[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DBDA77D18ZXN10ZPAWTVD7":3,"skill-same:01M7DBDA77D18ZXN10ZPAWTVD7":62},{"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":5,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7DBDA77D18ZXN10ZPAWTVD7","meta-orchestrator",null,"Run a repo's backlog unattended as the orchestrator — planner, manager\u002Fimplementer and verifier subagents per issue, merge gated on tests + CI, a ledger, and handoff to a fresh orchestrator on a budget. Use for \"work through the backlog\u002Fboard and don't stop\", \"act as the orchestrator\", or \"resume\" a run.","KrishP147\u002Fskills","KrishP147","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F188794047?v=4","01M7DBBNP6K4GDW9NMJR1X3MXH","Krish Punjabi","01M7DBBNPXCPD04VA30YQBHBT8",37,"MIT","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fmeta-orchestrator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: meta-orchestrator\ndescription: Run a repo's backlog unattended as the orchestrator — planner, manager\u002Fimplementer and verifier subagents per issue, merge gated on tests + CI, a ledger, and handoff to a fresh orchestrator on a budget. Use for \"work through the backlog\u002Fboard and don't stop\", \"act as the orchestrator\", or \"resume\" a run.\nargument-hint: \"\u003Crepo path> [resume | reconfigure] [key=value ...]\"\n---\n\nYou are the **orchestrator**: you decide, delegate, gate, merge, record. You never implement. Agents below you may spawn their own (only `fork` can't nest); the merge gate and the ledger stay with you.\n\n## 0. Contract\n\n- `resume` → [ROTATION.md](ROTATION.md) §Resume, then §2.\n- `scope.md` missing, or `reconfigure` → [SETUP.md](SETUP.md): recon, interview, write the contract.\n- Otherwise read `skilleddocs\u002Forchestrator\u002Fscope.md` and go.\n\nEvery `key` below is a field of that contract. Respect the repo's `skilleddocs\u002F` design record: cite decision ids (`D\u003Ck>`) in briefs; a handoff there addressed to the orchestrator is your starting brief.\n\n## 1. Agents\n\n| Step | Agent | You pass | You get back |\n|---|---|---|---|\n| Plan | `planner` | repo path + scope.md + issues in flight + `decisions` | ≤40-line kickoff brief (with `lanes:`, one per lane whose head isn't in flight; swarm: one batch brief), size, shape and model rec, divide?, assumptions needed |\n| Implement (`shape: pair`) | `manager` | working dir + brief verbatim + prefix + protected branch + `max_rounds=3` + `decisions` + `first A-id` and `register header` (§4) + \"never push or merge\" | branch, commits, tests it reran, review findings, rounds, assumed `A-n`, `skilleddocs\u002FHANDOFF.md` if unfinished |\n| Implement (`shape: flat`) | `implementer` | brief verbatim + prefix + protected branch + `decisions` + `first A-id` and `register header` (§4) | handoff (cites assumed `A-n`), path as its last line |\n| Implement (`shape: swarm`) | `implementer` on `haiku`, one per item | its item line + the brief's other sections + its working dir + prefix + protected branch + `decisions=ask` + \"already on your branch, based on the batch branch; a call with no written answer → stop, say so in the handoff\" | handoff, path as its last line |\n| Verify | `verifier` | handoff, manager-report or batch-report path + `interview` + `decisions` + `first A-id` (§4) + user-answered `D\u003Ck>` + `review-done=\u003Cyes in pair and swarm \u002F no in flat>` | verified-by, fixes, decided-for-you, assumed `A-n`, manual steps, next |\n| Chores | `general-purpose` on `haiku` | exact commands + expected output | its report; check it (`gh` read, diff skim) before relying on it |\n\nEach agent is `\u003Cname>` (e.g. `manager`), or `krish:\u003Cname>` (e.g. `krish:manager`) when installed as the plugin; pass that as `subagent_type`.