[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RWWGY9FD96P01X5W908T5":3,"skill-same:01M79RWWGY9FD96P01X5W908T5":52},{"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},"01M79RWWGY9FD96P01X5W908T5","tk-studio-launch",null,"Launch, inspect, or stop the execution substrate (bmad-loop) for one project epic through the studio — distill the epic's SPEC, bootstrap the first story's task manifest at the planner tier, then start the engine detached with a pre-minted run id. Use when the user says \"launch epic N\", \"tk launch\", \"start the run for this epic\", \"run status\", \"stop the run\", or a `run-epic` job's invoke-skill directive names this skill.","thkennedy\u002Ftk-studio","thkennedy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F4164502?v=4","01M79QZ8DMP5FF2HC6GS3S6FDF","Tim Kennedy","01M79QZ8EM9JBWJ15R5JNC4PW3",0,"MIT","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-launch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tk-studio-launch\ndescription: Launch, inspect, or stop the execution substrate (bmad-loop) for one project epic through the studio — distill the epic's SPEC, bootstrap the first story's task manifest at the planner tier, then start the engine detached with a pre-minted run id. Use when the user says \"launch epic N\", \"tk launch\", \"start the run for this epic\", \"run status\", \"stop the run\", or a `run-epic` job's invoke-skill directive names this skill.\n---\n\n# tk-studio-launch\n\nThe studio's only way to start a run (studio pipeline decision 5: driver →\norchestrator → substrate). A conformant driver — the studio supervisor, Hermes\nsubmitting to it, or direct invocation (driver contract §1) — runs a `run-epic`\njob; the job wrapper invokes this surface; this surface does the planner-tier preparation and then\nhands the epic to bmad-loop through `lib\u002Flaunch.py`, the one deterministic\ncore that talks to the substrate (CLI only, never imported — AD-2). Ending\nthis session never ends the run: the engine is detached and owns the\ncheckout until it finishes, pauses, or is stopped.\n\n## Payload\n\n- `verb` — `start` (default) | `status` | `stop` | `sweep` (Story 35.7, the `run-sweep` job type)\n- `directory` — the project root (the nested root for a supervisor epic, never an engine worktree); `lib\u002Flaunch.py` walks `--directory` up to the nearest folder holding `.tk-studio\u002Fconfig.yaml` (driver contract 0.1.22), so a nested project launches against its own root and store\n- `epic` — epic number (`start`; required unless `spec_folder` is given)\n- `spec_folder?` — project-relative epic spec folder; default `_bmad-output\u002Fspecs\u002Fspec-epic-\u003CN>`\n- `story?` — the first story to bootstrap as `\u003Cepic>-\u003Cstory>` (default: the epic's first story)\n- `bootstrap?` — `true` (default) prepares SPEC.md, the epic's manifest and a plan for every story in it (list order) when absent; `false` refuses instead\n- `allow_budget_mismatch?` — `start`: `true` acknowledges a `budget_mismatch` and launches anyway (passed to the core as `--allow-budget-mismatch`); default `false` refuses it\n- `max_bundles?` — `sweep`: an integer ≥ 1 bounding the sweep's bundles (passed as `--max-bundles`; default: the policy's `[sweep] max_bundles`)\n- `run_id?` — `status`\u002F`stop`: the run to address (default: the live run)\n- `graceful?` — `stop` after the current unit instead of immediately\n\n## Behavior (both modes)\n\n### `start`\n\n0. **Resolve the inputs before anything runs** (headless: a gap here ends `blocked`, never a guess):\n   - `\u003Croot>` = the `project_root` printed by `uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fconfig.py\" root --directory \u003Cdirectory>` (the payload's `directory` walked up to the nearest folder holding `.tk-studio\u002Fconfig.yaml`, driver contract 0.1.22). Every later `\u003Croot>` — in every step here and in `status` \u002F `stop`, which resolve it the same way first — is that resolved root, never the raw `directory`.\n   - `\u003Cspec_folder>` = the payload's `spec_folder`, else `_bmad-output\u002Fspecs\u002Fspec-epic-\u003Cepic>` (the core's `--epic` flag applies the same default); with neither `epic` nor `spec_folder`, end `blocked`: `spec folder unresolvable: neither epic nor spec_folder given`.\n   - `\u003Cstory>` = the payload's `story`, else the first entry under `## Stories` in `\u003Croot>\u002F_bmad-output\u002Fimplementation-artifacts\u002Fepic-\u003Cepic>-context.md` (`Story N.M: …` → `N-M`), else the first `### Story N.M` heading of the epic's section in `\u003Croot>\u002F_bmad-output\u002Fplanning-artifacts\u002Fepics.md`; with none of these, end `blocked`: `first story unresolvable for epic \u003Cepic>`.\n\n1. **Route the epic's first story** — the model and effort every leg of the run uses (the session, its implementer \u002F reviewer \u002F consult subagents, the seam check, the review and triage stages, the supervisor pass), resolved runtime > the project's `.bmad-loop\u002Frouting.toml` > the shipped measured defaults in this skill's `customize.toml` `[pipeline]` (AD-14; `kb\u002Fexecution-pipeline-model-routing.md` carries the numbers). Run:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fpipeline.py\" apply --directory \u003Croot> --story \u003Cepic>-\u003Cstory>\n   ```\n\n   It writes exactly the managed block in `.bmad-loop\u002Fpolicy.toml`, the subagent-model line in the tracked Claude profile when the project has one, and `.bmad-loop\u002Frouting.current.json`; nothing else. Read `writes` and `unignored[]`. A non-empty `unignored[]` names a file this write would leave dirty in the tree — the engine's preflight refuses a dirty tree — so end `blocked` naming it (`routing write not gitignored: \u003Cpath>`); never add the ignore line yourself in a headless run, and never launch around it. A refusal (`ok: false` — the policy is missing, the project's routing table is invalid) ends `blocked` with its `error` verbatim: the route is never invented. Report the route's session \u002F implementer \u002F reviewers \u002F consult models in the launch report.\n\n2. **Readiness first, and never guess around a gap.