[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M754RJRMR2WXJ01JSS35Y4PF":3,"skill-same:01M754RJRMR2WXJ01JSS35Y4PF":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M754RJRMR2WXJ01JSS35Y4PF","codex-reasoning-rigor",null,"Use when work needs deeper thinking, less generic output, repo evidence, tradeoffs, monitoring signals, or stronger quality discipline.","Bang-isme\u002FAgencyCLI","Bang-isme","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F179383529?v=4","01M754NDM8K05SAX2V31R63WEE","01M754NDMV48ECFT4HY6X2CKQ0",2,"MIT","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: codex-reasoning-rigor\ndescription: Use when work needs deeper thinking, less generic output, repo evidence, tradeoffs, monitoring signals, or stronger quality discipline.\nload_priority: on-demand\n---\n\n## TL;DR\nLock task contract (goal\u002Fconstraints\u002Fnon-goals) → explore 2+ options → ground in repo artifacts → attach monitoring signals → validate output specificity. Never settle for generic \"best practices\" without concrete evidence.\n\n# Codex Reasoning Rigor\n\n## Overview\n\nUse this skill to turn vague or generic model behavior into explicit decision-making, repo-grounded evidence gathering, and output contracts that are concrete enough to verify.\nActivate it when the task is important enough that \"sounds right\" is not good enough.\n\n## Activation\n\nActivate on explicit `$codex-reasoning-rigor` or `$rigor`.\n\nActivate when the user says or implies:\n\n- \"don't be generic\"\n- \"think harder\" or \"go deeper\"\n- \"make it specific\"\n- \"I need better workflow \u002F monitoring \u002F output quality\"\n- \"give me tradeoffs, not vague advice\"\n- \"show evidence\"\n- \"use the repo, not generic training data\"\n\nAlso activate for:\n\n- architecture or refactor decisions with hidden risk\n- reviews that need actionable findings instead of summaries\n- operational plans that need monitoring signals and stop\u002Fship criteria\n- repeated tasks where model output has drifted or become bland\n\n## Core Protocol\n\nRun this protocol before answering or implementing:\n\n### 1. Task Contract\n\nLock these fields explicitly:\n\n- `goal`: what outcome must change\n- `constraints`: what cannot change\n- `non_goals`: what should stay out of scope\n- `evidence_required`: what proof would make the answer credible\n- `quality_bar`: what would make the output clearly non-generic\n\nIf the task is complex, generate a brief with `scripts\u002Fbuild_reasoning_brief.py`.\nBy default the brief generator now requires those reasoning fields; use `--allow-placeholders` only when you intentionally want a scaffold.\n\n### 2. Decision Surface\n\nDo not jump straight to one answer.\nFrame at least 2 options whenever the task has hidden tradeoffs.\n\nFor each option, compare:\n\n- why it could work here\n- cost or blast radius\n- failure modes\n- what evidence would confirm or reject it\n\n### 3. Repo Grounding\n\nAnchor the answer in concrete artifacts whenever possible:\n\n- real file paths\n- real commands\n- actual counts, versions, or dates\n- existing scripts, references, or templates\n- diffable outputs instead of abstract advice\n\nUse [references\u002Fevidence-ladder.md](references\u002Fevidence-ladder.md) to keep evidence quality high.\n\n### 4. Monitoring Lens\n\nEvery serious workflow or recommendation should state:\n\n- what to watch\n- what \"healthy\" looks like\n- what drift or failure looks like\n- what to do next if the signal goes red\n\nUse [references\u002Fmonitoring-loops.md](references\u002Fmonitoring-loops.md) when the task affects delivery, release quality, or repeated execution.\n\n### 5. Output Contract\n\nBefore finishing, make the output earn its credibility.\nUse [references\u002Foutput-contracts.md](references\u002Foutput-contracts.md) and check that the result includes:\n\n- the chosen path\n- evidence or commands that support it\n- risks or open questions\n- next steps or exit criteria\n\n## Anti-Generic Rules\n\nNever end at \"best practices\", \"ensure\", \"optimize\", \"improve quality\", or similar filler unless you immediately attach:\n\n- a named artifact\n- a concrete command\n- a specific file or boundary\n- a measurable condition\n- a reason this matters in this repo or workflow\n\nUse [references\u002Fanti-generic-patterns.md](references\u002Fanti-generic-patterns.md) when the answer starts sounding interchangeable with any other project.\n\n## Document Clarity and Token Economy\n\nWhen the user wants clearer writing, better Vietnamese output, or lower token overhead:\n\n- remove repeated framing and prompt restatement\n- prefer explicit labels over connective filler\n- keep each sentence semantically complete, even when the sentence is long\n- use concrete verbs, exact artifacts, and stable section ordering\n- treat mojibake or mixed-encoding output as a quality failure\n- stack `codex-document-writer` when the deliverable is a report, memo, guide, handoff, proposal, or formal document\n\nUse [references\u002Fdocument-clarity.md](references\u002Fdocument-clarity.md) for writing rules, Vietnamese labeling, and rendering-safe output patterns.\n\n## Working Pattern\n\nFor medium or high-stakes work:\n\n1. Build a reasoning brief.\n2. Name the decision surface.\n3. Ground the answer in repo artifacts.\n4. State the monitoring loop.\n5. Run an output-quality pass with `$output-guard` before declaring the work complete.\n6. For plans, reviews, and handoffs, add an editorial pass with `$editorial-review` so the result reads like a human-made engineering deliverable instead of safe model prose.