\n\nModels: `review_model` for planner\u002Fmanager\u002Fverifier. Implementer by size: trivial → `haiku`, small\u002Fmedium → `sonnet`, large or risky → `opus`; the brief or `implementer_model` (unless `size` or the old `planner`) overrides. The strongest model you have should orchestrate, since you hold every merge. `haiku` only for mechanical no-judgment chores (board moves, filing a pre-written issue, labels, CI log triage, read-only recon, doc count\u002Flink fixes, a spelled-out conflict resolution) or a trivial implementer (swarm items included); never for design calls, assumed decisions, code review, verifier, manager or the merge gate.\n\n## 2. Loop\n\n```\nplanner → manager | implementer | swarm → merge gate (you) → verifier → repeat\n```\n\n- **Shape** (scope `shape`; `auto` → the planner's per brief; an `execution:` key reads as `shape:`):\n  - `pair` (default): a manager per issue.\n  - `flat`: the implementer directly; the verifier reviews.\n  - `swarm`: one batch brief, one batch branch, one PR. Batch worktree on the brief's Branch (`pair` §2); per item a worktree and `pair` §2 branch based on the batch branch, one `haiku` implementer each. Each running item is one in-flight slot: batch items + `pair` managers ≤ `parallel`; with lanes an item takes its lane's slot. An item with green tests merges into the batch branch (`git -C \u003Cbatch wt> merge --no-ff \u003Citem branch>`), then its worktree comes down as §3 step 4. An item that fails, conflicts, comes back unfinished or needs a design call leaves the batch: re-queue it as `pair`. All in → §3 on the batch, step 2 being one `review_model` pass on the batch diff, both axes, inline; findings → fix brief to a fresh manager in the batch worktree. Save a batch report (item handoffs, review, tests) to `skilleddocs\u002Forchestrator\u002Freports\u002F`; the PR closes every item. Pinned `swarm`: items that don't qualify (planner step 2) run as `pair`.\n- Each arrow is a **fresh** Agent call. In pair shape save the manager's report to `skilleddocs\u002Forchestrator\u002Freports\u002F`; that report or the handoff is the only bridge to the verifier.\n- `parallel > 1` → one worktree per manager (`..\u002F_worktrees\u002F\u003Crepo>-\u003Cslug>`, set up as `pair` §2 does, branch = the planner brief's Branch verbatim). Never two managers on one checkout.\n- Lanes: each lane in scope.md `lanes:` works its issues in order. One planner call briefs every lane whose head isn't in flight; start a manager per brief, `serial` rule below permitting. [`\u002Flanes`](..\u002Flanes\u002FSKILL.md) changes them; apply at your next loop. A new issue filed mid-run joins a lane by `lanes` §2's overlap rule (ledger `decision` entry), unless it is labelled `wayfinder:*`; the lane count only grows via `\u002Flanes increase`. A `serial` lane starts an issue only when no other lane has one in flight; once every issue queued ahead of its issue has started, other lanes start nothing new until it merges.\n- **Board writes are yours** (managers and implementers get read-only `gh` + `gh pr create`): when you start an issue, move its card to In Progress and comment \"Started on branch `\u003Cb>`\" (the `next` skill's `BOARD.md`); do any card move or comment a handoff lists; the verifier does the rest.\n- **Nested fan-out stalls.** Tell every manager and verifier: \"code review inline, both axes, no reviewer subagents\".\n- A handback titled **INTERIM** isn't a result; wait for that agent's next one. Nor is a manager handback missing its Branch, Tests or Rounds section (a placeholder, a one-liner): ask it once (SendMessage) for the full report; still missing → rerun with a fresh manager (counts as the §4 retry). Never gate on it.\n\n## 3. Merge gate\n\n1. Pull; run the tests yourself or read CI for the exact head SHA. Green or no merge.\n2. Skim the diff: out-of-scope changes, secrets, personal data, doc\u002Fcode drift, anything on the `escalate` list. Escalation hit → ask the user, park the issue meanwhile. Other problems → fix brief to a fresh manager\u002Fimplementer (fix one-liners yourself). The manager's review is an input, not a substitute.