\u002Fcouncil-report.v1.schema.json",4827,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Fschemas\u002Fcouncil-report.v1.schema.json",{"path":114,"resourceType":115,"resourceTypeDesc":116,"sizeBytes":117,"sourceHtmlUrl":118},"scripts\u002Fvalidate-output.sh","SCRIPT","脚本",4361,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Fscripts\u002Fvalidate-output.sh",{"path":120,"resourceType":115,"resourceTypeDesc":116,"sizeBytes":121,"sourceHtmlUrl":122},"scripts\u002Fvalidate.sh",4750,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcouncil\u002Fscripts\u002Fvalidate.sh",[124,134,142,150,158,166],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":129,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":133},"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":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":138,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":133},"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":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":146,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":133},"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":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":154,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":133},"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":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":162,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":133},"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":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":128,"licenseFileUrl":170,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":133},"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",[],[]]