playmaker-cli 0.12.0__tar.gz → 0.13.0__tar.gz

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/CHANGELOG.md

@@ -5,6 +5,69 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.13.0] - 2026-09-30
+
+### Added
+
+- **`muse` lane — Meta's Muse Code CLI as a first-class agent.**
+  `playmaker dispatch muse` runs `muse exec --json …`, and the session id
+  arrives in the **first** stdout line — unlike kimi, whose id comes last — so
+  `playmaker list` shows it at once. Resume re-runs `muse exec` with
+  `--session-id` in the same cwd, and `summary` reads
+  `${XDG_DATA_HOME:-~/.local/share}/muse/sessions/YYYY/MM/DD/<uuid>/session.jsonl`.
+  Permissions default to Muse's sandbox with approval off and the workspace
+  trusted (`--disable-approval --trust-workspace` — without trust Muse ignores
+  the repo's AGENTS.md), and `[agents.muse]` takes `binary`, `model`,
+  `reasoning_effort`, `yolo`, `trust_workspace`, `sandbox_network` and
+  `permission_profile`. Muse Spark is a senior-tier peer of codex, GLM and K3,
+  on its own `muse login`. No usage/quota API exists, so `playmaker quotas`
+  has no Muse block.
+
+### Fixed
+
+- **`playmaker quotas` printed `unsupported` for Kimi Code.** By 2026-09-29
+  the `/usages` endpoint stopped returning the `user` object — and with it
+  `membership.level` — and the probe required it, so a payload whose `usage`
+  and `limits[]` buckets were unchanged was rejected as unrecognised. `user`
+  is now optional (when present it must still be an object), so the Session
+  and Weekly rows render again; the `Kimi Code` header goes without the tier
+  the API no longer reports. The new `usages` block (`limit_5h`/`limit_7d`
+  with `used_ratio`) is not read: on the live account it said 0 while `usage`
+  counted 21 used.
+- **`playmaker quotas` printed an error for Antigravity while agy worked.**
+  Two things broke at once. agy 1.2's embedded language server now refuses a
+  request without its CSRF token (401 `missing CSRF token`), and an agy someone
+  else started keeps that token to itself, so the local path found nothing it
+  could read. The remote fallback (`retrieveUserQuota`, ideType ANTIGRAVITY)
+  meanwhile began answering 403 "You do not have a valid license of this
+  product". The probe now starts a short-lived agy of its own when no running
+  one answers — headless (`--input-format stream-json -p=` waits on stdin, so
+  no TTY and no request spent), with a token it chose, in an empty scratch
+  directory, stopped as a process group once the summary is in (about 1.5 s;
+  capped at 12 s) — and reads the full Gemini and Claude/GPT 5h/weekly
+  windows off it. Process discovery also matches `agy-real`, the binary
+  behind an `agy` wrapper. If both sources still fail and the remote says "no
+  valid license", the block reads `unavailable` with a hint and keeps its last
+  success instead of `error`; any other remote failure is still an error. A
+  remote fallback now says why the daemon was missed.
+
+## [0.12.1] - 2026-09-08
+
+### Fixed
+
+- **The bundled coach skill never named the `kimi` lane.** 0.11.0 made Kimi
+  Code a first-class agent and `references/lanes.md` listed it, but `SKILL.md`
+  — the file the coach reads first, and the description Claude Code matches a
+  request against — still said the workers were Claude, Codex, Antigravity and
+  opencode; the routing cheat-sheet sent write-heavy work that can leave
+  Claude to `codex / agy / opencode` only, and the tier table had no senior
+  seat for K3. A coach following the skill to the letter would never route a
+  WP to the one subscription nobody else on the machine draws from. The
+  description, the lane list, the per-agent-traps pointer, the cheat-sheet
+  and the tier table now name `kimi`; CONTRIBUTING's lane and handler lists
+  too. As with 0.5.1, this release exists because the skill ships inside the
+  wheel — doc fixes are not live until published.
+
 ## [0.12.0] - 2026-09-04
 