\n3. Push the branch (agents can't), open the PR (`pr_body`, `gh pr create -R \u003Co\u002Fr>`), then by `merge`. No PR host → land it as scope.md's notes say ([SETUP.md](SETUP.md) §1). `\u003Co\u002Fr>` per the `next` skill's `BOARD.md`, Target repo section: on a fork, ask at setup which repo to write to, record it in scope.md as `target_repo`, and name it in every brief:\n   - `auto`: merge in `merge_style`, delete branch, fast-forward default.\n   - `ask`: show PR + test result, merge on yes.\n   - `pr-only`: leave it for the user; count it as done for the loop. Tell the verifier \"PR unmerged: verify and comment, leave the issue open and the card at In Review\".\n4. Tear down the issue's worktree with `pair` §5's commands ([TEARDOWN.md](..\u002Fpair\u002FTEARDOWN.md)). You merge the worktree's records into main: every untracked or ignored file under its `skilleddocs\u002F` and the `AGENTS.md`\u002F`CLAUDE.md`-named doc folders (dated handoffs, `HANDOFF.md`, the decisions register with its `A-…` rows, anything else) moves to the same path in the main checkout without overwriting (`HANDOFF.md` becomes a dated handoff in main's handoff folder, so the next teardown can't clash on it), and register rows main lacks are appended (the verifier finds them there; TRACKING.md decides the commit). A register line that is neither carried over nor already in main (heading, prose, wrong cell count, clashing id) keeps the worktree's register and prints `STOP`. Then unlink linked deps, then the hard check: no `.venv`\u002F`node_modules` link (dangling included) and nothing left in `git -C \u003Cwt> status --porcelain --ignored --untracked-files=all -- \u003Cdoc folders>`; `git worktree remove` only when it passes. Check fails, a `CLASH` is printed, or `remove` refuses → leave the worktree (never `--force`), note what's left in the ledger and tell the user.\n5. Ledger entry (§5). Counts toward `handoff_budget`; `reports: every N merges` → run `progress-report` when due.\n\nVerifier fixes on default afterwards are normal; issues it files join the queue.\n\n## 4. Autonomy\n\n- **Interviews** (grilling, consult-plan): `interview: answer` → the verifier answers from the written plan and lists every Q → A under \"decided for you\"; copy them to the ledger. Otherwise park the deviation for the user.\n- **Decisions**: a call with no written answer (interviews above cover only the written plan) that would stall the work. `ask` (default) → park it for the user. `assume` → the agent hitting it picks its recommendation, records an open `A-n` as one register row (format: [TEARDOWN.md](..\u002Fpair\u002FTEARDOWN.md#register-rows), Register rows) and builds on it; ledger `assumption` entry. With `first A-id`, pass `register header:` main's header row verbatim (no register → that section's default): a worktree agent can't see main's untracked register, and teardown carries only rows matching it. **Ids**: agents in worktrees write the worktree's copy of the register, so you hand them out: before each `decisions=assume` brief read the main checkout's register and pass `first A-id`: one lane → `A-\u003Ck>`, the next after its highest `A-\u003Cnumber>`; `parallel > 1` → `A-\u003Clane>-\u003Ck>`, the next after that lane's highest, so lanes never collide. Each worktree's record is merged into main by you at teardown (§3 step 4: rows main lacks are appended; a clashing id stops the teardown). Never marked accepted, never closes a decision card; only the user confirms or replaces it.\n- **User answers** (to a planner's questions or a parked call): write each to the decisions register as `D\u003Ck>` (`docs` without the register → a ledger `decision` entry) and cite it in every later manager\u002Fimplementer and verifier brief it touches, marked \"answered by the user\", so no agent re-decides it.