playmaker-cli 0.9.0__tar.gz → 0.11.0__tar.gz

{playmaker_cli-0.9.0 → playmaker_cli-0.11.0}/CHANGELOG.md

@@ -5,6 +5,43 @@ 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).
 
+## [0.11.0] - 2026-09-04
+
+### Added
+
+- **`kimi` lane — the Kimi Code CLI as a first-class agent.**
+  `playmaker dispatch kimi -m kimi-code/k3-256k` runs `kimi -p …
+  --output-format stream-json`, tracks the session, resumes with `-S`, and
+  reads the per-cwd `wire.jsonl` for `summary`. K3 is a senior-tier model on a
+  subscription nobody else on the machine draws from, and routing it through
+  opencode would have needed a second credential; the native CLI reuses its
+  own OAuth login.
+
+## [0.10.0] - 2026-09-04
+
+### Added
+
+- **`playmaker quotas` shows the two buckets that actually run out first.**
+  Codex's `additional_rate_limits[]` carries a separate GPT-5.3-Codex-Spark
+  pool with its own 5h and weekly windows, and Anthropic's `limits[]` carries
+  a model-scoped weekly next to the all-models one. Both were in the raw
+  responses and dropped by the probe, so a coach could route a junior WP to
+  Spark while its weekly sat at 4%, or budget a session on the all-models bar
+  while its own model-scoped bucket was the one about to end it. Codex now
+  renders a `Codex — Spark` sub-block and Claude a `Weekly · <model>` row;
+  probes return an additive `blocks` key that `_render_provider` draws for any
+  provider.
+
+### Changed
+
+- **The coach no longer tiers Antigravity's Claude models by name.**
+  `lanes.md` called `agy`'s Claude-Opus "top-tier Claude judgment on Google's
+  pool" and offered it as the reviewer to reach for when the Anthropic bucket
+  is precious. That roster trails Anthropic's releases by a generation, and
+  the name kept pulling real work onto it. The reference now says to tier by
+  the version `agy models` shows, and points the second-strong-reviewer row
+  at Gemini Pro.
+
 ## [0.9.0] - 2026-08-24
 
 ### Added

playmaker_cli-0.9.0/README.md → playmaker_cli-0.11.0/PKG-INFO

@@ -1,3 +1,30 @@
+Metadata-Version: 2.5
+Name: playmaker-cli
+Version: 0.11.0
+Summary: Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity, Kimi 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
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Software Development
+Classifier: Topic :: Utilities
+Requires-Python: >=3.11
+Requires-Dist: rich>=13.7
+Requires-Dist: typer>=0.27.0
+Description-Content-Type: text/markdown
+
 # playmaker
 
 [![CI](https://github.com/vladsafedev/playmaker/actions/workflows/ci.yml/badge.svg)](https://github.com/vladsafedev/playmaker/actions/workflows/ci.yml)
@@ -5,7 +32,7 @@
 [![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 and opencode as parallel sub-agents from one terminal — and spend separate quotas instead of one.**
+**Run Claude Code, Codex, Antigravity, Kimi 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,
@@ -47,10 +74,11 @@ 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 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.
+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.
    `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
@@ -119,6 +147,10 @@ The other agents differ, because their CLIs do:
   { "permission": { "edit": "allow", "bash": "allow", "webfetch": "deny" } }
   ```
 
+- **kimi** has no permission flags at all in headless mode — `kimi -p` refuses
+  `--auto`, `--yolo` and `--plan`, and already runs with auto-approval, so
+  there is no read-only mode below the prompt.
+
 - **gemini** (legacy) runs with `--yolo`.
 
 ## Install
@@ -156,6 +188,7 @@ playmaker agents          # which agent CLIs are reachable
 | **Codex CLI** | `npm i -g @openai/codex` | the model roster depends on your plan; omit `--model` to use the account default |
 | **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` |
 | **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.
@@ -290,6 +323,7 @@ and locates the session file the tool writes locally. Empirically:
 | Codex | `~/.codex/sessions/<YYYY>/<MM>/<DD>/rollout-<ts>-<thread_id>.jsonl` |
 | 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) |
 | 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
@@ -364,14 +398,19 @@ stores, no scraping and no browser.
 ```console
 $ playmaker quotas --refresh
 Claude  Max 20x
-  Session     ████████████████░░░░ 80% left   resets in 3h 12m
-  Weekly      ███████████░░░░░░░░░ 55% left   resets in 4d 6h
-  Sonnet      ███████████████████░ 95% left   resets in 4d 6h
+  Session        ████████████████░░░░ 80% left   resets in 3h 12m
+  Weekly         ███████████░░░░░░░░░ 55% left   resets in 4d 6h
+  Weekly · Fable ██████░░░░░░░░░░░░░░ 28% left   resets in 4d 6h
+  Sonnet         ███████████████████░ 95% left   resets in 4d 6h
 