 ### Added

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/PKG-INFO

@@ -1,14 +1,14 @@
 Metadata-Version: 2.5
 Name: playmaker-cli
-Version: 0.12.0
-Summary: Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity, Kimi Code and opencode sub-agents in parallel.
+Version: 0.13.0
+Summary: Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity, Kimi Code, Muse Code and opencode sub-agents in parallel.
 Project-URL: Homepage, https://github.com/vladsafedev/playmaker
 Project-URL: Repository, https://github.com/vladsafedev/playmaker
 Project-URL: Issues, https://github.com/vladsafedev/playmaker/issues
 Author-email: Vladislav Shulyugin <vladislav.shulyugin@gmail.com>
 License-Expression: MIT
 License-File: LICENSE
-Keywords: agents,ai,antigravity,claude,claude-code,cli,codex,gemini,glm,kimi,kimi-code,opencode,orchestration,subagents
+Keywords: agents,ai,antigravity,claude,claude-code,cli,codex,gemini,glm,kimi,kimi-code,muse,muse-code,opencode,orchestration,subagents
 Classifier: Development Status :: 3 - Alpha
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
@@ -32,7 +32,7 @@ Description-Content-Type: text/markdown
 [![Python](https://img.shields.io/pypi/pyversions/playmaker-cli.svg?cacheSeconds=3600)](https://pypi.org/project/playmaker-cli/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
-**Run Claude Code, Codex, Antigravity, Kimi Code and opencode as parallel sub-agents from one terminal — and spend separate quotas instead of one.**
+**Run Claude Code, Codex, Antigravity, Kimi Code, Muse Code and opencode as parallel sub-agents from one terminal — and spend separate quotas instead of one.**
 
 You stay in your Claude Code session doing the part only you can do. `playmaker`
 fans the rest out to other agent CLIs as detached processes, tracks them,
@@ -74,11 +74,13 @@ in one serial session:
 1. **Wall-clock speed.** A task that decomposes into 3–5 independent
    work-streams (schema, backend, frontend, tests, docs) finishes 2–4× faster
    when each stream runs as its own parallel agent.
-2. **Provider arbitrage.** Codex, Antigravity, Kimi Code and opencode quotas
-   are entirely separate pools from your Anthropic plan. Every slice you hand
-   them is capacity your main session never spends — and Antigravity's roster
-   includes Claude Sonnet/Opus, so even Claude-quality work can run on Google's
-   pool. Kimi Code brings its own subscription with the senior-tier K3.
+2. **Provider arbitrage.** Codex, Antigravity, Kimi Code, Muse Code and
+   opencode quotas are entirely separate pools from your Anthropic plan. Every
+   slice you hand them is capacity your main session never spends — and
+   Antigravity's roster includes Claude Sonnet/Opus, so even Claude-quality
+   work can run on Google's pool. Kimi Code brings its own subscription with
+   the senior-tier K3; Muse Code adds Meta's senior-tier Muse Spark on its own
+   login.
    `opencode` widens this the most: one CLI fronting ~75 providers, from a z.ai
    GLM coding plan to models running locally on your own machine.
 3. **Bucket arbitrage inside one plan.** Headless `claude -p` draws on the same
@@ -151,6 +153,11 @@ The other agents differ, because their CLIs do:
   `--auto`, `--yolo` and `--plan`, and already runs with auto-approval, so
   there is no read-only mode below the prompt.
 
+- **muse** runs sandboxed by default with approval off and the workspace
+  trusted (`--disable-approval --trust-workspace`). The sandbox denies writes
+  outside the repo, so `uv run`, npm and similar caches fail inside it — set
+  `yolo = true` if workers must run such gates.
+
 - **gemini** (legacy) runs with `--yolo`.
 
 ## Install
@@ -189,6 +196,7 @@ playmaker agents          # which agent CLIs are reachable
 | **Antigravity (`agy`)** | bundled with [Antigravity](https://antigravity.google) | `--model claude-opus-4-6-thinking` — the roster moves, so read it from `agy models` |
 | **opencode** | `brew install sst/tap/opencode` (or see [opencode.ai](https://opencode.ai)) | `--model provider/model`, e.g. `zai-coding-plan/glm-5.2`; roster from `opencode models`, providers from `opencode auth login` |
 | **Kimi Code CLI** | `npm i -g @moonshot-ai/kimi-code` | needs Node ≥ 22.19 (a wrapper that pins a newer Node is fine — point `[agents.kimi] binary` at it); `--model kimi-code/k3-256k` — 256k window at half the quota cost of `k3`; log in once with `kimi login --region global`; model ids from `~/.kimi-code/config.toml` |
+| **Muse Code CLI** | `curl -fsSL https://dev.meta.ai/install.sh \| sh` | self-updating launcher in `~/.local/bin` (point `[agents.muse] binary` at it if a detached dispatch can't find it); log in once with `muse login` or set `META_API_KEY`; `--model muse-spark-1.3` — omit it and Muse's own default from `~/.config/muse/settings.json` applies |
 | **Gemini CLI** (legacy) | `npm i -g @google/gemini-cli` | still supported, superseded by `agy` |
 