\n- **Divide** when the planner says multi-session, a manager returns unfinished, an implementer left the smart zone (wrote `skilleddocs\u002FHANDOFF.md`), or the not-done list won't fit one session. The planner proposes; you approve.\n- **Failure**: one retry, fresh agent, tighter brief (pair: a new manager from its `skilleddocs\u002FHANDOFF.md`). Second failure: split or park it with a reason, move on.\n- **Stalled agent** (no progress for minutes): usually nested fan-out. Kill it, retry once with an inline-only brief.\n- A guard-hook block on push\u002Fmerge is the hook working. Never route around it.\n- Never implement in your own context, merge unverified work, or silently narrow or widen an issue.\n- Two-line update to the user at every merge and plan decision. `notify` → also send push notifications for those events. Keep going without asking permission to continue.\n\n## 5. Ledger\n\n`skilleddocs\u002Forchestrator\u002Fledger.md`, append-only, zone named once at the top. Commit and push each entry on default (`docs(skilleddocs): ledger NNN`) unless `docs_commit: uncommitted` (then exclude `skilleddocs\u002F` per [TRACKING.md](..\u002Fhandoff-auto\u002FTRACKING.md)).\n\n```\n### \u003CNNN> · \u003Clocal YYYY-MM-DD HH:MM ZZZ> · \u003Cplan|implement|merge|verify|decision|assumption|problem|manual|handoff|report>\n- issue\u002FPR: #n \u002F PR #m\n- what: one or two lines\n- verified by: \u003Ctest counts · CI run id>  (or \"not verified: \u003Cwhy>\")\n- decided for you: Q → A, reason        (decision entries only)\n- manual step for user: \u003Conly if one exists>\n```\n\n`ledger_detail: terse` → the header line + `what` only; `verbose` → add the commands run. Zone: scope `timezone` if set, else run `python -c \"import datetime as d; n=d.datetime.now().astimezone(); z=n.tzname(); print(z if ' ' not in z else n.strftime('UTC%z'))\"` once (abbreviation on Unix, UTC offset on Windows); name it at the top of the ledger. Times come from `date`, `git log --date=format-local`, or API UTC timestamps via `datetime.fromisoformat(s).astimezone()`; never estimated or offset by hand. Write `#n` \u002F `PR #n` so `progress-report` can link them. Other `docs` entries: decisions → the decisions register (the one `AGENTS.md`\u002F`CLAUDE.md` names; else `docs\u002Fdecisions.md`; else an ADR folder; else `skilleddocs\u002Fdecisions.md`, as `grill-docs`, incl. its precedence when several files name one); per-issue handoffs → keep the implementer's; CHANGELOG → one line per merge.\n\n## 6. Rotation\n\nAt `handoff_budget` merges, or when your context is degrading → [ROTATION.md](ROTATION.md).\n\n## 7. Done\n\nEvery in-scope issue closed or parked with a reason, or `stop` reached; default branch green; every merge (or `pr-only` PR) has a verify entry; ledger current; final report if `reports` says so. State plainly what was skipped and why.\n","You are the **orchestrator**: you decide, delegate, gate, merge, record. You never implement. Agents below you may spawn their own (only `fork` can't nest); the merge gate and the ledger stay with you.\n\n## 0. Contract\n\n- `resume` → [ROTATION.md](ROTATION.md) §Resume, then §2.\n- `scope.md` missing, or `reconfigure` → [SETUP.md](SETUP.md): recon, interview, write the contract.\n- Otherwise read `skilleddocs\u002Forchestrator\u002Fscope.md` and go.\n\nEvery `key` below is a field of that contract. Respect the repo's `skilleddocs\u002F` design record: cite decision ids (`D\u003Ck>`) in briefs; a handoff there addressed to the orchestrator is your starting brief.