\n\nFor plans, reviews, and handoffs, treat strict output validation as the default quality bar, not an optional extra.\n\n## Resources\n\n- `scripts\u002Fbuild_reasoning_brief.py`: generate a structured execution brief for complex, high-signal work.\n- `references\u002Fanti-generic-patterns.md`: common signs of generic output and concrete repair moves.\n- `references\u002Fdocument-clarity.md`: token economy, Vietnamese document structure, and mojibake-safe writing rules.\n- `references\u002Fevidence-ladder.md`: how to rank evidence from weak intuition to strong verification.\n- `references\u002Fmonitoring-loops.md`: how to attach health signals and follow-up actions to workflows.\n- `references\u002Foutput-contracts.md`: response shapes that push outputs toward specificity and accountability.\n- `assets\u002Freasoning-brief-template.md`: markdown template used by the brief generator.\n- `assets\u002Foutput-review-template.md`: template for reviewing whether a deliverable is specific, accountable, and editorially strong enough.\n- `assets\u002Fmonitoring-checklist-template.md`: template for tracking healthy vs drifting workflow signals.\n","## TL;DR\nLock task contract (goal\u002Fconstraints\u002Fnon-goals) → explore 2+ options → ground in repo artifacts → attach monitoring signals → validate output specificity. Never settle for generic \"best practices\" without concrete evidence.\n\n# Codex Reasoning Rigor\n\n## Overview\n\nUse this skill to turn vague or generic model behavior into explicit decision-making, repo-grounded evidence gathering, and output contracts that are concrete enough to verify.\nActivate it when the task is important enough that \"sounds right\" is not good enough.\n\n## Activation\n\nActivate on explicit `$codex-reasoning-rigor` or `$rigor`.\n\nActivate when the user says or implies:\n\n- \"don't be generic\"\n- \"think harder\" or \"go deeper\"\n- \"make it specific\"\n- \"I need better workflow \u002F monitoring \u002F output quality\"\n- \"give me tradeoffs, not vague advice\"\n- \"show evidence\"\n- \"use the repo, not generic training data\"\n\nAlso activate for:\n\n- architecture or refactor decisions with hidden risk\n- reviews that need actionable findings instead of summaries\n- operational plans that need monitoring signals and stop\u002Fship criteria\n- repeated tasks where model output has drifted or become bland\n\n## Core Protocol\n\nRun this protocol before answering or implementing:\n\n### 1. Task Contract\n\nLock these fields explicitly:\n\n- `goal`: what outcome must change\n- `constraints`: what cannot change\n- `non_goals`: what should stay out of scope\n- `evidence_required`: what proof would make the answer credible\n- `quality_bar`: what would make the output clearly non-generic\n\nIf the task is complex, generate a brief with `scripts\u002Fbuild_reasoning_brief.py`.\nBy default the brief generator now requires those reasoning fields; use `--allow-placeholders` only when you intentionally want a scaffold.\n\n### 2. Decision Surface\n\nDo not jump straight to one answer.\nFrame at least 2 options whenever the task has hidden tradeoffs.\n\nFor each option, compare:\n\n- why it could work here\n- cost or blast radius\n- failure modes\n- what evidence would confirm or reject it\n\n### 3. Repo Grounding\n\nAnchor the answer in concrete artifacts whenever possible:\n\n- real file paths\n- real commands\n- actual counts, versions, or dates\n- existing scripts, references, or templates\n- diffable outputs instead of abstract advice\n\nUse [references\u002Fevidence-ladder.md](references\u002Fevidence-ladder.md) to keep evidence quality high.\n\n### 4. Monitoring Lens\n\nEvery serious workflow or recommendation should state:\n\n- what to watch\n- what \"healthy\" looks like\n- what drift or failure looks like\n- what to do next if the signal goes red\n\nUse [references\u002Fmonitoring-loops.md](references\u002Fmonitoring-loops.md) when the task affects delivery, release quality, or repeated execution.\n\n### 5. Output Contract\n\nBefore finishing, make the output earn its credibility.\nUse [references\u002Foutput-contracts.md](references\u002Foutput-contracts.md) and check that the result includes:\n\n- the chosen path\n- evidence or commands that support it\n- risks or open questions\n- next steps or exit criteria\n\n## Anti-Generic Rules\n\nNever end at \"best practices\", \"ensure\", \"optimize\", \"improve quality\", or similar filler unless you immediately attach:\n\n- a named artifact\n- a concrete command\n- a specific file or boundary\n- a measurable condition\n- a reason this matters in this repo or workflow\n\nUse [references\u002Fanti-generic-patterns.md](references\u002Fanti-generic-patterns.md) when the answer starts sounding interchangeable with any other project.\n\n## Document Clarity and Token Economy\n\nWhen the user wants clearer writing, better Vietnamese output, or lower token overhead:\n\n- remove repeated framing and prompt restatement\n- prefer explicit labels over connective filler\n- keep each sentence semantically complete, even when the sentence is long\n- use concrete verbs, exact artifacts, and stable section ordering\n- treat mojibake or mixed-encoding output as a quality failure\n- stack `codex-document-writer` when the deliverable is a report, memo, guide, handoff, proposal, or formal document\n\nUse [references\u002Fdocument-clarity.md](references\u002Fdocument-clarity.md) for writing rules, Vietnamese labeling, and rendering-safe output patterns.\n\n## Working Pattern\n\nFor medium or high-stakes work:\n\n1. Build a reasoning brief.