** Run:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" check --directory \u003Croot> --spec \u003Cspec_folder>\n   ```\n\n   Read `gaps[]`. Gaps you may close in this session (only when `bootstrap` is true): a missing `SPEC.md` (step 3) and an empty or missing task manifest (step 4). Story 35.2: the gap `open questions` refuses the story the launch would start (the first manifest entry with no `stories\u002F\u003Cid>-*.md` at `status: done`) — one of its CAPs has a `- CAP-N:` line under SPEC.md `## Open Questions` and no design note names that CAP or the story; its detail is `\u003Cstory id>: CAP-N has no design note — \u003Cquestion>` (`; ` between CAPs). This session never answers it (the planner's task planning notes it or escalates): end `blocked` with the gap verbatim, every CAP named, before any dev session. A later story's un-noted CAP is never a gap. Every other gap — a live engine already on the checkout, `bmad-loop` not installed, a failing `bmad-loop validate` (a dirty tree, a broken policy) — ends the run `blocked` with the gap verbatim in `reason`. Never stop another run to make room; never clean a tree.\n\n   Read `budget` too: the core compares the engine's `.bmad-loop\u002Fpolicy.toml` limits with `.tk-studio\u002Fbudget-bands.yaml` and names each limit the bands exceed in `budget.budget_mismatch[]` (`{limit, policy, band, band_field, band_value}`). A mismatch is not a gap — `check` ends `partial` naming it — but step 6's `start` refuses it unless the payload carries `allow_budget_mismatch: true`. Report it with both numbers; never edit its `[limits]` to clear it (the limit is the operator's machine-local setting; step 1's managed routing block and `check`'s `[verify] commands` reconciliation are the only launch writes to that file, except a run worktree's per-band cap). Story 38.7: `max_followup_reviews` is compared per band (`followup_reviews_max`), each entry naming its `policy_key` (`limits.by_band.\u003Cband>.max_followup_reviews`, else `limits.max_followup_reviews`); the operator's `[limits.by_band]` closes a band's mismatch. In a linked run worktree whose run takes one story, `start` itself writes the next story's by-band figure into `[limits] max_followup_reviews` of that worktree's policy copy and answers `followup_cap {band, figure, applied, reason}`; a main checkout's policy is never written — report `followup_cap` as it reads.\n\n   Read `verify_commands` too (Story 33.5): `check` reconciles the policy's `[verify] commands` from the tracked list (`.tk-studio\u002Fconfig.yaml` `engine.verify_commands`, else `plugins\u002Ftk-studio\u002Fpipeline\u002Fverify-commands.toml`) and reports it there and in the `verify commands` row: `verify_commands.policy` is `written`, `unchanged`, `skipped (…)` or `refused`, and the row's detail reads `added \u003Cn> from \u003Csource>; kept \u003Cm> operator commands`, `unchanged (…)`, `skipped (…)` or `refused: … — fix it by hand`; a refusal is a gap the session never closes by hand — end `blocked` with it verbatim.\n\n   Story 36.6: a tracked or unignored `.bmad-loop\u002Fpolicy.toml` with commands to add is refused (nothing written, `verify_commands.policy: \"refused\"`, a gap naming the file: add them by hand), and the row's engine-gate clause over a non-empty `engine.verify_commands` names each running engine sandbox: `sandbox \u003Csb>: provisioned WITH_GODOT \u003Cver>`, or `warning: sandbox \u003Csb> has no WITH_GODOT record; an engine.verify_commands gate there refuses`, advisory. The advisory `run rhythm` row names the `run-epic` instance's `stop.after_stories` (the supervisor arms the graceful stop from it and marks each story In Progress; never issue that stop by hand, except the command a refused arming's notifier line gives), or says the run goes to the epic's end when none is declared.\n\n   The advisory rows never become a gap: `studio-pipeline plugin` (present or absent) and, after it, `engine sandbox` (Story 33.3). That row reads the supervisor config's engine sandboxes (`TK_SUPERVISOR_CONFIG` `jobs.*.sandbox`), runs `sbx daemon status` and then `sbx ls`. A sandbox listed as running with no live supervisor pin record (`\u003Cstore>\u002Fsandboxes\u002F\u003Csandbox>.pin`) reads `warning: \u003Csandbox> started outside the supervisor; the next pin restarts it` — report it; never stop or start the sandbox yourself. A record is live only when it parses (`supervisor_pid` an integer, `since` an ISO-8601 instant), its `supervisor_pid` is a running process on this host, and its `since` is not older than the sandbox's start (host-now minus `sbx exec \u003Csandbox> cat \u002Fproc\u002Fuptime`, run only for a live pid) by more than a 120-second clock-skew tolerance. A record therefore reads as absent when it is unreadable, its `supervisor_pid` is not a live process, or its `since` predates the sandbox's start beyond that tolerance — e.g. after a supervisor exit, a reboot or a manual stop\u002Fstart; a kept pin under a live supervisor is still a legitimate pin (the record is removed only when a release stops the sandbox). An uptime that cannot be read leaves the pid verdict. Otherwise it reads `pinned by the supervisor`, `not running`, `no engine sandbox configured`, `sbx absent` or `daemon down`. Right after it comes `engine sandbox inodes`, advisory too: for each running engine sandbox it runs `sbx exec \u003Csandbox> df -i \u002F` and reads `\u003Cn> free inodes on \u002F`, `warning: \u003Csandbox> has \u003Cn> free inodes on \u002F (below 50000); the engine may fail to write`, or `\u003Csandbox>: inodes unknown` when the read fails or does not parse (several sandboxes are each named `\u003Csandbox>: …`, joined by `; `); otherwise the same `not running`, `no engine sandbox configured`, `sbx absent` or `daemon down`. Report a low reading; never prune or restart the sandbox yourself. After it comes `playable path` (Story 34.2), advisory too: for a project whose tracked `.tk-studio\u002Fconfig.yaml` declares `verify.engine`, it reads `warning: no $env:GODOT (unset or not an absolute file); playable runs refuse`, `warning: no display session; the \u003Cpath> path needs the logged-in desktop` (or `warning: display session unknown (\u003Cerror>)`) or `ready (\u003Cpath>)`, where `\u003Cpath>` is the ruled rendering path; any other project reads `not a game project (no verify.engine)`. Report it; never start the engine. After it comes `story plans` (Story 35.2), advisory too: `all \u003Cn> planned` or `without a plan: \u003Cid>, …` (manifest order; a plan is `\u003Cspec_folder>\u002Fplans\u002F\u003CN>-\u003CM>.md`), plus `; un-noted open questions: CAP-N (\u003Cid>), …` for the stories after the next one. Report it. After it comes `engine mcp` (Story 35.4), advisory too, from the tracked `.tk-studio\u002Fconfig.yaml`: `not configured (no engine.mcp)`, or `verify-only filter \u003Cflag>; port \u003Cper-run|fixed \u003Cn> (one flagged run at a time)>; forwarder \u003C…>; a host:port sandbox policy needs the fixed forwarder port (runbook)` when `engine.mcp.start` carries the server's verify-only allowlist flag (`engine.mcp.filter`, default `--exclude-domains`), else `warning: engine.mcp.start has no \u003Cflag>; the verify-only rule (kb\u002Fengine-mcp-godot.md) rests on the engine skill alone; port …`; an `engine.mcp` the pin's `parseEngineMcp` refuses (`port: 0` with no `{port}` in `start`, a missing or non-integer port, an empty or multi-token `filter`, …) reads `warning: \u003Cthe pin's reason, e.g. engine.mcp.start has no {port} for port: 0>; the pin refuses engine-mcp:no-config` (the flagged run would end `blocked`); a config the lib's YAML subset refuses reads `warning: .tk-studio\u002Fconfig.yaml unreadable by the lib's YAML subset (\u003Cerr>); write engine.mcp in block style`. Report it; the run proceeds, and never edit the project's config yourself.