 At least one is required; `playmaker agents` tells you which it can see.
@@ -324,6 +332,7 @@ and locates the session file the tool writes locally. Empirically:
 | Antigravity | `~/.gemini/antigravity-cli/brain/<conversation-id>/.system_generated/logs/transcript_full.jsonl` |
 | opencode | SQLite — `~/.local/share/opencode/opencode.db` (`session` / `message` / `part`); playmaker keeps a pointer at `~/.playmaker/opencode/<id>.session` |
 | kimi | `~/.kimi-code/sessions/wd_<cwd-basename>_<hash>/session_<id>/agents/main/wire.jsonl` (per-cwd; `KIMI_CODE_HOME` overrides the root) |
+| muse | `${XDG_DATA_HOME:-~/.local/share}/muse/sessions/YYYY/MM/DD/<session-uuid>/session.jsonl` (the date directory is the session's creation date; a resume appends to the same file) |
 | Gemini | `~/.gemini/tmp/<cwd-basename>/chats/session-<ts>-<short_id>.{json,jsonl}` |
 
 `thread` and `summary` normalize all of them into the same turn list, so every
@@ -450,6 +459,9 @@ whole Z.ai block. Routing a subtask is choosing which of them to spend.
   `~/.kimi-code/credentials/kimi-code-env-*.json` (`$KIMI_CODE_HOME` overrides
   the root). Its 5-hour `Session` and weekly rows are separate percentage
   buckets; no credential reads as *unsupported* rather than a failed probe.
+- **Muse Code** — no usage or quota API exists (billing is pay-as-you-go or a
+  subscription via accountscenter.meta.com), so `playmaker quotas` has no Muse
+  block.
 
 Reading these at *model* granularity is the point: they are the load-balancing
 input the coach skill uses to route each subtask.

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/README.md

@@ -5,7 +5,7 @@
 [![Python](https://img.shields.io/pypi/pyversions/playmaker-cli.svg?cacheSeconds=3600)](https://pypi.org/project/playmaker-cli/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 
-**Run Claude Code, Codex, Antigravity, Kimi Code and opencode as parallel sub-agents from one terminal — and spend separate quotas instead of one.**
+**Run Claude Code, Codex, Antigravity, Kimi Code, Muse Code and opencode as parallel sub-agents from one terminal — and spend separate quotas instead of one.**
 
 You stay in your Claude Code session doing the part only you can do. `playmaker`
 fans the rest out to other agent CLIs as detached processes, tracks them,
@@ -47,11 +47,13 @@ in one serial session:
 1. **Wall-clock speed.** A task that decomposes into 3–5 independent
    work-streams (schema, backend, frontend, tests, docs) finishes 2–4× faster
    when each stream runs as its own parallel agent.
-2. **Provider arbitrage.** Codex, Antigravity, Kimi Code and opencode quotas
-   are entirely separate pools from your Anthropic plan. Every slice you hand
-   them is capacity your main session never spends — and Antigravity's roster
-   includes Claude Sonnet/Opus, so even Claude-quality work can run on Google's
-   pool. Kimi Code brings its own subscription with the senior-tier K3.
+2. **Provider arbitrage.** Codex, Antigravity, Kimi Code, Muse Code and
+   opencode quotas are entirely separate pools from your Anthropic plan. Every
+   slice you hand them is capacity your main session never spends — and
+   Antigravity's roster includes Claude Sonnet/Opus, so even Claude-quality
+   work can run on Google's pool. Kimi Code brings its own subscription with
+   the senior-tier K3; Muse Code adds Meta's senior-tier Muse Spark on its own
+   login.
    `opencode` widens this the most: one CLI fronting ~75 providers, from a z.ai
    GLM coding plan to models running locally on your own machine.
 3. **Bucket arbitrage inside one plan.** Headless `claude -p` draws on the same
@@ -124,6 +126,11 @@ The other agents differ, because their CLIs do:
   `--auto`, `--yolo` and `--plan`, and already runs with auto-approval, so
   there is no read-only mode below the prompt.
 