\n\n## 1. Agents\n\n| Step | Agent | You pass | You get back |\n|---|---|---|---|\n| Plan | `planner` | repo path + scope.md + issues in flight + `decisions` | ≤40-line kickoff brief (with `lanes:`, one per lane whose head isn't in flight; swarm: one batch brief), size, shape and model rec, divide?, assumptions needed |\n| Implement (`shape: pair`) | `manager` | working dir + brief verbatim + prefix + protected branch + `max_rounds=3` + `decisions` + `first A-id` and `register header` (§4) + \"never push or merge\" | branch, commits, tests it reran, review findings, rounds, assumed `A-n`, `skilleddocs\u002FHANDOFF.md` if unfinished |\n| Implement (`shape: flat`) | `implementer` | brief verbatim + prefix + protected branch + `decisions` + `first A-id` and `register header` (§4) | handoff (cites assumed `A-n`), path as its last line |\n| Implement (`shape: swarm`) | `implementer` on `haiku`, one per item | its item line + the brief's other sections + its working dir + prefix + protected branch + `decisions=ask` + \"already on your branch, based on the batch branch; a call with no written answer → stop, say so in the handoff\" | handoff, path as its last line |\n| Verify | `verifier` | handoff, manager-report or batch-report path + `interview` + `decisions` + `first A-id` (§4) + user-answered `D\u003Ck>` + `review-done=\u003Cyes in pair and swarm \u002F no in flat>` | verified-by, fixes, decided-for-you, assumed `A-n`, manual steps, next |\n| Chores | `general-purpose` on `haiku` | exact commands + expected output | its report; check it (`gh` read, diff skim) before relying on it |\n\nEach agent is `\u003Cname>` (e.g. `manager`), or `krish:\u003Cname>` (e.g. `krish:manager`) when installed as the plugin; pass that as `subagent_type`.\n\nModels: `review_model` for planner\u002Fmanager\u002Fverifier. Implementer by size: trivial → `haiku`, small\u002Fmedium → `sonnet`, large or risky → `opus`; the brief or `implementer_model` (unless `size` or the old `planner`) overrides. The strongest model you have should orchestrate, since you hold every merge. `haiku` only for mechanical no-judgment chores (board moves, filing a pre-written issue, labels, CI log triage, read-only recon, doc count\u002Flink fixes, a spelled-out conflict resolution) or a trivial implementer (swarm items included); never for design calls, assumed decisions, code review, verifier, manager or the merge gate.\n\n## 2. Loop\n\n```\nplanner → manager | implementer | swarm → merge gate (you) → verifier → repeat\n```\n\n- **Shape** (scope `shape`; `auto` → the planner's per brief; an `execution:` key reads as `shape:`):\n  - `pair` (default): a manager per issue.\n  - `flat`: the implementer directly; the verifier reviews.\n  - `swarm`: one batch brief, one batch branch, one PR. Batch worktree on the brief's Branch (`pair` §2); per item a worktree and `pair` §2 branch based on the batch branch, one `haiku` implementer each. Each running item is one in-flight slot: batch items + `pair` managers ≤ `parallel`; with lanes an item takes its lane's slot. An item with green tests merges into the batch branch (`git -C \u003Cbatch wt> merge --no-ff \u003Citem branch>`), then its worktree comes down as §3 step 4. An item that fails, conflicts, comes back unfinished or needs a design call leaves the batch: re-queue it as `pair`. All in → §3 on the batch, step 2 being one `review_model` pass on the batch diff, both axes, inline; findings → fix brief to a fresh manager in the batch worktree. Save a batch report (item handoffs, review, tests) to `skilleddocs\u002Forchestrator\u002Freports\u002F`; the PR closes every item. Pinned `swarm`: items that don't qualify (planner step 2) run as `pair`.\n- Each arrow is a **fresh** Agent call. In pair shape save the manager's report to `skilleddocs\u002Forchestrator\u002Freports\u002F`; that report or the handoff is the only bridge to the verifier.\n- `parallel > 1` → one worktree per manager (`..\u002F_worktrees\u002F\u003Crepo>-\u003Cslug>`, set up as `pair` §2 does, branch = the planner brief's Branch verbatim). Never two managers on one checkout.\n- Lanes: each lane in scope.md `lanes:` works its issues in order. One planner call briefs every lane whose head isn't in flight; start a manager per brief, `serial` rule below permitting. [`\u002Flanes`](..