\n\n   **Relaunch.** When `SPEC.md` and the manifest already exist (the epic launched before: stories already `done`, the route already applied), steps 3 and 4 write nothing and step 5 makes no commit; go straight to step 6. A relaunch ends exactly as a fresh launch does — on the core's block (see Status block).\n\n3. **Epic SPEC (when missing).** Invoke the project's own `bmad-spec` skill by name, headless, on the epic: input = the epic's section of `_bmad-output\u002Fplanning-artifacts\u002Fepics.md` plus `_bmad-output\u002Fimplementation-artifacts\u002Fepic-\u003CN>-context.md` when present; slug `epic-\u003CN>`, so it lands at `\u003Cspec_folder>\u002FSPEC.md`. Express mode: gaps become `open_questions[]`, never invented answers. The stock skill is invoked untouched (AD-4); if it is not installed in the project, end `blocked` naming it.\n\n4. **The manifest and every story's plan (when the manifest is empty).** The task-planning instructions are a **project resource**: `\u003Croot>\u002F.bmad-loop\u002Fplugins\u002Fstudio-pipeline\u002Ftask-planning.md` (the studio pipeline's gate plugin). Read it and follow it as \"bootstrap story `\u003Cepic>-\u003Cstory>`\" — it transcribes the epic into `\u003Cspec_folder>\u002Fstories.yaml` and writes `\u003Cspec_folder>\u002Fplans\u002F\u003CN>-\u003CM>.md` for every entry in list order (`\u003Cepic>-\u003Cstory>` first; a Code Map and the band each), then validates with `bmad-loop validate`. When the named (next) story has a SPEC open question (`CAP-N`) it cannot settle into a design note, it ends `blocked` naming the CAPs, never plans around it (step 6's `check` also refuses it with the gap `open questions`). A later story's unsettled CAP never blocks the launch: it stays un-noted, recorded as a Block If under that story's plan's Risks, named in the `story plans` row, re-checked at that story's boundary and refused by `check` once that story is next. This is planner-tier work and the reason this surface's model default is the top tier. If the file is absent, end `blocked` naming it: this surface never invents a task breakdown of its own.\n\n5. **Commit the bootstrap output** — the one rule for the launch's own writes, so the dirty-tree refusal never fires on them. When steps 3–4 wrote files, commit exactly those files (`\u003Cspec_folder>\u002FSPEC.md`, `\u003Cspec_folder>\u002F.memlog.md`, `\u003Cspec_folder>\u002Fstories.yaml`, every `\u003Cspec_folder>\u002Fplans\u002F\u003CN>-\u003CM>.md` step 4 wrote, and any canonical plan files the transcription wrote) on the checkout's current branch at launch — that branch is the run branch (`loop\u002Fepic-\u003CN>` by convention; a supervisor worktree may name it otherwise, and this surface never checks the name or switches branches) — in one commit with exactly this message:\n\n   ```text\n   loop(epic-\u003CN>): SPEC, manifest and story plans from the launch bootstrap\n   ```\n\n   Name those paths, only the ones that exist, in both commands — `git add -- \u003Cpaths>` then `git commit -m '\u003Cmessage>' -- \u003Cpaths>` (a pathspec commit records only those paths, whatever else is staged) — never `git add -A`, never anything else. If `git add` or `git commit` fails, end `blocked` with the git error verbatim in `reason`. When nothing was written (a relaunch), make no commit. Never push. This happens after step 4 and before step 6's `check`.\n\n6. **Launch.** Re-run `check`; when it answers `ok`, start the engine (add `--allow-budget-mismatch` only when the payload carries `allow_budget_mismatch: true`):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" start --directory \u003Croot> --spec \u003Cspec_folder> [--allow-budget-mismatch]\n   ```\n\n   A `budget_mismatch` without the acknowledgement is a refusal (exit 2, `blocked`, both numbers in `reason`, the `budget` object carried in the refusal): report it and do not launch. The core mints the run id, spawns `bmad-loop run --spec … --run-id …` detached and console-less with its output in `~\u002F.tk-studio\u002Fprojects\u002F\u003Ckey>\u002Flaunches\u002F\u003Crun-id>.log`, and answers `ok` only once the engine has written `.bmad-loop\u002Fruns\u002F\u003Crun-id>\u002Fstate.json`. A launch it could not confirm answers `ok: false` with the pid and log named — report that as `blocked` with the reason; do not launch again.\n\n7. **Report.** Attended and headless alike: the run id, the spec folder, the stories planned (none on a relaunch) and the `story plans` row, the route (session \u002F implementer \u002F reviewers \u002F consult models and where each came from), any `budget_mismatch` with both numbers, and how to watch it — the studio supervisor's status page, `launch.py status` (this surface's `status` verb), and `bmad-loop tui`. Then end with the status block (below).\n\n### `sweep`\n\nStory 35.7: one deferred-work sweep through the studio (the `run-sweep` job type). Resolve `\u003Croot>` as `start` step 0 does, then run — no route, no bootstrap, no `check` (the core refuses on its own):\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" sweep --directory \u003Croot> --triage-wait 540 [--max-bundles \u003Cmax_bundles>]\n```\n\nRun it with the Bash tool timeout set to 600000 ms: the status block must print inside the tool's 600 s cap (the wait counts from the call's start), so the skill waits 540 s; the core's default stays 1500 s. A longer triage ends `complete` \u002F `triage still running` and the supervisor's watch records it.