[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753PGDE1ZPHD3RJPMSCJMNK":3,"skill-same:01M753PGDE1ZPHD3RJPMSCJMNK":66},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M753PGDE1ZPHD3RJPMSCJMNK","condux-doctor",null,"Health check for the condux plugin on the host it is installed on. Runs the SessionStart routing hook on both hosts and checks each wire format, confirms Codex's hooks flag is on and plan-review's Stop hook resolves, checks the OpenCode registration and its bundled agents and skills, verifies the five specialist agents shipped, compares the installed version against the marketplace clone, and flags conflicting skill libraries installed. Offline; read-only unless --fix. Checking whether condux itself works on this machine: is condux working, the routing rule stopped appearing, \u002Fworkflow is not being reached, did the SessionStart hook fire, check my condux install, the agents are missing, does condux clash with another workflow plugin. Run it after installing or updating. Not for routing a dev task (that is workflow); not for diagnosing this repo's own build or dist drift (that is toolkit-debugging-playbook).","jabworks\u002Fagentic-toolkit","jabworks","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F159094119?v=4","01M753P4JBZBTT7WN1PJBPZJZP","JAB Works","01M753P4K5KDGEWGXWT811BZET",2,"MIT","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: condux-doctor\ndescription: \"Health check for the condux plugin on the host it is installed on. Runs the SessionStart routing hook on both hosts and checks each wire format, confirms Codex's hooks flag is on and plan-review's Stop hook resolves, checks the OpenCode registration and its bundled agents and skills, verifies the five specialist agents shipped, compares the installed version against the marketplace clone, and flags conflicting skill libraries installed. Offline; read-only unless --fix. Checking whether condux itself works on this machine: is condux working, the routing rule stopped appearing, \u002Fworkflow is not being reached, did the SessionStart hook fire, check my condux install, the agents are missing, does condux clash with another workflow plugin. Run it after installing or updating. Not for routing a dev task (that is workflow); not for diagnosing this repo's own build or dist drift (that is toolkit-debugging-playbook).\"\nargument-hint: \"[--host claude|codex|opencode] [--fix]\"\n---\n\n# \u002Fcondux-doctor\n\nAnswers one question: **is condux actually working on this host?**\n\n```bash\nnode \u003Cskill-base>\u002Fdoctor.mjs                    # every host, every probe\nnode \u003Cskill-base>\u002Fdoctor.mjs --host codex       # one host\nnode \u003Cskill-base>\u002Fdoctor.mjs --quiet            # only what is not fine\nnode \u003Cskill-base>\u002Fdoctor.mjs --fix              # run the installer, then re-probe\n```\n\nExit 0 when nothing is broken, 1 when something is, 2 when the doctor cannot\nfind condux's own hooks.\n\n`--fix` performs no registration itself — it runs condux's plugin-level\n`install.mjs` and probes again, so idempotency, backups and atomic writes stay\nin one place. If the installer fails, the report says how it failed rather than\nre-probing in silence, and the re-probe still decides the exit code. Without an\ninstaller beside the plugin (an `npx skills add` tree has none), it says so and\nchanges nothing.\n\n## Reading the report\n\nOne row per probe: `host  status  detail`, fix on an indented continuation\nline. `done` works · `broken` needs the fix · `absent` is not there and not a\nfailure · `skipped` deliberately needs nothing · `warn` works but something\nelse on the machine competes with it. Only `broken` affects the exit code.\n\n## What it probes\n\n- **The SessionStart routing hook, by running it.** Claude Code must get a\n  `hookSpecificOutput` envelope carrying non-empty context; Codex must get\n  the raw routing payload. Each host's manifest must use its own root\n  variable — `${CLAUDE_PLUGIN_ROOT}` or `${PLUGIN_ROOT}`, never the other.\n- **Codex's `features.hooks` flag**, before anything else on that host. A\n  plugin manifest can declare hooks; nothing in a plugin can enable them. With\n  the flag off, the manifest parses, every path resolves, and no hook fires —\n  which this doctor scored `done` until it learned to read the flag. It proves\n  the flag is set, not that Codex has restarted since.\n- **plan-review's Codex Stop hook** — resolved, never executed. It blocks a\n  turn for up to four days waiting on a human by design.\n- **OpenCode** — `@jabworks\u002Fcondux` in the plugin array, and when a local\n  copy exists, that it ships its bundled `agents\u002F` and `skills\u002F` and that the\n  routing reminder it injects names the OpenCode verb, `skill(name=\"workflow\")`\n  — a payload still saying `\u002Fcondux:workflow` is the docket #72 under-firing\n  shape, reported broken with an upgrade as the fix.