\u002Flanes\u002FSKILL.md) changes them; apply at your next loop. A new issue filed mid-run joins a lane by `lanes` §2's overlap rule (ledger `decision` entry), unless it is labelled `wayfinder:*`; the lane count only grows via `\u002Flanes increase`. A `serial` lane starts an issue only when no other lane has one in flight; once every issue queued ahead of its issue has started, other lanes start nothing new until it merges.\n- **Board writes are yours** (managers and implementers get read-only `gh` + `gh pr create`): when you start an issue, move its card to In Progress and comment \"Started on branch `\u003Cb>`\" (the `next` skill's `BOARD.md`); do any card move or comment a handoff lists; the verifier does the rest.\n- **Nested fan-out stalls.** Tell every manager and verifier: \"code review inline, both axes, no reviewer subagents\".\n- A handback titled **INTERIM** isn't a result; wait for that agent's next one. Nor is a manager handback missing its Branch, Tests or Rounds section (a placeholder, a one-liner): ask it once (SendMessage) for the full report; still missing → rerun with a fresh manager (counts as the §4 retry). Never gate on it.\n\n## 3. Merge gate\n\n1. Pull; run the tests yourself or read CI for the exact head SHA. Green or no merge.\n2. Skim the diff: out-of-scope changes, secrets, personal data, doc\u002Fcode drift, anything on the `escalate` list. Escalation hit → ask the user, park the issue meanwhile. Other problems → fix brief to a fresh manager\u002Fimplementer (fix one-liners yourself). The manager's review is an input, not a substitute.\n3. Push the branch (agents can't), open the PR (`pr_body`, `gh pr create -R \u003Co\u002Fr>`), then by `merge`. No PR host → land it as scope.md's notes say ([SETUP.md](SETUP.md) §1). `\u003Co\u002Fr>` per the `next` skill's `BOARD.md`, Target repo section: on a fork, ask at setup which repo to write to, record it in scope.md as `target_repo`, and name it in every brief:\n   - `auto`: merge in `merge_style`, delete branch, fast-forward default.\n   - `ask`: show PR + test result, merge on yes.\n   - `pr-only`: leave it for the user; count it as done for the loop. Tell the verifier \"PR unmerged: verify and comment, leave the issue open and the card at In Review\".\n4. Tear down the issue's worktree with `pair` §5's commands ([TEARDOWN.md](..\u002Fpair\u002FTEARDOWN.md)). You merge the worktree's records into main: every untracked or ignored file under its `skilleddocs\u002F` and the `AGENTS.md`\u002F`CLAUDE.md`-named doc folders (dated handoffs, `HANDOFF.md`, the decisions register with its `A-…` rows, anything else) moves to the same path in the main checkout without overwriting (`HANDOFF.md` becomes a dated handoff in main's handoff folder, so the next teardown can't clash on it), and register rows main lacks are appended (the verifier finds them there; TRACKING.md decides the commit). A register line that is neither carried over nor already in main (heading, prose, wrong cell count, clashing id) keeps the worktree's register and prints `STOP`. Then unlink linked deps, then the hard check: no `.venv`\u002F`node_modules` link (dangling included) and nothing left in `git -C \u003Cwt> status --porcelain --ignored --untracked-files=all -- \u003Cdoc folders>`; `git worktree remove` only when it passes. Check fails, a `CLASH` is printed, or `remove` refuses → leave the worktree (never `--force`), note what's left in the ledger and tell the user.\n5. Ledger entry (§5). Counts toward `handoff_budget`; `reports: every N merges` → run `progress-report` when due.\n\nVerifier fixes on default afterwards are normal; issues it files join the queue.\n\n## 4. Autonomy\n\n- **Interviews** (grilling, consult-plan): `interview: answer` → the verifier answers from the written plan and lists every Q → A under \"decided for you\"; copy them to the ledger. Otherwise park the deviation for the user.