\n\nThe core refuses before spawning anything (`blocked`, the gap named): no `.bmad-loop\u002Fpolicy.toml`, no `_bmad-output\u002Fimplementation-artifacts\u002Fdeferred-work.md`, a live engine owning the checkout (one engine per checkout, as `start`: the run ids and statuses named — never stopped to make room, never a second engine), a dirty tree (`git status --porcelain`, the paths named), an existing run dir. Otherwise it starts `bmad-loop sweep --project \u003Croot> --no-prompt --run-id \u003Crid> [--max-bundles \u003Cn>]` detached (the triage pass: `bmad-loop-sweep` partitions the ledger; `max_bundles` and the attempt caps come from the policy, whose `[sweep] auto` stays `never` — an explicit start ignores it), waits for its `state.json`, then for `.bmad-loop\u002Fruns\u002F\u003Crid>\u002Ftriage.json` (`--triage-wait`: the skill waits 540 s; the core's default stays 1500 s). A read triage is emitted once as the `sweep-triage` ledger event and returned as `triage {bundles: [{name, dw_ids}], blocked: [{id, blocker}], decisions: [{id, question}], already_resolved: [id], skip: [id]}`. Never clean the tree, never edit the policy or the ledger, never answer a decision: under `--no-prompt` they are skipped unattended and listed for `bmad-loop decisions`.\n\nReport the bundles, the blocked entries and the human decisions, then end on the core's block. The bundles run in the engine afterwards; the supervisor closes the run out (one PR per sweep) and flips the ledger after the merge.\n\n### `status`\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" status --directory \u003Croot> [--run-id \u003Cid>]\n```\n\nRelay the live runs and the named run's phase\u002Fattempt\u002Fcycle per task, its pause (stage, reason, story) when paused, and its token totals. Read-only.\n\n### `stop`\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" stop --directory \u003Croot> --run-id \u003Cid> [--graceful]\n```\n\nAttended: confirm before an immediate stop (work in the current unit is preserved by the engine's attempt-preserve refs, but the unit is interrupted). Headless: stop as instructed; never ask.\n\n### Status block\n\nEvery path — `start` fresh or relaunch, `status`, `stop`, attended or headless — ends with the block (§3 of the driver contract) as its final line of output. The core ends every result, refusals included, with the block's keys in order (`status`, `intent`, `artifacts`, `reason`), so the rule is one: print the last core result's block as the final line, adding to `artifacts` only the SPEC\u002Fplan files this session wrote (never `run_dir_abs` or the store `log` path — §3 forbids absolute local paths). A `start` that launched ends:\n\n```json\n{\"status\": \"complete\", \"intent\": \"tk-studio-launch\", \"artifacts\": [\".bmad-loop\u002Fruns\u002F20260903-101500-ab12\", \"_bmad-output\u002Fspecs\u002Fspec-epic-2\"], \"reason\": null}\n```\n\nA `sweep` ends on its block: `complete` with `artifacts: [\".bmad-loop\u002Fruns\u002F\u003Crid>\", \".bmad-loop\u002Fruns\u002F\u003Crid>\u002Ftriage.json\"]` and the one-line reason `bundles: \u003Cname> (DW-a, DW-b); …; blocked: DW-x, …; decisions: DW-y, …` (`none` for an empty list); `complete` with `artifacts: [\".bmad-loop\u002Fruns\u002F\u003Crid>\"]` and `reason: \"triage still running\"` when the wait elapsed with the engine live (the supervisor's watch records the triage later); `blocked` when the engine ended or paused before any `triage.json` (the triage escalated — or, when the engine's journal holds `sweep-nothing-open`, `reason` names `sweep: nothing open in the ledger`) or leaving a `triage.json` that does not parse (`sweep triage unreadable`, no full wait), or a refusal.\n\n`blocked` names the gap verbatim: the readiness check's `gaps[]` (an `open questions` gap naming every CAP of the next story that has no design note), an unacknowledged `budget_mismatch`, the missing project resource, an unconfirmed launch. A path that ends before any core call (an unresolvable input, an unignored routing write, a missing `bmad-spec`) prints the same block shape itself, `blocked` with the gap. `partial` is the core's `check` naming a `budget_mismatch`.\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## Rules\n\n- One engine per checkout: the core refuses a launch while any run owns the checkout; this skill never stops one to make room.\n- The core never writes into the project tree: run state is the engine's, launch logs live in the per-user store (AD-3).\n- SPEC.md comes from `bmad-spec`, the task manifest from the project's task-planning instructions — this surface authors neither.\n- The route comes from `lib\u002Fpipeline.py` — the shipped legs are measured defaults (AD-14 resource tier); a project overrides them in `.bmad-loop\u002Frouting.toml`, a driver per invocation with `--set leg.field=value`. Escalation is deliberate: this surface never routes a leg onto a larger model than the resolved value, and never launches a subagent on the planner tier.\n- Job-level events belong to the job wrapper (`job-run`); this surface emits none of its own (AD-12) except `sweep-triage`, which the core's `sweep` verb alone emits once per triage read (Story 35.7).\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n","# tk-studio-launch\n\nThe studio's only way to start a run (studio pipeline decision 5: driver →\norchestrator → substrate). A conformant driver — the studio supervisor, Hermes\nsubmitting to it, or direct invocation (driver contract §1) — runs a `run-epic`\njob; the job wrapper invokes this surface; this surface does the planner-tier preparation and then\nhands the epic to bmad-loop through `lib\u002Flaunch.py`, the one deterministic\ncore that talks to the substrate (CLI only, never imported — AD-2). Ending\nthis session never ends the run: the engine is detached and owns the\ncheckout until it finishes, pauses, or is stopped.\n\n## Payload\n\n- `verb` — `start` (default) | `status` | `stop` | `sweep` (Story 35.7, the `run-sweep` job type)\n- `directory` — the project root (the nested root for a supervisor epic, never an engine worktree); `lib\u002Flaunch.py` walks `--directory` up to the nearest folder holding `.tk-studio\u002Fconfig.yaml` (driver contract 0.1.22), so a nested project launches against its own root and store\n- `epic` — epic number (`start`; required unless `spec_folder` is given)\n- `spec_folder?` — project-relative epic spec folder; default `_bmad-output\u002Fspecs\u002Fspec-epic-\u003CN>`\n- `story?` — the first story to bootstrap as `\u003Cepic>-\u003Cstory>` (default: the epic's first story)\n- `bootstrap?` — `true` (default) prepares SPEC.md, the epic's manifest and a plan for every story in it (list order) when absent; `false` refuses instead\n- `allow_budget_mismatch?` — `start`: `true` acknowledges a `budget_mismatch` and launches anyway (passed to the core as `--allow-budget-mismatch`); default `false` refuses it\n- `max_bundles?