 Codex  Plus
   Session     ██████████████████░░ 90% left   resets in 1h 40m
   Weekly      █████████████░░░░░░░ 65% left   resets in 2d 9h
 
+Codex — Spark
+  Session     ████████████████████ 100% left  resets in 4h 59m
+  Weekly      ██░░░░░░░░░░░░░░░░░░ 8% left    resets in 5d 22h
+
 Antigravity (agy)
   Gemini 5h         ████████████████████ 100% left
   Gemini weekly     ███████████████████░ 95% left
@@ -384,12 +423,16 @@ Z.ai (GLM, via opencode)  Max
   MCP tools   ███████████████████░ 99% left   resets in 25d 11h
 ```
 
-The `Weekly` and `Sonnet` rows above are the point: they are **separate
-buckets**. So is every agy row, and so is the whole Z.ai block. Routing a
-subtask is choosing which of them to spend.
+The `Weekly`, `Weekly · Fable` and `Sonnet` rows above are the point: they are
+**separate buckets**. So is the `Codex — Spark` block, every agy row, and the
+whole Z.ai block. Routing a subtask is choosing which of them to spend.
 
 - **Claude** — OAuth usage API; token from the Claude Code Keychain entry.
-- **Codex** — ChatGPT `wham/usage` API; token from `~/.codex/auth.json`.
+  Model-scoped weekly buckets come from the usage API's `limits[]` array and
+  print as `Weekly · <model>`.
+- **Codex** — ChatGPT `wham/usage` API; token from `~/.codex/auth.json`. The
+  Spark model's own 5-hour and weekly windows come from
+  `additional_rate_limits[]` and print as their own `Codex — Spark` block.
 - **Antigravity** — prefers agy's **local daemon**
   (`RetrieveUserQuotaSummary` over its embedded gRPC-web endpoint), which is
   the only source for the full categorized breakdown above. Works whenever any

playmaker_cli-0.9.0/PKG-INFO → playmaker_cli-0.11.0/README.md

@@ -1,30 +1,3 @@
-Metadata-Version: 2.5
-Name: playmaker-cli
-Version: 0.9.0
-Summary: Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity 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,opencode,orchestration,subagents
-Classifier: Development Status :: 3 - Alpha
-Classifier: Environment :: Console
-Classifier: Intended Audience :: Developers
-Classifier: Operating System :: MacOS
-Classifier: Operating System :: POSIX :: Linux
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Software Development
-Classifier: Topic :: Utilities
-Requires-Python: >=3.11
-Requires-Dist: rich>=13.7
-Requires-Dist: typer>=0.27.0
-Description-Content-Type: text/markdown
-
 # playmaker
 
 [![CI](https://github.com/vladsafedev/playmaker/actions/workflows/ci.yml/badge.svg)](https://github.com/vladsafedev/playmaker/actions/workflows/ci.yml)
@@ -32,7 +5,7 @@ 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 and opencode as parallel sub-agents from one terminal — and spend separate quotas instead of one.**
+**Run Claude Code, Codex, Antigravity, Kimi 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,
@@ -74,10 +47,11 @@ 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 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.
+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.
    `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
@@ -146,6 +120,10 @@ The other agents differ, because their CLIs do:
   { "permission": { "edit": "allow", "bash": "allow", "webfetch": "deny" } }
   ```
 
+- **kimi** has no permission flags at all in headless mode — `kimi -p` refuses
+  `--auto`, `--yolo` and `--plan`, and already runs with auto-approval, so
+  there is no read-only mode below the prompt.
+
 - **gemini** (legacy) runs with `--yolo`.
 