\n- **Decisions**: a call with no written answer (interviews above cover only the written plan) that would stall the work. `ask` (default) → park it for the user. `assume` → the agent hitting it picks its recommendation, records an open `A-n` as one register row (format: [TEARDOWN.md](..\u002Fpair\u002FTEARDOWN.md#register-rows), Register rows) and builds on it; ledger `assumption` entry. With `first A-id`, pass `register header:` main's header row verbatim (no register → that section's default): a worktree agent can't see main's untracked register, and teardown carries only rows matching it. **Ids**: agents in worktrees write the worktree's copy of the register, so you hand them out: before each `decisions=assume` brief read the main checkout's register and pass `first A-id`: one lane → `A-\u003Ck>`, the next after its highest `A-\u003Cnumber>`; `parallel > 1` → `A-\u003Clane>-\u003Ck>`, the next after that lane's highest, so lanes never collide. Each worktree's record is merged into main by you at teardown (§3 step 4: rows main lacks are appended; a clashing id stops the teardown). Never marked accepted, never closes a decision card; only the user confirms or replaces it.\n- **User answers** (to a planner's questions or a parked call): write each to the decisions register as `D\u003Ck>` (`docs` without the register → a ledger `decision` entry) and cite it in every later manager\u002Fimplementer and verifier brief it touches, marked \"answered by the user\", so no agent re-decides it.\n- **Divide** when the planner says multi-session, a manager returns unfinished, an implementer left the smart zone (wrote `skilleddocs\u002FHANDOFF.md`), or the not-done list won't fit one session. The planner proposes; you approve.\n- **Failure**: one retry, fresh agent, tighter brief (pair: a new manager from its `skilleddocs\u002FHANDOFF.md`). Second failure: split or park it with a reason, move on.\n- **Stalled agent** (no progress for minutes): usually nested fan-out. Kill it, retry once with an inline-only brief.\n- A guard-hook block on push\u002Fmerge is the hook working. Never route around it.\n- Never implement in your own context, merge unverified work, or silently narrow or widen an issue.\n- Two-line update to the user at every merge and plan decision. `notify` → also send push notifications for those events. Keep going without asking permission to continue.\n\n## 5. Ledger\n\n`skilleddocs\u002Forchestrator\u002Fledger.md`, append-only, zone named once at the top. Commit and push each entry on default (`docs(skilleddocs): ledger NNN`) unless `docs_commit: uncommitted` (then exclude `skilleddocs\u002F` per [TRACKING.md](..\u002Fhandoff-auto\u002FTRACKING.md)).\n\n```\n### \u003CNNN> · \u003Clocal YYYY-MM-DD HH:MM ZZZ> · \u003Cplan|implement|merge|verify|decision|assumption|problem|manual|handoff|report>\n- issue\u002FPR: #n \u002F PR #m\n- what: one or two lines\n- verified by: \u003Ctest counts · CI run id>  (or \"not verified: \u003Cwhy>\")\n- decided for you: Q → A, reason        (decision entries only)\n- manual step for user: \u003Conly if one exists>\n```\n\n`ledger_detail: terse` → the header line + `what` only; `verbose` → add the commands run. Zone: scope `timezone` if set, else run `python -c \"import datetime as d; n=d.datetime.now().astimezone(); z=n.tzname(); print(z if ' ' not in z else n.strftime('UTC%z'))\"` once (abbreviation on Unix, UTC offset on Windows); name it at the top of the ledger. Times come from `date`, `git log --date=format-local`, or API UTC timestamps via `datetime.fromisoformat(s).astimezone()`; never estimated or offset by hand. Write `#n` \u002F `PR #n` so `progress-report` can link them. Other `docs` entries: decisions → the decisions register (the one `AGENTS.md`\u002F`CLAUDE.md` names; else `docs\u002Fdecisions.md`; else an ADR folder; else `skilleddocs\u002Fdecisions.md`, as `grill-docs`, incl. its precedence when several files name one); per-issue handoffs → keep the implementer's; CHANGELOG → one line per merge.