[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DDZBAS762RHDG89HWX4MA5":3,"skill-same:01M7DDZBAS762RHDG89HWX4MA5":46},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7DDZBAS762RHDG89HWX4MA5","brigd-plan",null,"Plan a brigd flow — split a task into stages of parallel coding agents and return the flow JSON that `brigd \u003Cname> --flow flow.json` runs. Use when asked to \"plan a brigd flow\", \"make a brigd flow\", or \"\u002Fbrigd-plan \u003Ctask>\".","markvrma\u002Fbrigd","markvrma","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F78155861?v=4","01M7DDZ61KKY9JX0HQEBZPH9Z3","Mark Verma","01M7DDZ62MS420N2Y5S7RZJZFA",0,"MIT","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fbrigd-plan\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: brigd-plan\ndescription: Plan a brigd flow — split a task into stages of parallel coding agents and return the flow JSON that `brigd \u003Cname> --flow flow.json` runs. Use when asked to \"plan a brigd flow\", \"make a brigd flow\", or \"\u002Fbrigd-plan \u003Ctask>\".\n---\n\n# brigd-plan\n\nTurn a task into a **brigd flow**: stages that run one after another, where every\nagent inside a stage runs in parallel as its own interactive agent session. brigd\nstarts stage N+1 only after every agent in stage N has written its result file.\n\nFrom an agent session you may run `brigd \u003Cname> --flow \u003Cfile>` yourself: it opens in a\nnew herdr tab, tmux window or Terminal window and returns at once.\n\n## Output contract\n\nReturn **only** the flow JSON. No prose, no code fence, no comments.\n\n```\n{\n  \"goal\": string,                     \u002F\u002F one line: what the whole flow achieves\n  \"stages\": [                         \u002F\u002F run in order\n    [                                 \u002F\u002F one stage: these agents run in parallel\n      {\n        \"name\": string,               \u002F\u002F ^[a-z][a-z0-9_-]{0,18}$, unique in the flow, not \"log\"\n        \"agent\": \"claude\" | \"codex\" | \"pi\" | \"kimi\",  \u002F\u002F an enabled agent, see ## Agents\n        \"model\": string,              \u002F\u002F a model of that agent, or \"default\"; see ## Agents\n        \"effort\": \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\",\n        \"worktree\": string | null,    \u002F\u002F ^[a-z][a-z0-9_-]{0,18}$ or null (main repo)\n        \"task\": string,               \u002F\u002F self-contained instructions for this agent\n        \"files\": [string],            \u002F\u002F repo paths the agent should check first\n        \"mode\": \"default\" | \"acceptEdits\" | \"auto\",\n        \"loop\": {\"to\": string, \"max\": integer}  \u002F\u002F optional, reviewers only; see ## Loops\n      }\n    ]\n  ]\n}\n```\n\nExample, for \"find why login is slow and fix it\":\n\n```json\n{\n  \"goal\": \"Find and fix the slow login path\",\n  \"stages\": [\n    [\n      {\"name\": \"trace-auth\", \"agent\": \"claude\", \"model\": \"sonnet\", \"effort\": \"medium\", \"worktree\": null,\n       \"task\": \"Read the login request path and list every call that can block, with file:line and why.\",\n       \"files\": [\"src\u002Fauth\u002Flogin.rs\", \"src\u002Fdb\u002Fsession.rs\"], \"mode\": \"default\"},\n      {\"name\": \"check-db\", \"agent\": \"claude\", \"model\": \"haiku\", \"effort\": \"low\", \"worktree\": null,\n       \"task\": \"List the queries the session table gets on login and whether each has an index.\",\n       \"files\": [\"migrations\u002F\"], \"mode\": \"default\"}\n    ],\n    [\n      {\"name\": \"fix-login\", \"agent\": \"claude\", \"model\": \"opus\", \"effort\": \"high\", \"worktree\": \"login-fix\",\n       \"task\": \"Using the earlier stage results, fix the slowest blocking call. Keep the diff small. Run the auth tests.\",\n       \"files\": [\"src\u002Fauth\u002Flogin.rs\"], \"mode\": \"acceptEdits\"}\n    ],\n    [\n      {\"name\": \"review-fix\", \"agent\": \"claude\", \"model\": \"sonnet\", \"effort\": \"medium\", \"worktree\": \"login-fix\",\n       \"task\": \"Review the uncommitted diff in this worktree for correctness bugs. Report findings only.