+- **muse** runs sandboxed by default with approval off and the workspace
+  trusted (`--disable-approval --trust-workspace`). The sandbox denies writes
+  outside the repo, so `uv run`, npm and similar caches fail inside it — set
+  `yolo = true` if workers must run such gates.
+
 - **gemini** (legacy) runs with `--yolo`.
 
 ## Install
@@ -162,6 +169,7 @@ playmaker agents          # which agent CLIs are reachable
 | **Antigravity (`agy`)** | bundled with [Antigravity](https://antigravity.google) | `--model claude-opus-4-6-thinking` — the roster moves, so read it from `agy models` |
 | **opencode** | `brew install sst/tap/opencode` (or see [opencode.ai](https://opencode.ai)) | `--model provider/model`, e.g. `zai-coding-plan/glm-5.2`; roster from `opencode models`, providers from `opencode auth login` |
 | **Kimi Code CLI** | `npm i -g @moonshot-ai/kimi-code` | needs Node ≥ 22.19 (a wrapper that pins a newer Node is fine — point `[agents.kimi] binary` at it); `--model kimi-code/k3-256k` — 256k window at half the quota cost of `k3`; log in once with `kimi login --region global`; model ids from `~/.kimi-code/config.toml` |
+| **Muse Code CLI** | `curl -fsSL https://dev.meta.ai/install.sh \| sh` | self-updating launcher in `~/.local/bin` (point `[agents.muse] binary` at it if a detached dispatch can't find it); log in once with `muse login` or set `META_API_KEY`; `--model muse-spark-1.3` — omit it and Muse's own default from `~/.config/muse/settings.json` applies |
 | **Gemini CLI** (legacy) | `npm i -g @google/gemini-cli` | still supported, superseded by `agy` |
 
 At least one is required; `playmaker agents` tells you which it can see.
@@ -297,6 +305,7 @@ and locates the session file the tool writes locally. Empirically:
 | Antigravity | `~/.gemini/antigravity-cli/brain/<conversation-id>/.system_generated/logs/transcript_full.jsonl` |
 | opencode | SQLite — `~/.local/share/opencode/opencode.db` (`session` / `message` / `part`); playmaker keeps a pointer at `~/.playmaker/opencode/<id>.session` |
 | kimi | `~/.kimi-code/sessions/wd_<cwd-basename>_<hash>/session_<id>/agents/main/wire.jsonl` (per-cwd; `KIMI_CODE_HOME` overrides the root) |
+| muse | `${XDG_DATA_HOME:-~/.local/share}/muse/sessions/YYYY/MM/DD/<session-uuid>/session.jsonl` (the date directory is the session's creation date; a resume appends to the same file) |
 | Gemini | `~/.gemini/tmp/<cwd-basename>/chats/session-<ts>-<short_id>.{json,jsonl}` |
 
 `thread` and `summary` normalize all of them into the same turn list, so every
@@ -423,6 +432,9 @@ whole Z.ai block. Routing a subtask is choosing which of them to spend.
   `~/.kimi-code/credentials/kimi-code-env-*.json` (`$KIMI_CODE_HOME` overrides
   the root). Its 5-hour `Session` and weekly rows are separate percentage
   buckets; no credential reads as *unsupported* rather than a failed probe.
+- **Muse Code** — no usage or quota API exists (billing is pay-as-you-go or a
+  subscription via accountscenter.meta.com), so `playmaker quotas` has no Muse
+  block.
 
 Reading these at *model* granularity is the point: they are the load-balancing
 input the coach skill uses to route each subtask.

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "playmaker-cli"
-version = "0.12.0"
-description = "Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity, Kimi Code and opencode sub-agents in parallel."
+version = "0.13.0"
+description = "Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity, Kimi Code, Muse Code and opencode sub-agents in parallel."
 readme = "README.md"
 requires-python = ">=3.11"
 license = "MIT"
@@ -21,6 +21,8 @@ keywords = [
     "gemini",
     "kimi",
     "kimi-code",
+    "muse",
+    "muse-code",
     "opencode",
     "glm",
     "subagents",

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/skills/playmaker-coach/SKILL.md