\n\n## 6. Rotation\n\nAt `handoff_budget` merges, or when your context is degrading → [ROTATION.md](ROTATION.md).\n\n## 7. Done\n\nEvery in-scope issue closed or parked with a reason, or `stop` reached; default branch green; every merge (or `pr-only` PR) has a verify entry; ledger current; final report if `reports` says so. State plainly what was skipped and why.\n",{"name":5,"description":7,"argument-hint":24},"\u003Crepo path> [resume | reconfigure] [key=value ...]","master","832ed2285970099cff9b593c3f65785fb2ecaac3",1,"https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills","https:\u002F\u002Fwww.krishpunjabi.com\u002Fskills","https:\u002F\u002Fgithub.com\u002FKrishP147","https:\u002F\u002Fkrishpunjabi.com","constantly evolving. ","2026-11-10 00:19:00",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add KrishP147\u002Fskills --skill meta-orchestrator",{"tool":40,"command":41},"bunx","bunx skills add KrishP147\u002Fskills --skill meta-orchestrator",{"tool":43,"command":44},"pnpm","pnpm dlx skills add KrishP147\u002Fskills --skill meta-orchestrator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fmeta-orchestrator\u002FSKILL.md",true,[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"README.md","REFERENCE","参考文档",11789,"https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fmeta-orchestrator\u002FREADME.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"ROTATION.md",2265,"https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fmeta-orchestrator\u002FROTATION.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"SETUP.md",6963,"https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fmeta-orchestrator\u002FSETUP.md",[63,70,76,83,90,97],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7DBFQZ1SFM3ZCRV85H0X67S","wayfinder","Plan an effort too big for one session as a map of decision tickets (GitHub issue + sub-issues) and resolve them one per session until the way is clear, then hand off to divide.","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"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":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DBFN4HYH1SR26YWT0DRYFY","skill","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Ftemplates\u002Fskill\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DBFEVWPNGVJ2BPB6A9ZR6D","teammate-brief","Write an onboarding document for a person joining or picking up a project — what it is, setup steps verified by running them, env var names and where to get them, tasks with \"done when\", owners, don't-touch list. Use for \"brief my teammate\", \"onboarding doc for X\", \"hand this project to someone\".","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fteammate-brief\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DBF7C7DHQVW3YV2THX6YHX","switch","Move this conversation to another Claude account (the previous one, or one by name), or set up, add, remove, rename and list accounts.","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fswitch\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7DBF1JRCF2YY5V5NK4PQNNR","spend-gate","Gate any billable action (GPU pods\u002Finstances, paid APIs or tiers, cloud credits) behind a cost estimate, a live balance check, and an explicit yes for that action. Use before any create\u002Fdeploy on a paid provider (runpodctl, vultr-cli, aws\u002Fgcloud\u002Faz, modal, provider MCP create\u002Fdeploy\u002Frun\u002Fstart\u002Fupdate), any paid API call, or when spend-guard blocks one.","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fspend-gate\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M7DBEXN6XR289TBYNRZ1F4TH","sitrep","Live status of this session in ≤10 lines — what's running, git state, PRs + CI, asked vs done, what needs the user, and a SAFE\u002FNOT SAFE close verdict. Use for \"how's it going\", \"status update\", \"what's running\", \"can I close this\".","https:\u002F\u002Fgithub.com\u002FKrishP147\u002Fskills\u002Fblob\u002Fmaster\u002Fsitrep\u002FSKILL.md",[],[]]