\n- **The five specialist agents** — `coder`, `explorer`, `planner`,\n  `researcher`, `scout`. They live in a plugin-level directory reached by its own sync\n  step, which is exactly the mirror that drifted once before.\n- **Version** — installed against the local marketplace clone, with that\n  clone's own last-fetch date printed beside it. Never fetches.\n- **Conflicting skill libraries** — anything in\n  `conflicts.json` that is already on this machine, matched by name against\n  the host plugin registrations and the loose skill directories. Entries are\n  libraries that register a competing `SessionStart` router. Reported `warn`, never `broken`: condux is\n  fine, and the removal command is printed rather than run.\n\n## Why running the hook matters\n\n`session-start.mjs` fails open on purpose: if its payload is missing it exits\n0 and prints nothing, because a hook that breaks the session is worse than a\nhook that does nothing. Every static check passes in that state. Only\nexecuting it reveals that condux's routing rule is silently absent — which is\nthe difference between `\u002Fworkflow` being the entry point and being a lucky\nguess from the catalog.\n\n## What it cannot prove\n\nThat the host *invoked* the hook. Nothing readable from a child process says\nwhether Claude Code or Codex loaded a registration this session. If every\nprobe is green and the routing rule still never appears, the fault is\nhost-side and this report is the evidence.\n\n## Boundaries\n\nRouting an actual dev task is `workflow`. Problems with this *repo's* build —\ndist drift, a manifest that will not parse, a skill that will not trigger —\nbelong to `toolkit-debugging-playbook`: that one needs the source tree, this\none needs only the install.\n","# \u002Fcondux-doctor\n\nAnswers one question: **is condux actually working on this host?**\n\n```bash\nnode \u003Cskill-base>\u002Fdoctor.mjs                    # every host, every probe\nnode \u003Cskill-base>\u002Fdoctor.mjs --host codex       # one host\nnode \u003Cskill-base>\u002Fdoctor.mjs --quiet            # only what is not fine\nnode \u003Cskill-base>\u002Fdoctor.mjs --fix              # run the installer, then re-probe\n```\n\nExit 0 when nothing is broken, 1 when something is, 2 when the doctor cannot\nfind condux's own hooks.\n\n`--fix` performs no registration itself — it runs condux's plugin-level\n`install.mjs` and probes again, so idempotency, backups and atomic writes stay\nin one place. If the installer fails, the report says how it failed rather than\nre-probing in silence, and the re-probe still decides the exit code. Without an\ninstaller beside the plugin (an `npx skills add` tree has none), it says so and\nchanges nothing.\n\n## Reading the report\n\nOne row per probe: `host  status  detail`, fix on an indented continuation\nline. `done` works · `broken` needs the fix · `absent` is not there and not a\nfailure · `skipped` deliberately needs nothing · `warn` works but something\nelse on the machine competes with it. Only `broken` affects the exit code.\n\n## What it probes\n\n- **The SessionStart routing hook, by running it.** Claude Code must get a\n  `hookSpecificOutput` envelope carrying non-empty context; Codex must get\n  the raw routing payload. Each host's manifest must use its own root\n  variable — `${CLAUDE_PLUGIN_ROOT}` or `${PLUGIN_ROOT}`, never the other.\n- **Codex's `features.hooks` flag**, before anything else on that host. A\n  plugin manifest can declare hooks; nothing in a plugin can enable them. With\n  the flag off, the manifest parses, every path resolves, and no hook fires —\n  which this doctor scored `done` until it learned to read the flag. It proves\n  the flag is set, not that Codex has restarted since.\n- **plan-review's Codex Stop hook** — resolved, never executed. It blocks a\n  turn for up to four days waiting on a human by design.\n- **OpenCode** — `@jabworks\u002Fcondux` in the plugin array, and when a local\n  copy exists, that it ships its bundled `agents\u002F` and `skills\u002F` and that the\n  routing reminder it injects names the OpenCode verb, `skill(name=\"workflow\")`\n  — a payload still saying `\u002Fcondux:workflow` is the docket #72 under-firing\n  shape, reported broken with an upgrade as the fix.\n- **The five specialist agents** — `coder`, `explorer`, `planner`,\n  `researcher`, `scout`. They live in a plugin-level directory reached by its own sync\n  step, which is exactly the mirror that drifted once before.\n- **Version** — installed against the local marketplace clone, with that\n  clone's own last-fetch date printed beside it. Never fetches.\n- **Conflicting skill libraries** — anything in\n  `conflicts.json` that is already on this machine, matched by name against\n  the host plugin registrations and the loose skill directories. Entries are\n  libraries that register a competing `SessionStart` router. Reported `warn`, never `broken`: condux is\n  fine, and the removal command is printed rather than run.