 ## Install
@@ -183,6 +161,7 @@ playmaker agents          # which agent CLIs are reachable
 | **Codex CLI** | `npm i -g @openai/codex` | the model roster depends on your plan; omit `--model` to use the account default |
 | **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` |
 | **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.
@@ -317,6 +296,7 @@ and locates the session file the tool writes locally. Empirically:
 | Codex | `~/.codex/sessions/<YYYY>/<MM>/<DD>/rollout-<ts>-<thread_id>.jsonl` |
 | 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) |
 | 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
@@ -391,14 +371,19 @@ stores, no scraping and no browser.
 ```console
 $ playmaker quotas --refresh
 Claude  Max 20x
-  Session     ████████████████░░░░ 80% left   resets in 3h 12m
-  Weekly      ███████████░░░░░░░░░ 55% left   resets in 4d 6h
-  Sonnet      ███████████████████░ 95% left   resets in 4d 6h
+  Session        ████████████████░░░░ 80% left   resets in 3h 12m
+  Weekly         ███████████░░░░░░░░░ 55% left   resets in 4d 6h
+  Weekly · Fable ██████░░░░░░░░░░░░░░ 28% left   resets in 4d 6h
+  Sonnet         ███████████████████░ 95% left   resets in 4d 6h
 
 Codex  Plus
   Session     ██████████████████░░ 90% left   resets in 1h 40m
   Weekly      █████████████░░░░░░░ 65% left   resets in 2d 9h
 
+Codex — Spark
+  Session     ████████████████████ 100% left  resets in 4h 59m
+  Weekly      ██░░░░░░░░░░░░░░░░░░ 8% left    resets in 5d 22h
+
 Antigravity (agy)
   Gemini 5h         ████████████████████ 100% left
   Gemini weekly     ███████████████████░ 95% left
@@ -411,12 +396,16 @@ Z.ai (GLM, via opencode)  Max
   MCP tools   ███████████████████░ 99% left   resets in 25d 11h
 ```
 
-The `Weekly` and `Sonnet` rows above are the point: they are **separate
-buckets**. So is every agy row, and so is the whole Z.ai block. Routing a
-subtask is choosing which of them to spend.
+The `Weekly`, `Weekly · Fable` and `Sonnet` rows above are the point: they are
+**separate buckets**. So is the `Codex — Spark` block, every agy row, and the
+whole Z.ai block. Routing a subtask is choosing which of them to spend.
 
 - **Claude** — OAuth usage API; token from the Claude Code Keychain entry.
-- **Codex** — ChatGPT `wham/usage` API; token from `~/.codex/auth.json`.
+  Model-scoped weekly buckets come from the usage API's `limits[]` array and
+  print as `Weekly · <model>`.
+- **Codex** — ChatGPT `wham/usage` API; token from `~/.codex/auth.json`. The
+  Spark model's own 5-hour and weekly windows come from
+  `additional_rate_limits[]` and print as their own `Codex — Spark` block.
 - **Antigravity** — prefers agy's **local daemon**
   (`RetrieveUserQuotaSummary` over its embedded gRPC-web endpoint), which is
   the only source for the full categorized breakdown above. Works whenever any

{playmaker_cli-0.9.0 → playmaker_cli-0.11.0}/pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "playmaker-cli"
-version = "0.9.0"
-description = "Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity and opencode sub-agents in parallel."
+version = "0.11.0"
+description = "Playing-coach CLI for orchestrating Claude Code, Codex, Antigravity, Kimi Code and opencode sub-agents in parallel."
 readme = "README.md"
 requires-python = ">=3.11"
 license = "MIT"
@@ -19,6 +19,8 @@ keywords = [
     "codex",
     "antigravity",
     "gemini",
+    "kimi",
+    "kimi-code",
     "opencode",
     "glm",
     "subagents",

{playmaker_cli-0.9.0 → playmaker_cli-0.11.0}/skills/playmaker-coach/references/agent-gotchas.md

@@ -65,6 +65,22 @@ line from `agy models` / `opencode models` rather than typing it.
 - Neither trap applies to **review** dispatches, which write nothing — which makes opencode a
   perfectly good reviewer even where it is a shaky implementer.
 