` — `sweep`: an integer ≥ 1 bounding the sweep's bundles (passed as `--max-bundles`; default: the policy's `[sweep] max_bundles`)\n- `run_id?` — `status`\u002F`stop`: the run to address (default: the live run)\n- `graceful?` — `stop` after the current unit instead of immediately\n\n## Behavior (both modes)\n\n### `start`\n\n0. **Resolve the inputs before anything runs** (headless: a gap here ends `blocked`, never a guess):\n   - `\u003Croot>` = the `project_root` printed by `uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fconfig.py\" root --directory \u003Cdirectory>` (the payload's `directory` walked up to the nearest folder holding `.tk-studio\u002Fconfig.yaml`, driver contract 0.1.22). Every later `\u003Croot>` — in every step here and in `status` \u002F `stop`, which resolve it the same way first — is that resolved root, never the raw `directory`.\n   - `\u003Cspec_folder>` = the payload's `spec_folder`, else `_bmad-output\u002Fspecs\u002Fspec-epic-\u003Cepic>` (the core's `--epic` flag applies the same default); with neither `epic` nor `spec_folder`, end `blocked`: `spec folder unresolvable: neither epic nor spec_folder given`.\n   - `\u003Cstory>` = the payload's `story`, else the first entry under `## Stories` in `\u003Croot>\u002F_bmad-output\u002Fimplementation-artifacts\u002Fepic-\u003Cepic>-context.md` (`Story N.M: …` → `N-M`), else the first `### Story N.M` heading of the epic's section in `\u003Croot>\u002F_bmad-output\u002Fplanning-artifacts\u002Fepics.md`; with none of these, end `blocked`: `first story unresolvable for epic \u003Cepic>`.\n\n1. **Route the epic's first story** — the model and effort every leg of the run uses (the session, its implementer \u002F reviewer \u002F consult subagents, the seam check, the review and triage stages, the supervisor pass), resolved runtime > the project's `.bmad-loop\u002Frouting.toml` > the shipped measured defaults in this skill's `customize.toml` `[pipeline]` (AD-14; `kb\u002Fexecution-pipeline-model-routing.md` carries the numbers). Run:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Fpipeline.py\" apply --directory \u003Croot> --story \u003Cepic>-\u003Cstory>\n   ```\n\n   It writes exactly the managed block in `.bmad-loop\u002Fpolicy.toml`, the subagent-model line in the tracked Claude profile when the project has one, and `.bmad-loop\u002Frouting.current.json`; nothing else. Read `writes` and `unignored[]`. A non-empty `unignored[]` names a file this write would leave dirty in the tree — the engine's preflight refuses a dirty tree — so end `blocked` naming it (`routing write not gitignored: \u003Cpath>`); never add the ignore line yourself in a headless run, and never launch around it. A refusal (`ok: false` — the policy is missing, the project's routing table is invalid) ends `blocked` with its `error` verbatim: the route is never invented. Report the route's session \u002F implementer \u002F reviewers \u002F consult models in the launch report.\n\n2. **Readiness first, and never guess around a gap.** Run:\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" check --directory \u003Croot> --spec \u003Cspec_folder>\n   ```\n\n   Read `gaps[]`. Gaps you may close in this session (only when `bootstrap` is true): a missing `SPEC.md` (step 3) and an empty or missing task manifest (step 4). Story 35.2: the gap `open questions` refuses the story the launch would start (the first manifest entry with no `stories\u002F\u003Cid>-*.md` at `status: done`) — one of its CAPs has a `- CAP-N:` line under SPEC.md `## Open Questions` and no design note names that CAP or the story; its detail is `\u003Cstory id>: CAP-N has no design note — \u003Cquestion>` (`; ` between CAPs). This session never answers it (the planner's task planning notes it or escalates): end `blocked` with the gap verbatim, every CAP named, before any dev session. A later story's un-noted CAP is never a gap. Every other gap — a live engine already on the checkout, `bmad-loop` not installed, a failing `bmad-loop validate` (a dirty tree, a broken policy) — ends the run `blocked` with the gap verbatim in `reason`. Never stop another run to make room; never clean a tree.\n\n   Read `budget` too: the core compares the engine's `.bmad-loop\u002Fpolicy.toml` limits with `.tk-studio\u002Fbudget-bands.yaml` and names each limit the bands exceed in `budget.budget_mismatch[]` (`{limit, policy, band, band_field, band_value}`). A mismatch is not a gap — `check` ends `partial` naming it — but step 6's `start` refuses it unless the payload carries `allow_budget_mismatch: true`. Report it with both numbers; never edit its `[limits]` to clear it (the limit is the operator's machine-local setting; step 1's managed routing block and `check`'s `[verify] commands` reconciliation are the only launch writes to that file, except a run worktree's per-band cap). Story 38.7: `max_followup_reviews` is compared per band (`followup_reviews_max`), each entry naming its `policy_key` (`limits.by_band.\u003Cband>.max_followup_reviews`, else `limits.max_followup_reviews`); the operator's `[limits.by_band]` closes a band's mismatch. In a linked run worktree whose run takes one story, `start` itself writes the next story's by-band figure into `[limits] max_followup_reviews` of that worktree's policy copy and answers `followup_cap {band, figure, applied, reason}`; a main checkout's policy is never written — report `followup_cap` as it reads.\n\n   Read `verify_commands` too (Story 33.5): `check` reconciles the policy's `[verify] commands` from the tracked list (`.tk-studio\u002Fconfig.yaml` `engine.verify_commands`, else `plugins\u002Ftk-studio\u002Fpipeline\u002Fverify-commands.toml`) and reports it there and in the `verify commands` row: `verify_commands.policy` is `written`, `unchanged`, `skipped (…)` or `refused`, and the row's detail reads `added \u003Cn> from \u003Csource>; kept \u003Cm> operator commands`, `unchanged (…)`, `skipped (…)` or `refused: … — fix it by hand`; a refusal is a gap the session never closes by hand — end `blocked` with it verbatim.\n\n   Story 36.6: a tracked or unignored `.bmad-loop\u002Fpolicy.toml` with commands to add is refused (nothing written, `verify_commands.policy: \"refused\"`, a gap naming the file: add them by hand), and the row's engine-gate clause over a non-empty `engine.verify_commands` names each running engine sandbox: `sandbox \u003Csb>: provisioned WITH_GODOT \u003Cver>`, or `warning: sandbox \u003Csb> has no WITH_GODOT record; an engine.verify_commands gate there refuses`, advisory. The advisory `run rhythm` row names the `run-epic` instance's `stop.after_stories` (the supervisor arms the graceful stop from it and marks each story In Progress; never issue that stop by hand, except the command a refused arming's notifier line gives), or says the run goes to the epic's end when none is declared.