@@ -1,13 +1,14 @@
 ---
 name: playmaker-coach
-description: Team-lead mode for coding work. Decompose the task into work packages, dispatch them to Claude/Codex/Antigravity(agy)/opencode workers through the `playmaker` CLI, then run an automatic multi-agent review board over every diff before it lands, and drive the fix cycles. Use for ANY request that will change code in more than one place, needs an independent review pass, or has two or more parts that can run at once — "implement", "add", "fix", "refactor", "wire up", "сделай", "почини", "добавь", "реализуй", "собери". NOT for answering a question, reading or explaining code, a single-line edit, or a git/ops command.
+description: Team-lead mode for coding work. Decompose the task into work packages, dispatch them to Claude/Codex/Antigravity(agy)/opencode/Kimi Code(kimi)/Muse Code(muse) workers through the `playmaker` CLI, then run an automatic multi-agent review board over every diff before it lands, and drive the fix cycles. Use for ANY request that will change code in more than one place, needs an independent review pass, or has two or more parts that can run at once — "implement", "add", "fix", "refactor", "wire up", "сделай", "почини", "добавь", "реализуй", "собери". NOT for answering a question, reading or explaining code, a single-line edit, or a git/ops command.
 ---
 
 # playmaker-coach — you are the tech lead, not the typist
 
-`playmaker` dispatches sub-tasks to Codex / Antigravity (`agy`) / opencode / a sibling Claude,
-tracks them, and returns their threads. This skill is the judgment on top: what to split,
-who gets which slice, how to size it so verifying is cheap, and **how the review board runs**.
+`playmaker` dispatches sub-tasks to Codex / Antigravity (`agy`) / opencode / Kimi Code (`kimi`) /
+Muse Code (`muse`) / a sibling Claude, tracks them, and returns their threads. This skill is the
+judgment on top: what to split, who gets which slice, how to size it so verifying is cheap, and
+**how the review board runs**.
 
 **The coach produces plans, prompts, verdicts and integration — not feature diffs.** Your context
 window is the most expensive resource on the table. Every file you read yourself and every line you
@@ -118,7 +119,7 @@ playmaker dispatch <agent> --model <name> --batch "$B" --cwd "$(pwd)" --prompt "
 Detached by default — that is the point; never `--sync` a whole fan-out. Always pass `--cwd`,
 `--batch` (one summary ping for the batch), and `--model` unless the profile says otherwise.
 Prompt shape: `references/prompt-templates.md`. Per-agent traps (agy scratch dir, opencode relative
-paths, codex model roster): `references/agent-gotchas.md`.
+paths, codex model roster, kimi's K2.7 default and exit codes, muse's sandbox): `references/agent-gotchas.md`.
 
 Parallel WPs that touch the same files go in **git worktrees**, one per WP, or they will collide.
 

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/skills/playmaker-coach/references/agent-gotchas.md

@@ -81,6 +81,23 @@ line from `agy models` / `opencode models` rather than typing it.
 - Needs **Node ≥ 22.19** — hence the wrapper binary; point `[agents.kimi] binary` at it.
 - **Always pass `-m kimi-code/k3-256k`** — the CLI default is the weaker K2.7 `kimi-for-coding`.
 
+## muse (Muse Code CLI)
+
+- The default run keeps Muse's **sandbox**: approval off, workspace trusted, writes inside the
+  repo fine — but writes **outside** it are denied, so `uv run pytest` fails initializing
+  `~/.cache/uv` (npm/pnpm caches alike). A WP whose gate needs those caches needs
+  `[agents.muse] yolo = true`.
+- **Without workspace trust Muse ignores the repo's AGENTS.md.** playmaker passes
+  `--trust-workspace` by default; `trust_workspace = false` drops it, and repo rules stop
+  applying.
+- Exit codes: **0** turn completed; **1** run failed (bad model, auth) — the reason is in the
+  terminal event and stderr's last line; **2** usage error; **130/143** SIGINT/SIGTERM.
+- **Resume only from the same cwd** — a `--session-id` elsewhere would need
+  `--allow-workspace-switch`, which playmaker never passes.
+- stderr **always** carries informational lines such as `muse: workspace root: …`, even on
+  success — they are not errors.
+- The stream has **no cost fields** — token usage exists only in the session log on disk.
+
 ## Worktrees
 
 Parallel WPs that touch the same files collide. Give each its own git worktree and dispatch with

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/skills/playmaker-coach/references/lanes.md

@@ -18,9 +18,9 @@ pays. Four lanes:
    (`haiku` for trivial mechanical work). playmaker runs it in `acceptEdits`: it writes freely
    inside `--cwd` and is refused outside it, so keep every path in the prompt inside `--cwd`.
 