+## kimi (Kimi Code CLI)
+
+- There is **no read-only mode below the prompt**: `-p` refuses `--auto`, `--yolo` and `--plan`
+  (exit 1) and already runs with auto-approval. Only dispatch work you would run unattended anyway.
+- The session id arrives **only in the trailing `session.resume_hint` line**, so `playmaker list`
+  shows the agent session late — do not conclude a dispatch failed just because the id has not
+  appeared yet.
+- Sessions are **per-cwd**: `kimi session list` from another directory shows nothing. Track the
+  session through playmaker, not through the CLI.
+- The stream carries **no token/cost fields** — there is nothing to budget against mid-run.
+- Exit codes: **exit 1 is non-retryable** (auth, quota, unknown model — "is not configured in
+  config.toml"); **exit 75 is retryable**. Fix the cause on 1, re-dispatch on 75.
+- K3 is **slow on real tickets** — never `--sync` a big WP; dispatch detached and poll.
+- 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`.
+
 ## Worktrees
 
 Parallel WPs that touch the same files collide. Give each its own git worktree and dispatch with

{playmaker_cli-0.9.0 → playmaker_cli-0.11.0}/skills/playmaker-coach/references/lanes.md

@@ -18,15 +18,20 @@ 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`.** 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`.** 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 mid tier. Its Claude runs on *Google's*
-     pool — top-tier Claude judgment that spends none of the Anthropic bucket. Note the internal
-     split: all Gemini models share one bucket, Claude and GPT-OSS share another.
+     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
+     releases by a generation (Claude 4.6 on agy while Claude 5 ships on Anthropic), so tier it by
+     the version `agy models` shows, never by the name. Note the internal split: all Gemini models
+     share one bucket, Claude and GPT-OSS share another.
    - **`opencode`** is the widest lane: one CLI over ~75 providers addressed as `provider/model` — a
      GLM coding plan, or a model running locally on this machine, which spends no subscription quota
      at all.
+   - **`kimi`** runs the Kimi Code CLI on its own subscription: senior tier (K3), native login, no
+     opencode.
 
 **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`
@@ -40,17 +45,17 @@ against the live roster, failing the dispatch on a stale name.
 | 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 top-tier Claude but the Anthropic bucket is precious | `dispatch agy --model <claude-opus-thinking>` | Claude quality on Google's pool |
+| needs a second strong reviewer without touching the Anthropic bucket | `dispatch agy --model <gemini-pro-high>` | near-senior judgment on an uncontended pool |
 | 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, agy's Claude-Opus
-  or Gemini-Pro-high, top-tier Codex).
+- **Architectural / spec judgment / cross-module integration** → top tier (coach, top-tier Codex,
+  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, agy's Claude-Sonnet / Gemini-Pro-low,
-  mid-tier Codex). Most delegated implementation lives here.
+  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.
 - **Recon, summarization, mechanical loops over many files, normalization** → cheap tier (Flash
   tiers, Haiku, fast Codex modes).
 

{playmaker_cli-0.9.0 → playmaker_cli-0.11.0}/skills/playmaker-coach/references/quotas.md

@@ -13,15 +13,17 @@ the plan instead of quoting the numbers.
 several tiers with independent buckets, and the whole point of pulling quotas is to push work
 *away from* the depleted bucket and *toward* the fresh one.
 
-- **Claude:** the top-tier weekly and the mid-tier weekly are **independent**. The coach and
-  in-session sub-agents spend the top one; the mid tier usually sits idle. Push mid-tier work there
-  instead of burning the scarce bucket.
+- **Claude:** the block shows the account-wide `Weekly` plus one `Weekly · <model>` row per
+  model-scoped bucket (e.g. `Weekly · Fable`). The model-scoped row is the one that empties first
+  during a long coach session — read it, not just `Weekly`.
 - **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.
-- **Codex:** top-tier versus lighter modes, where the account plan carries them.
+- **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.
 - **opencode:** the quota belongs to the *plan behind the provider*, not to the CLI — it appears
   under that provider (e.g. a GLM coding plan's session and weekly credit windows) and reads
   unsupported without a credential. A dispatch pointed at a **local** model spends nothing and never