\",\n       \"files\": [], \"mode\": \"default\", \"loop\": {\"to\": \"fix-login\", \"max\": 3}}\n    ]\n  ]\n}\n```\n\n## Splitting rules\n\n- Use the **fewest agents** that cover the task. One agent is a valid flow.\n- Agents in one stage must be **independent**: none needs another's output.\n- Put work that needs earlier output in a later stage. brigd gives every agent the\n  result files of all earlier stages.\n- Each `task` must stand alone: the agent sees only its task, its files and earlier\n  results, not this conversation.\n- An agent may use its own Task\u002FAgent subagents for fan-out inside its task.\n- brigd saves the flow as the thread's `flowmap.json` and rereads it before every stage;\n  agents may edit its later stages if the remaining plan must change.\n\n## Agents\n\nUse only the agents named in the line `Enabled agents: ...` of your prompt; if there is none, read `~\u002F.brigd\u002Fconfig.json` (`agents`, `base`), and if that is missing use claude only. Pick the\ncheapest agent and model that can do the stage; top tier only for planning, hard\ndebugging, high-stakes edits. Models (cost tier: strengths):\n\n- `claude`: `haiku` cheap (listing, grepping, renaming, formatting); `sonnet` mid\n  (standard coding, tests, reviews); `opus` top (planning, hard debugging, high-stakes changes).\n- `codex`: a `-mini` model cheap (mechanical edits); `gpt-5.4` mid (standard coding);\n  `gpt-5.5` top (hard debugging, planning). Names move fast: use `\"default\"` when unsure.\n- `pi`: `\"default\"`. Models depend on the user's provider; treat it as that model's tier.\n- `kimi`: `\"default\"`. Cheap long-context coding, strong tool use. It runs one-shot and cannot ask you questions.\n\n`effort` for kimi is ignored; codex clamps `max` to `high`, pi to `xhigh`.\nStart `effort` at `low` and raise it only when the task needs real reasoning.\n\n## Loops\n- A reviewer may send work back with `\"loop\": {\"to\": \"\u003Cagent>\", \"max\": 3}`. After the\n  reviewer's stage, brigd types \"fix these\" into `to`'s session and \"re-review\" into the\n  reviewer's, up to `max` rounds, until the reviewer's verdict is pass. Both keep their sessions.\n- Prefer a loop over implement → review → fix → re-review chains of fresh agents.\n- `to` must be an agent of the stage right before the reviewer, in the same `worktree`.\n  The reviewer's `mode` is `default`. An agent is in at most one loop.\n- `max` 3 unless told otherwise. brigd adds the verdict and round rules to the prompts;\n  the tasks need not mention them.\n- A final reviewer after the loop is a normal agent in a later stage.\n\n## Worktrees and modes\n\n- Agents with the same `worktree` string share one git worktree, across all stages.\n  A different string means a different worktree.\n- `null` means the main repo checkout. Use it for read-only work.\n- Give a worktree only to agents that **edit code**. A fresh worktree has no build\n  artifacts or untracked files (e.g. `.env`).\n- One independent change set = one worktree.\n- `mode`: brigd launches every agent in its closest no-prompt mode (claude `auto`, codex workspace-write sandbox, pi and kimi auto-approve);\n  `mode` only marks which agents edit files. `default` for read-only work,\n  `acceptEdits` (or `auto`) for agents that edit files.\n- At most **one** `acceptEdits`\u002F`auto` agent per worktree per stage (`null` counts\n  as one worktree). Put a second editor of the same worktree in the next stage.\n\n## Paths\n\n`files` must be real paths in the repo. Read the repo (Read, Grep, Glob) before\nchoosing them. Use `[]` rather than guessing.\n\n## plan-review-go (opt-in)\n\nOnly when the user's task **explicitly** asks for it (it names `plan-review-go` or\n`\u002Fplan-review-go`): return exactly this flow, with `\u003Ctask>` = the user's task. Never\ninfer it; otherwise ignore this section and plan as usual.