\n2. Name the decision surface.\n3. Ground the answer in repo artifacts.\n4. State the monitoring loop.\n5. Run an output-quality pass with `$output-guard` before declaring the work complete.\n6. For plans, reviews, and handoffs, add an editorial pass with `$editorial-review` so the result reads like a human-made engineering deliverable instead of safe model prose.\n\nFor plans, reviews, and handoffs, treat strict output validation as the default quality bar, not an optional extra.\n\n## Resources\n\n- `scripts\u002Fbuild_reasoning_brief.py`: generate a structured execution brief for complex, high-signal work.\n- `references\u002Fanti-generic-patterns.md`: common signs of generic output and concrete repair moves.\n- `references\u002Fdocument-clarity.md`: token economy, Vietnamese document structure, and mojibake-safe writing rules.\n- `references\u002Fevidence-ladder.md`: how to rank evidence from weak intuition to strong verification.\n- `references\u002Fmonitoring-loops.md`: how to attach health signals and follow-up actions to workflows.\n- `references\u002Foutput-contracts.md`: response shapes that push outputs toward specificity and accountability.\n- `assets\u002Freasoning-brief-template.md`: markdown template used by the brief generator.\n- `assets\u002Foutput-review-template.md`: template for reviewing whether a deliverable is specific, accountable, and editorially strong enough.\n- `assets\u002Fmonitoring-checklist-template.md`: template for tracking healthy vs drifting workflow signals.\n",{"name":5,"description":7,"load_priority":23},"on-demand","main","19b976c6b4f182f06d2d2e6b030549f2f8a69cc0","packages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor",0,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI","https:\u002F\u002Fgithub.com\u002FBang-isme","Hi my name is jeff","2026-07-15 19:58:17",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Bang-isme\u002FAgencyCLI --skill codex-reasoning-rigor",{"tool":38,"command":39},"bunx","bunx skills add Bang-isme\u002FAgencyCLI --skill codex-reasoning-rigor",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Bang-isme\u002FAgencyCLI --skill codex-reasoning-rigor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002FSKILL.md",true,[46,52,58,62,66,70,74,78,82,86],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",233,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"assets\u002Fmonitoring-checklist-template.md","ASSET","资产文件",201,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Fassets\u002Fmonitoring-checklist-template.md",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"assets\u002Foutput-review-template.md",648,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Fassets\u002Foutput-review-template.md",{"path":63,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":64,"sourceHtmlUrl":65},"assets\u002Freasoning-brief-template.md",459,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Fassets\u002Freasoning-brief-template.md",{"path":67,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Fanti-generic-patterns.md",6897,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Freferences\u002Fanti-generic-patterns.md",{"path":71,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fdocument-clarity.md",2302,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Freferences\u002Fdocument-clarity.md",{"path":75,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fevidence-ladder.md",4835,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Freferences\u002Fevidence-ladder.md",{"path":79,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fmonitoring-loops.md",5062,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Freferences\u002Fmonitoring-loops.md",{"path":83,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Foutput-contracts.md",5651,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Freferences\u002Foutput-contracts.md",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fbuild_reasoning_brief.py","SCRIPT","脚本",5861,"https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Fpackages\u002Fcli\u002Fskills\u002Fcodex-reasoning-rigor\u002Fscripts\u002Fbuild_reasoning_brief.py",[93,100,107,114,121,128],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M754T5CB6WCXB2AV8N0M50AC","codex-test-driven-development","Fixture stub for TDD skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-test-driven-development\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M754T41J59TG0MJYC52TES58","codex-subagent-execution","Fixture stub for subagent execution skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-subagent-execution\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M754T2JDSPA3YF83FK6BMNV6","codex-runtime-hook","Fixture stub for runtime hook skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-runtime-hook\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":18},"01M754T1HG4JRTJVZC2PBFTXDT","codex-plan-writer","Fixture stub for plan writer skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-plan-writer\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":18},"01M754SZJVZKGQR5PSA6YFFY09","codex-execution-quality-gate","Fixture stub for quality gate skill.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-execution-quality-gate\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":18},"01M754SXBJ1DE0JR6TK0XJ4SAK","codex-demo","Minimal fixture skill for Agency CLI skill-md parser tests.","https:\u002F\u002Fgithub.com\u002FBang-isme\u002FAgencyCLI\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmock-skills\u002Fcodex-demo\u002FSKILL.md",[],[]]