\n\n   The advisory rows never become a gap: `studio-pipeline plugin` (present or absent) and, after it, `engine sandbox` (Story 33.3). That row reads the supervisor config's engine sandboxes (`TK_SUPERVISOR_CONFIG` `jobs.*.sandbox`), runs `sbx daemon status` and then `sbx ls`. A sandbox listed as running with no live supervisor pin record (`\u003Cstore>\u002Fsandboxes\u002F\u003Csandbox>.pin`) reads `warning: \u003Csandbox> started outside the supervisor; the next pin restarts it` — report it; never stop or start the sandbox yourself. A record is live only when it parses (`supervisor_pid` an integer, `since` an ISO-8601 instant), its `supervisor_pid` is a running process on this host, and its `since` is not older than the sandbox's start (host-now minus `sbx exec \u003Csandbox> cat \u002Fproc\u002Fuptime`, run only for a live pid) by more than a 120-second clock-skew tolerance. A record therefore reads as absent when it is unreadable, its `supervisor_pid` is not a live process, or its `since` predates the sandbox's start beyond that tolerance — e.g. after a supervisor exit, a reboot or a manual stop\u002Fstart; a kept pin under a live supervisor is still a legitimate pin (the record is removed only when a release stops the sandbox). An uptime that cannot be read leaves the pid verdict. Otherwise it reads `pinned by the supervisor`, `not running`, `no engine sandbox configured`, `sbx absent` or `daemon down`. Right after it comes `engine sandbox inodes`, advisory too: for each running engine sandbox it runs `sbx exec \u003Csandbox> df -i \u002F` and reads `\u003Cn> free inodes on \u002F`, `warning: \u003Csandbox> has \u003Cn> free inodes on \u002F (below 50000); the engine may fail to write`, or `\u003Csandbox>: inodes unknown` when the read fails or does not parse (several sandboxes are each named `\u003Csandbox>: …`, joined by `; `); otherwise the same `not running`, `no engine sandbox configured`, `sbx absent` or `daemon down`. Report a low reading; never prune or restart the sandbox yourself. After it comes `playable path` (Story 34.2), advisory too: for a project whose tracked `.tk-studio\u002Fconfig.yaml` declares `verify.engine`, it reads `warning: no $env:GODOT (unset or not an absolute file); playable runs refuse`, `warning: no display session; the \u003Cpath> path needs the logged-in desktop` (or `warning: display session unknown (\u003Cerror>)`) or `ready (\u003Cpath>)`, where `\u003Cpath>` is the ruled rendering path; any other project reads `not a game project (no verify.engine)`. Report it; never start the engine. After it comes `story plans` (Story 35.2), advisory too: `all \u003Cn> planned` or `without a plan: \u003Cid>, …` (manifest order; a plan is `\u003Cspec_folder>\u002Fplans\u002F\u003CN>-\u003CM>.md`), plus `; un-noted open questions: CAP-N (\u003Cid>), …` for the stories after the next one. Report it. After it comes `engine mcp` (Story 35.4), advisory too, from the tracked `.tk-studio\u002Fconfig.yaml`: `not configured (no engine.mcp)`, or `verify-only filter \u003Cflag>; port \u003Cper-run|fixed \u003Cn> (one flagged run at a time)>; forwarder \u003C…>; a host:port sandbox policy needs the fixed forwarder port (runbook)` when `engine.mcp.start` carries the server's verify-only allowlist flag (`engine.mcp.filter`, default `--exclude-domains`), else `warning: engine.mcp.start has no \u003Cflag>; the verify-only rule (kb\u002Fengine-mcp-godot.md) rests on the engine skill alone; port …`; an `engine.mcp` the pin's `parseEngineMcp` refuses (`port: 0` with no `{port}` in `start`, a missing or non-integer port, an empty or multi-token `filter`, …) reads `warning: \u003Cthe pin's reason, e.g. engine.mcp.start has no {port} for port: 0>; the pin refuses engine-mcp:no-config` (the flagged run would end `blocked`); a config the lib's YAML subset refuses reads `warning: .tk-studio\u002Fconfig.yaml unreadable by the lib's YAML subset (\u003Cerr>); write engine.mcp in block style`. Report it; the run proceeds, and never edit the project's config yourself.\n\n   **Relaunch.** When `SPEC.md` and the manifest already exist (the epic launched before: stories already `done`, the route already applied), steps 3 and 4 write nothing and step 5 makes no commit; go straight to step 6. A relaunch ends exactly as a fresh launch does — on the core's block (see Status block).\n\n3. **Epic SPEC (when missing).** Invoke the project's own `bmad-spec` skill by name, headless, on the epic: input = the epic's section of `_bmad-output\u002Fplanning-artifacts\u002Fepics.md` plus `_bmad-output\u002Fimplementation-artifacts\u002Fepic-\u003CN>-context.md` when present; slug `epic-\u003CN>`, so it lands at `\u003Cspec_folder>\u002FSPEC.md`. Express mode: gaps become `open_questions[]`, never invented answers. The stock skill is invoked untouched (AD-4); if it is not installed in the project, end `blocked` naming it.\n\n4. **The manifest and every story's plan (when the manifest is empty).** The task-planning instructions are a **project resource**: `\u003Croot>\u002F.bmad-loop\u002Fplugins\u002Fstudio-pipeline\u002Ftask-planning.md` (the studio pipeline's gate plugin). Read it and follow it as \"bootstrap story `\u003Cepic>-\u003Cstory>`\" — it transcribes the epic into `\u003Cspec_folder>\u002Fstories.yaml` and writes `\u003Cspec_folder>\u002Fplans\u002F\u003CN>-\u003CM>.md` for every entry in list order (`\u003Cepic>-\u003Cstory>` first; a Code Map and the band each), then validates with `bmad-loop validate`. When the named (next) story has a SPEC open question (`CAP-N`) it cannot settle into a design note, it ends `blocked` naming the CAPs, never plans around it (step 6's `check` also refuses it with the gap `open questions`). A later story's unsettled CAP never blocks the launch: it stays un-noted, recorded as a Block If under that story's plan's Risks, named in the `story plans` row, re-checked at that story's boundary and refused by `check` once that story is next. This is planner-tier work and the reason this surface's model default is the top tier. If the file is absent, end `blocked` naming it: this surface never invents a task breakdown of its own.