\n\nplan-review-go needs claude's ponytail plugin and a stage that can hold an approval dialog: use claude for stage 1 when it is enabled, and never kimi (it runs one-shot).\n\n```json\n{\"goal\": \"\u003Ctask, one line>\", \"stages\": [\n  [{\"name\": \"plan-review\", \"agent\": \"\u003Cbase agent>\", \"model\": \"\u003Copus for claude, else that agent's top model>\", \"effort\": \"high\", \"worktree\": null,\n    \"task\": \"Invoke the plan-review-go skill on this task: \u003Ctask>. It needs the grill-me skill and the ponytail plugin's ponytail-review skill; if any is missing, say so and stop. Follow it through to the user approving the plan. Then APPEND stages 2..N to this thread's flowmap.json that implement the approved plan, following the brigd-plan splitting, agent\u002Fmodel\u002Feffort, worktree, mode and paths rules and keeping the schema valid. Leave stage 1 untouched. Do not implement the plan yourself. Your output.md holds the approved plan plus a short summary of the stages you added.\",\n    \"files\": [], \"mode\": \"default\"}]\n]}\n```\n\nThis one-stage flow is intentional: brigd rereads flowmap.json after each stage and runs whatever stages the agent appended.\n","# brigd-plan\n\nTurn a task into a **brigd flow**: stages that run one after another, where every\nagent inside a stage runs in parallel as its own interactive agent session. brigd\nstarts stage N+1 only after every agent in stage N has written its result file.\n\nFrom an agent session you may run `brigd \u003Cname> --flow \u003Cfile>` yourself: it opens in a\nnew herdr tab, tmux window or Terminal window and returns at once.\n\n## Output contract\n\nReturn **only** the flow JSON. No prose, no code fence, no comments.\n\n```\n{\n  \"goal\": string,                     \u002F\u002F one line: what the whole flow achieves\n  \"stages\": [                         \u002F\u002F run in order\n    [                                 \u002F\u002F one stage: these agents run in parallel\n      {\n        \"name\": string,               \u002F\u002F ^[a-z][a-z0-9_-]{0,18}$, unique in the flow, not \"log\"\n        \"agent\": \"claude\" | \"codex\" | \"pi\" | \"kimi\",  \u002F\u002F an enabled agent, see ## Agents\n        \"model\": string,              \u002F\u002F a model of that agent, or \"default\"; see ## Agents\n        \"effort\": \"low\" | \"medium\" | \"high\" | \"xhigh\" | \"max\",\n        \"worktree\": string | null,    \u002F\u002F ^[a-z][a-z0-9_-]{0,18}$ or null (main repo)\n        \"task\": string,               \u002F\u002F self-contained instructions for this agent\n        \"files\": [string],            \u002F\u002F repo paths the agent should check first\n        \"mode\": \"default\" | \"acceptEdits\" | \"auto\",\n        \"loop\": {\"to\": string, \"max\": integer}  \u002F\u002F optional, reviewers only; see ## Loops\n      }\n    ]\n  ]\n}\n```\n\nExample, for \"find why login is slow and fix it\":\n\n```json\n{\n  \"goal\": \"Find and fix the slow login path\",\n  \"stages\": [\n    [\n      {\"name\": \"trace-auth\", \"agent\": \"claude\", \"model\": \"sonnet\", \"effort\": \"medium\", \"worktree\": null,\n       \"task\": \"Read the login request path and list every call that can block, with file:line and why.\",\n       \"files\": [\"src\u002Fauth\u002Flogin.rs\", \"src\u002Fdb\u002Fsession.rs\"], \"mode\": \"default\"},\n      {\"name\": \"check-db\", \"agent\": \"claude\", \"model\": \"haiku\", \"effort\": \"low\", \"worktree\": null,\n       \"task\": \"List the queries the session table gets on login and whether each has an index.\",\n       \"files\": [\"migrations\u002F\"], \"mode\": \"default\"}\n    ],\n    [\n      {\"name\": \"fix-login\", \"agent\": \"claude\", \"model\": \"opus\", \"effort\": \"high\", \"worktree\": \"login-fix\",\n       \"task\": \"Using the earlier stage results, fix the slowest blocking call. Keep the diff small. Run the auth tests.