\n\n## Why running the hook matters\n\n`session-start.mjs` fails open on purpose: if its payload is missing it exits\n0 and prints nothing, because a hook that breaks the session is worse than a\nhook that does nothing. Every static check passes in that state. Only\nexecuting it reveals that condux's routing rule is silently absent — which is\nthe difference between `\u002Fworkflow` being the entry point and being a lucky\nguess from the catalog.\n\n## What it cannot prove\n\nThat the host *invoked* the hook. Nothing readable from a child process says\nwhether Claude Code or Codex loaded a registration this session. If every\nprobe is green and the routing rule still never appears, the fault is\nhost-side and this report is the evidence.\n\n## Boundaries\n\nRouting an actual dev task is `workflow`. Problems with this *repo's* build —\ndist drift, a manifest that will not parse, a skill that will not trigger —\nbelong to `toolkit-debugging-playbook`: that one needs the source tree, this\none needs only the install.\n",{"name":5,"description":7,"argument-hint":24},"[--host claude|codex|opencode] [--fix]","main","5277649b071c1c0cdf4f15eee861b1608fc1bbcb","packages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor",0,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit","https:\u002F\u002Fgithub.com\u002Fjabworks","2026-11-03 15:03:51",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add jabworks\u002Fagentic-toolkit --skill condux-doctor",{"tool":38,"command":39},"bunx","bunx skills add jabworks\u002Fagentic-toolkit --skill condux-doctor",{"tool":41,"command":42},"pnpm","pnpm dlx skills add jabworks\u002Fagentic-toolkit --skill condux-doctor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor\u002FSKILL.md",true,[46,52,58,62],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"conflicts.json","REFERENCE","参考文档",3598,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor\u002Fconflicts.json",{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"conflicts.mjs","SCRIPT","脚本",7433,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor\u002Fconflicts.mjs",{"path":59,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":60,"sourceHtmlUrl":61},"doctor.mjs",21607,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor\u002Fdoctor.mjs",{"path":63,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":64,"sourceHtmlUrl":65},"evals\u002Ftrigger_eval.json",1702,"https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fpackages\u002Fcondux-opencode\u002Fskills\u002Fcondux-doctor\u002Fevals\u002Ftrigger_eval.json",[67,73,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7540BPNTFZH7V41P5E2S692","orphan","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomposition\u002Fbad\u002Fskills\u002Forphan\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7540AG2KFTQ8DJMNV6806MV","no-blurb","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomposition\u002Fbad\u002Fskills\u002Fno-blurb\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M75404N306PY1JFPQ0GGNTYB","workflow","Routes any dev task into the right execution tier (Small\u002FMedium\u002FLarge) and carries condux's operating rules — proportional effort, lazy skill loading, soft gates, implement-yourself-by-default.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M753ZZ6TTA06GRJAG679BQ2H","usage-trace","Checks and manages durable, local usage capture — ingest, health status, and the opt-in limit snapshot — for Claude Code and Codex. Capture itself runs automatically at session start.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fusage-trace\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M753ZSKJSF8WFS7AXR2N65SE","toolkit-skill-standards","Use when writing or reviewing a SKILL.md for jabworks\u002Fagentic-toolkit — frontmatter budgets, the trigger contract (\"Use when…\" description or when_to_use field), progressive disclosure into references\u002F, and keeping a new description out of existing skills' trigger space. Triggers include \"review this skill description\", \"write the frontmatter\", \"does this collide with an existing skill\", \"where should this content live\". Not for scaffold\u002Fsync mechanics; use toolkit-foundry.","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftoolkit-skill-standards\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M753ZKX3KTVYWX15A9A0WZN0","toolkit-research-frontier","Use when planning improvement work on jabworks\u002Fagentic-toolkit itself — open problems (trigger-collision automation, YAML-strict frontmatter checks, docs-catalog enforcement), existing assets, the next three concrete steps, and the four-front library-health campaign with commands and success criteria. Triggers include \"let's improve our toolkit\", \"let's improve this repo\", \"what should we improve next\", \"toolkit roadmap\", \"open problems\", \"run the health campaign\".","https:\u002F\u002Fgithub.com\u002Fjabworks\u002Fagentic-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftoolkit-research-frontier\u002FSKILL.md",[],[]]