\n\n5. **Commit the bootstrap output** — the one rule for the launch's own writes, so the dirty-tree refusal never fires on them. When steps 3–4 wrote files, commit exactly those files (`\u003Cspec_folder>\u002FSPEC.md`, `\u003Cspec_folder>\u002F.memlog.md`, `\u003Cspec_folder>\u002Fstories.yaml`, every `\u003Cspec_folder>\u002Fplans\u002F\u003CN>-\u003CM>.md` step 4 wrote, and any canonical plan files the transcription wrote) on the checkout's current branch at launch — that branch is the run branch (`loop\u002Fepic-\u003CN>` by convention; a supervisor worktree may name it otherwise, and this surface never checks the name or switches branches) — in one commit with exactly this message:\n\n   ```text\n   loop(epic-\u003CN>): SPEC, manifest and story plans from the launch bootstrap\n   ```\n\n   Name those paths, only the ones that exist, in both commands — `git add -- \u003Cpaths>` then `git commit -m '\u003Cmessage>' -- \u003Cpaths>` (a pathspec commit records only those paths, whatever else is staged) — never `git add -A`, never anything else. If `git add` or `git commit` fails, end `blocked` with the git error verbatim in `reason`. When nothing was written (a relaunch), make no commit. Never push. This happens after step 4 and before step 6's `check`.\n\n6. **Launch.** Re-run `check`; when it answers `ok`, start the engine (add `--allow-budget-mismatch` only when the payload carries `allow_budget_mismatch: true`):\n\n   ```bash\n   uv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" start --directory \u003Croot> --spec \u003Cspec_folder> [--allow-budget-mismatch]\n   ```\n\n   A `budget_mismatch` without the acknowledgement is a refusal (exit 2, `blocked`, both numbers in `reason`, the `budget` object carried in the refusal): report it and do not launch. The core mints the run id, spawns `bmad-loop run --spec … --run-id …` detached and console-less with its output in `~\u002F.tk-studio\u002Fprojects\u002F\u003Ckey>\u002Flaunches\u002F\u003Crun-id>.log`, and answers `ok` only once the engine has written `.bmad-loop\u002Fruns\u002F\u003Crun-id>\u002Fstate.json`. A launch it could not confirm answers `ok: false` with the pid and log named — report that as `blocked` with the reason; do not launch again.\n\n7. **Report.** Attended and headless alike: the run id, the spec folder, the stories planned (none on a relaunch) and the `story plans` row, the route (session \u002F implementer \u002F reviewers \u002F consult models and where each came from), any `budget_mismatch` with both numbers, and how to watch it — the studio supervisor's status page, `launch.py status` (this surface's `status` verb), and `bmad-loop tui`. Then end with the status block (below).\n\n### `sweep`\n\nStory 35.7: one deferred-work sweep through the studio (the `run-sweep` job type). Resolve `\u003Croot>` as `start` step 0 does, then run — no route, no bootstrap, no `check` (the core refuses on its own):\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" sweep --directory \u003Croot> --triage-wait 540 [--max-bundles \u003Cmax_bundles>]\n```\n\nRun it with the Bash tool timeout set to 600000 ms: the status block must print inside the tool's 600 s cap (the wait counts from the call's start), so the skill waits 540 s; the core's default stays 1500 s. A longer triage ends `complete` \u002F `triage still running` and the supervisor's watch records it.\n\nThe core refuses before spawning anything (`blocked`, the gap named): no `.bmad-loop\u002Fpolicy.toml`, no `_bmad-output\u002Fimplementation-artifacts\u002Fdeferred-work.md`, a live engine owning the checkout (one engine per checkout, as `start`: the run ids and statuses named — never stopped to make room, never a second engine), a dirty tree (`git status --porcelain`, the paths named), an existing run dir. Otherwise it starts `bmad-loop sweep --project \u003Croot> --no-prompt --run-id \u003Crid> [--max-bundles \u003Cn>]` detached (the triage pass: `bmad-loop-sweep` partitions the ledger; `max_bundles` and the attempt caps come from the policy, whose `[sweep] auto` stays `never` — an explicit start ignores it), waits for its `state.json`, then for `.bmad-loop\u002Fruns\u002F\u003Crid>\u002Ftriage.json` (`--triage-wait`: the skill waits 540 s; the core's default stays 1500 s). A read triage is emitted once as the `sweep-triage` ledger event and returned as `triage {bundles: [{name, dw_ids}], blocked: [{id, blocker}], decisions: [{id, question}], already_resolved: [id], skip: [id]}`. Never clean the tree, never edit the policy or the ledger, never answer a decision: under `--no-prompt` they are skipped unattended and listed for `bmad-loop decisions`.\n\nReport the bundles, the blocked entries and the human decisions, then end on the core's block. The bundles run in the engine afterwards; the supervisor closes the run out (one PR per sweep) and flips the ledger after the merge.\n\n### `status`\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" status --directory \u003Croot> [--run-id \u003Cid>]\n```\n\nRelay the live runs and the named run's phase\u002Fattempt\u002Fcycle per task, its pause (stage, reason, story) when paused, and its token totals. Read-only.\n\n### `stop`\n\n```bash\nuv run \"${CLAUDE_PLUGIN_ROOT}\u002Flib\u002Flaunch.py\" stop --directory \u003Croot> --run-id \u003Cid> [--graceful]\n```\n\nAttended: confirm before an immediate stop (work in the current unit is preserved by the engine's attempt-preserve refs, but the unit is interrupted). Headless: stop as instructed; never ask.\n\n### Status block\n\nEvery path — `start` fresh or relaunch, `status`, `stop`, attended or headless — ends with the block (§3 of the driver contract) as its final line of output. The core ends every result, refusals included, with the block's keys in order (`status`, `intent`, `artifacts`, `reason`), so the rule is one: print the last core result's block as the final line, adding to `artifacts` only the SPEC\u002Fplan files this session wrote (never `run_dir_abs` or the store `log` path — §3 forbids absolute local paths). A `start` that launched ends:\n\n```json\n{\"status\": \"complete\", \"intent\": \"tk-studio-launch\", \"artifacts\": [\".bmad-loop\u002Fruns\u002F20260903-101500-ab12\", \"_bmad-output\u002Fspecs\u002Fspec-epic-2\"], \"reason\": null}\n```\n\nA `sweep` ends on its block: `complete` with `artifacts: [\".bmad-loop\u002Fruns\u002F\u003Crid>\", \".bmad-loop\u002Fruns\u002F\u003Crid>\u002Ftriage.json\"]` and the one-line reason `bundles: \u003Cname> (DW-a, DW-b); …; blocked: DW-x, …; decisions: DW-y, …` (`none` for an empty list); `complete` with `artifacts: [\".bmad-loop\u002Fruns\u002F\u003Crid>\"]` and `reason: \"triage still running\"` when the wait elapsed with the engine live (the supervisor's watch records the triage later); `blocked` when the engine ended or paused before any `triage.json` (the triage escalated — or, when the engine's journal holds `sweep-nothing-open`, `reason` names `sweep: nothing open in the ledger`) or leaving a `triage.json` that does not parse (`sweep triage unreadable`, no full wait), or a refusal.