-4. **External dispatch — `codex` / `agy` / `opencode` / `kimi`.** Each on its own subscription or
-   plan — the home for write-heavy parallel implementation that can leave the Anthropic
-   subscription.
+4. **External dispatch — `codex` / `agy` / `opencode` / `kimi` / `muse`.** Each on its own
+   subscription or plan — the home for write-heavy parallel implementation that can leave the
+   Anthropic subscription.
    - **`agy` (Antigravity)** carries more than Google models: alongside Gemini Flash and Pro tiers it
      serves **Claude Sonnet/Opus (Thinking)** and a GPT-OSS tier. Its Claude runs on *Google's*
      pool and spends none of the Anthropic bucket — but that roster has trailed Anthropic's own
@@ -32,6 +32,8 @@ pays. Four lanes:
      at all.
    - **`kimi`** runs the Kimi Code CLI on its own subscription: senior tier (K3), native login, no
      opencode.
+   - **`muse`** runs Meta's Muse Code CLI on its own login: senior tier (Muse Spark), sandboxed
+     by default.
 
 **Never write an agy or opencode model name from memory** — run `agy models` / `opencode models` and
 copy a line. Both rosters and their spelling move with releases, and playmaker validates `--model`
@@ -44,15 +46,17 @@ against the live roster, failing the dispatch on a stale name.
 | writes files, coach integrates the result directly | in-session sub-agent | write-capable, returns into context |
 | is an independent stream to monitor separately | `dispatch claude --model sonnet` | tracked, detached, spares the top bucket |
 | is heavy reasoning only the coach can do | coach | top tier, serial |
-| is write-heavy and can leave Claude | codex / agy / opencode | their own quotas |
-| needs a second strong reviewer without touching the Anthropic bucket | `dispatch agy --model <gemini-pro-high>` | near-senior judgment on an uncontended pool |
+| is write-heavy and can leave Claude | codex / agy / opencode / kimi / muse | their own quotas |
+| needs senior judgment on a pool nobody else on the machine draws from | `dispatch kimi -m kimi-code/k3-256k` / `dispatch muse` | K3 and Muse Spark on their own subscriptions; K3 is slow, so detached only |
+| needs a second strong reviewer without touching the Anthropic bucket | `dispatch agy --model <gemini-pro-high>` / `dispatch muse` | near-senior judgment on an uncontended pool; Muse Spark is senior |
 | is bulk work with every subscription low | `dispatch opencode --model <plan>/<model>` | a separate plan, untouched by the others |
 | is mechanical and privacy-sensitive, or all quotas spent | `dispatch opencode --model <local>/<model>` | runs on this machine, costs wall-clock only |
 
 ## Tier-matching
 
 - **Architectural / spec judgment / cross-module integration** → top tier (coach, top-tier Codex,
-  Gemini-Pro-high on agy for review and advice rather than implementation).
+  K3 on `kimi`, Muse Spark on `muse`, Gemini-Pro-high on agy for review and advice rather than
+  implementation).
 - **Pattern-following implementation, scoped CRUD, mechanical refactor, test scaffolding, writing
   inside an existing convention** → mid tier (Claude Sonnet, Gemini-Pro-low, mid-tier Codex;
   agy's Claude models only when the roster shows a current version). Most delegated implementation lives here.

{playmaker_cli-0.12.0 → playmaker_cli-0.13.0}/skills/playmaker-coach/references/quotas.md

@@ -19,8 +19,10 @@ several tiers with independent buckets, and the whole point of pulling quotas is
 - **Antigravity (`agy`):** one Google pool split by family — `Gemini 5h` / `Gemini weekly` and
   `Claude/GPT 5h` / `Claude/GPT weekly`. All Gemini models share the first; Claude *and* GPT-OSS
   share the second. So one Gemini reviewer plus one agy-Claude reviewer costs one hit in each of two
-  separate buckets — the cheapest way to buy two independent opinions. Requires agy's local daemon;
-  if the table says "daemon offline" it fell back to a coarse Gemini-only view.
+  separate buckets — the cheapest way to buy two independent opinions. Read off agy's local daemon —
+  playmaker starts a short-lived one itself when none answers. "daemon offline" means it fell back
+  to a coarse Gemini-only view; `unavailable` means neither source answered — the lane still works,
+  so route by the last success and say the numbers are old.
 - **Codex:** the main block is the primary Codex window; `Codex — Spark` is a separate block with
   its own `Session` / `Weekly` rows for the Spark model, the junior Codex lane — route Spark work
   off that block, not off the main one.