\",\n       \"files\": [\"src\u002Fauth\u002Flogin.rs\"], \"mode\": \"acceptEdits\"}\n    ],\n    [\n      {\"name\": \"review-fix\", \"agent\": \"claude\", \"model\": \"sonnet\", \"effort\": \"medium\", \"worktree\": \"login-fix\",\n       \"task\": \"Review the uncommitted diff in this worktree for correctness bugs. Report findings only.\",\n       \"files\": [], \"mode\": \"default\", \"loop\": {\"to\": \"fix-login\", \"max\": 3}}\n    ]\n  ]\n}\n```\n\n## Splitting rules\n\n- Use the **fewest agents** that cover the task. One agent is a valid flow.\n- Agents in one stage must be **independent**: none needs another's output.\n- Put work that needs earlier output in a later stage. brigd gives every agent the\n  result files of all earlier stages.\n- Each `task` must stand alone: the agent sees only its task, its files and earlier\n  results, not this conversation.\n- An agent may use its own Task\u002FAgent subagents for fan-out inside its task.\n- brigd saves the flow as the thread's `flowmap.json` and rereads it before every stage;\n  agents may edit its later stages if the remaining plan must change.\n\n## Agents\n\nUse only the agents named in the line `Enabled agents: ...` of your prompt; if there is none, read `~\u002F.brigd\u002Fconfig.json` (`agents`, `base`), and if that is missing use claude only. Pick the\ncheapest agent and model that can do the stage; top tier only for planning, hard\ndebugging, high-stakes edits. Models (cost tier: strengths):\n\n- `claude`: `haiku` cheap (listing, grepping, renaming, formatting); `sonnet` mid\n  (standard coding, tests, reviews); `opus` top (planning, hard debugging, high-stakes changes).\n- `codex`: a `-mini` model cheap (mechanical edits); `gpt-5.4` mid (standard coding);\n  `gpt-5.5` top (hard debugging, planning). Names move fast: use `\"default\"` when unsure.\n- `pi`: `\"default\"`. Models depend on the user's provider; treat it as that model's tier.\n- `kimi`: `\"default\"`. Cheap long-context coding, strong tool use. It runs one-shot and cannot ask you questions.\n\n`effort` for kimi is ignored; codex clamps `max` to `high`, pi to `xhigh`.\nStart `effort` at `low` and raise it only when the task needs real reasoning.\n\n## Loops\n- A reviewer may send work back with `\"loop\": {\"to\": \"\u003Cagent>\", \"max\": 3}`. After the\n  reviewer's stage, brigd types \"fix these\" into `to`'s session and \"re-review\" into the\n  reviewer's, up to `max` rounds, until the reviewer's verdict is pass. Both keep their sessions.\n- Prefer a loop over implement → review → fix → re-review chains of fresh agents.\n- `to` must be an agent of the stage right before the reviewer, in the same `worktree`.\n  The reviewer's `mode` is `default`. An agent is in at most one loop.\n- `max` 3 unless told otherwise. brigd adds the verdict and round rules to the prompts;\n  the tasks need not mention them.\n- A final reviewer after the loop is a normal agent in a later stage.\n\n## Worktrees and modes\n\n- Agents with the same `worktree` string share one git worktree, across all stages.\n  A different string means a different worktree.\n- `null` means the main repo checkout. Use it for read-only work.\n- Give a worktree only to agents that **edit code**. A fresh worktree has no build\n  artifacts or untracked files (e.g. `.env`).\n- One independent change set = one worktree.\n- `mode`: brigd launches every agent in its closest no-prompt mode (claude `auto`, codex workspace-write sandbox, pi and kimi auto-approve);\n  `mode` only marks which agents edit files. `default` for read-only work,\n  `acceptEdits` (or `auto`) for agents that edit files.\n- At most **one** `acceptEdits`\u002F`auto` agent per worktree per stage (`null` counts\n  as one worktree). Put a second editor of the same worktree in the next stage.\n\n## Paths\n\n`files` must be real paths in the repo. Read the repo (Read, Grep, Glob) before\nchoosing them. Use `[]` rather than guessing.\n\n## plan-review-go (opt-in)\n\nOnly when the user's task **explicitly** asks for it (it names `plan-review-go` or\n`\u002Fplan-review-go`): return exactly this flow, with `\u003Ctask>` = the user's task. Never\ninfer it; otherwise ignore this section and plan as usual.