\n\n`blocked` names the gap verbatim: the readiness check's `gaps[]` (an `open questions` gap naming every CAP of the next story that has no design note), an unacknowledged `budget_mismatch`, the missing project resource, an unconfirmed launch. A path that ends before any core call (an unresolvable input, an unignored routing write, a missing `bmad-spec`) prints the same block shape itself, `blocked` with the gap. `partial` is the core's `check` naming a `budget_mismatch`.\n\nIf the deterministic core is unrunnable — a tool call denied by permissions, `uv`\u002Fpython unavailable — end `blocked` with the status block naming the unrunnable core as `reason`: never a question, never a headless run that ends without the block (AD-11).\n\n## Rules\n\n- One engine per checkout: the core refuses a launch while any run owns the checkout; this skill never stops one to make room.\n- The core never writes into the project tree: run state is the engine's, launch logs live in the per-user store (AD-3).\n- SPEC.md comes from `bmad-spec`, the task manifest from the project's task-planning instructions — this surface authors neither.\n- The route comes from `lib\u002Fpipeline.py` — the shipped legs are measured defaults (AD-14 resource tier); a project overrides them in `.bmad-loop\u002Frouting.toml`, a driver per invocation with `--set leg.field=value`. Escalation is deliberate: this surface never routes a leg onto a larger model than the resolved value, and never launches a subagent on the planner tier.\n- Job-level events belong to the job wrapper (`job-run`); this surface emits none of its own (AD-12) except `sweep-triage`, which the core's `sweep` verb alone emits once per triage read (Story 35.7).\n- All paths resolve through `${CLAUDE_PLUGIN_ROOT}`.\n",{"name":5,"description":7},"main","ecd23b3c0458cd511812f643d9111e3d7c8235f4","plugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-launch","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio","https:\u002F\u002Fgithub.com\u002Fthkennedy","https:\u002F\u002Ftimothyhkennedy.com","Just a guy who loves making tools, automation and games.","2026-11-10 20:38:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add thkennedy\u002Ftk-studio --skill tk-studio-launch",{"tool":38,"command":39},"bunx","bunx skills add thkennedy\u002Ftk-studio --skill tk-studio-launch",{"tool":41,"command":42},"pnpm","pnpm dlx skills add thkennedy\u002Ftk-studio --skill tk-studio-launch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-launch\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"customize.toml","OTHER","其他",6620,"https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-launch\u002Fcustomize.toml",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M79RYSQ8C3MWDFTDSRAYFJYA","tk-studio-track","Tracking verbs on the bound Jira project — `block` moves a story the loop cannot progress, and each dependent story, to \"Blocked - Awaiting User\" with a comment that @mentions the owner (or, with `--engagement`, one engagement's questions issue, which `close` later moves to \"Done\"); `reply` posts the owner's answer (or \"Done.\") with the owner's host-only token and moves the issue to \"Block Resolved\"; `validate` checks that resolution and passes the issue back to work or re-blocks it with a follow-up. Use when the user says \"block this story\", \"tk track block\", \"put it in the owner's inbox\", \"reply to the blocked issue\", \"validate the resolution\", or a supervisor or engagement payload names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-track\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M79RYMVE0031EV5B64MBGD8V","tk-studio-session","Session discipline as a surface — land a boundary handoff (optionally carrying knowledge deltas) and end the session, or resume a fresh session from a run workspace alone. Use when the user says \"hand off this run\", \"tk session\", \"resume the run\", or a boundary\u002Fbudget trigger says the session must split.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-session\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M79RYFM9ATWHM6HAXJ3D19WV","tk-studio-research","Run a chartered research pass — survey the topics a charter scopes, grade every finding by evidence, land the findings in the run workspace, and emit observation events for recommendation-worthy ones. Use when the user says \"run the ecosystem watch\", \"tk research\", or a research job's invoke-skill directive names this skill.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-research\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M79RYA1AWZZF83KBHGR6JDN3","tk-studio-report","One-verb human defect report — \"the skill did the wrong thing\" — recorded as a report event in the local measurement ledger. Use when the user says \"tk report\", \"report a defect\", \"that skill misbehaved\", or \"log a studio issue\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-report\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M79RY33VMYR5YNPVFKWRNW9S","tk-studio-playable-judge","The playable-verify leg's screenshot judge (Story 34.3) — reads only a playable run's report.json and its frames, answers the fixed rubric (scene loaded, player visible and framed, no magenta or error overlay, HUD reads, the named moments shown) with pass or fail and findings each naming a frame and a rubric line. Driven headless by the supervisor's host leg on the project's sandbox tier; use when the payload names a playable `media` folder, or the user says \"judge the playable frames\".","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-playable-judge\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M79RXY4AM8JM6ZK2MAR3W3X2","tk-studio-plan-sync","Planning adapter — canonicalize BMad-native planning artifacts (normalize pass, sole id authority) and sync them with the bound planning backend. Use when the user says \"sync the plan\", \"normalize planning artifacts\", \"tk plan sync\", or after stock BMad planning flows produce or change epics\u002Fstories.","https:\u002F\u002Fgithub.com\u002Fthkennedy\u002Ftk-studio\u002Fblob\u002Fmain\u002Fplugins\u002Ftk-studio\u002Fskills\u002Ftk-studio-plan-sync\u002FSKILL.md",[],[]]