\n\nplan-review-go needs claude's ponytail plugin and a stage that can hold an approval dialog: use claude for stage 1 when it is enabled, and never kimi (it runs one-shot).\n\n```json\n{\"goal\": \"\u003Ctask, one line>\", \"stages\": [\n  [{\"name\": \"plan-review\", \"agent\": \"\u003Cbase agent>\", \"model\": \"\u003Copus for claude, else that agent's top model>\", \"effort\": \"high\", \"worktree\": null,\n    \"task\": \"Invoke the plan-review-go skill on this task: \u003Ctask>. It needs the grill-me skill and the ponytail plugin's ponytail-review skill; if any is missing, say so and stop. Follow it through to the user approving the plan. Then APPEND stages 2..N to this thread's flowmap.json that implement the approved plan, following the brigd-plan splitting, agent\u002Fmodel\u002Feffort, worktree, mode and paths rules and keeping the schema valid. Leave stage 1 untouched. Do not implement the plan yourself. Your output.md holds the approved plan plus a short summary of the stages you added.\",\n    \"files\": [], \"mode\": \"default\"}]\n]}\n```\n\nThis one-stage flow is intentional: brigd rereads flowmap.json after each stage and runs whatever stages the agent appended.\n",{"name":5,"description":7},"main","5275da29f1bc0c50c3ad417632e24c0e0a825d58","skills\u002Fbrigd-plan","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd","https:\u002F\u002Fgithub.com\u002Fmarkvrma","markvrma.github.io","CS @ IIITM Gwalior\r\n","2026-11-12 19:42:34",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add markvrma\u002Fbrigd --skill brigd-plan",{"tool":38,"command":39},"bunx","bunx skills add markvrma\u002Fbrigd --skill brigd-plan",{"tool":41,"command":42},"pnpm","pnpm dlx skills add markvrma\u002Fbrigd --skill brigd-plan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fbrigd-plan\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7DE00M5VDW15Z2GXXPY63RQ","plan-review-go","For any non-trivial task, first draft a plan, have ponytail review it, revise per feedback, build a todo list, then ask the user before starting work. Use when the user says \"plan-review-go\", \"\u002Fplan-review-go\", or asks to plan-then-execute a task with review.","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fplan-review-go\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7DDZXW2TBB92TP9TWYDDDTN","grilling","Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fgrilling\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7DDZVBN5HKA112ZBTFGMZ3Z","grill-me","A relentless interview to sharpen a plan or design.","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fgrill-me\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7DDZNCZ09ZCZKWFS46R1EH3","find-skills","Helps users discover and install agent skills when they ask questions like \"how do I do X\", \"find a skill for X\", \"is there a skill that can...\", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Ffind-skills\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7DDZG7D6Y6T9641PN6N3FTQ","brigd-resume","Continue a finished or stopped brigd thread with new stages. Appends stages to the thread's flowmap.json, reopens the thread, and runs `brigd resume \u003Cname> --bg` so an open brigd TUI or a new terminal picks them up. Use when asked to \"resume a brigd thread\", \"add a stage to a brigd flow\", \"continue the flow\", or \"\u002Fbrigd-resume \u003Cthread> \u003Cwhat to add>\".","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fbrigd-resume\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7DDZ7PRTSZC176X802EQ854","brigd-master","Run the brigd master session — turn each thing the user asks for into a background brigd thread in the right repo, asking only \"Use plan-review-go? (y\u002FN)\". Use when started by `brigd master` or the brigd TUI's master row, or on \"\u002Fbrigd-master\".","https:\u002F\u002Fgithub.com\u002Fmarkvrma\u002Fbrigd\u002Fblob\u002Fmain\u002Fskills\u002Fbrigd-master\u002FSKILL.md",[],[]]