docs(preset): let the preset directory be the roster

The README and the note each restated which presets ship. `code` was added a
layer later and neither followed, so both said three where the directory holds
four — the drift the review predicted, arriving on schedule. They point at
`apps/cli/config/agent-presets/` now: one directory per preset, and the
listing is the answer. The real-composition test still pins the exact set,
which is where a roster change should be felt.

.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md
-2026-08-03-per-session-agent-presets.md: b0f0de131b6f5051bb5a17a38636826ebd5771fd
-2026-08-03-per-session-agent-presets.zh.md: 9ca1374d1b4b43fda24fea81adf741d474dc0084
+2026-08-03-per-session-agent-presets.md: ba8476690f6b4b71e571ef7a19b61a2b31d00724
+2026-08-03-per-session-agent-presets.zh.md: fcca281068055d24475e3bbfdc959f9930815a30

.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.md

@@ -23,7 +23,7 @@ Composition splits into two planes, decided by what must be shared rather than b
 
 Model routing stays out of presets. `installAgentLlmTarget` is already the per-agent seam for provider, model, and reasoning effort, and an LLM adapter mounted inside a preset would never be resolved by `agent-loop`, which lives in the host plane.
 
-The deployment ships three presets — `standard` (the full coding agent), `minimal` (a two-tool benchmark surface), and `cordis` (the standard agent plus the self-referential toolset and a composition-authoring skill).
+The presets the deployment ships are the directories under `apps/cli/config/agent-presets/`; the roster is that listing, not a list restated here.
 
 Mounting is per-session by default. Measured cost for a twelve-row composition is ~3ms and ~600KB per session, so isolation is the cheaper default than any sharing scheme, and a preset authored by a user or by an agent then has the smallest possible blast radius. A preset that genuinely owns an expensive singleton opts into sharing with Cordis's own `isolate` vocabulary: a named realm label is process-global, so two subtrees naming the same label resolve one instance.
 

.agents/notes/implemented/architecture/2026-08-03-per-session-agent-presets.zh.md

@@ -23,7 +23,7 @@ Status: implemented
 
 模型路由不进 preset。`installAgentLlmTarget` 已经是 provider、model 与 reasoning effort 的按 agent 可替换点；而挂在 preset 内部的 LLM 适配器永远不会被 `agent-loop` 解析到，因为后者位于宿主平面。
 
-部署随附三个 preset —— `standard`（完整编码 agent）、`minimal`（两个工具的 benchmark 表层）与 `cordis`（标准 agent 加上自指工具集与一份组装创作 skill）。
+部署交付哪些 preset，取决于 `apps/cli/config/agent-presets/` 下有哪些目录；清单是那份目录列表，而不是在此另抄一份。
 
 挂载默认按会话进行。实测一份十二行组装每会话约 3ms、约 600KB，因此隔离比任何共享方案都更划算；而由用户或 agent 写出的 preset 也因此拥有尽可能小的影响面。确实自带昂贵单例的 preset，可以用 Cordis 自身的 `isolate` 词汇显式选择共享：命名 realm 的 label 是进程级全局的，因此两棵子树只要写同一个 label 就解析到同一个实例。
 

packages/preset/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/preset/README.md
-README.md: ca874398f06728af60999d11f03b67fb2f4b62e0
-README.zh.md: 2187bc78ed2ad2dffcc989c587992e3aeda3c5ea
+README.md: f6d42624eced995ad77eb7bf6c99d6f4e2a76af9
+README.zh.md: 3859fa9c928a1d5a9f6ed2b7aaca6666f1d12921

packages/preset/README.md

@@ -9,7 +9,7 @@ An **agent preset** is a directory holding one `agent.cordis.yml`. Mounting it u
 | `agent-presets/` | Preset vocabulary, filesystem discovery over trusted and user-authored roots, and the guarded per-agent mount | `ctx.agentPresets` |
 | `persona/` | The agent persona as a composable row, so a preset can change identity and not only tools | — |
 
-The deployment ships `standard` (the full coding agent), `minimal` (a two-tool benchmark surface), and `cordis` (the standard agent plus the self-referential toolset and a composition-authoring skill, so a person can ask an agent to author another agent).
+The presets the deployment ships live in [`apps/cli/config/agent-presets/`](../../apps/cli/config/agent-presets) — one directory each, and that directory listing is the roster. Naming them here too would be a second list to keep in step, and the first one to fall behind.
 
 The composition split this group assumes: registries and cross-session facilities are process singletons and stay in the host composition, while a preset carries what one agent contributes to them. A preset that names a row publishing a process-global service is rejected at mount rather than allowed to collide with the next session.
 

packages/preset/README.zh.md

@@ -9,7 +9,7 @@
 | `agent-presets/` | preset 词汇、在受信任目录与用户自建目录上的文件系统发现，以及带校验的按 agent 挂载 | `ctx.agentPresets` |
 | `persona/` | 把 agent 人设做成可组装的行，使 preset 不止能改工具、也能改身份 | — |
 
-部署随附三个 preset：`standard`（完整编码 agent）、`minimal`（两个工具的 benchmark 表层），以及 `cordis`（标准 agent 加上自指工具集与一份组装创作 skill，使人可以让 agent 去创作另一个 agent）。
+部署交付哪些 preset，看 [`apps/cli/config/agent-presets/`](../../apps/cli/config/agent-presets)——一个 preset 一个目录，那份目录列表就是清单。在这里再列一遍只会多出一份需要同步的名单，而且总是它先过时。
 
 本组假定的组装划分是：注册表与跨会话设施是进程单例，留在宿主组装中；preset 只承载单个 agent 对它们的贡献。若 preset 中某一行发布了进程级全局服务，挂载时即被拒绝，而不是留到与下一个会话相撞。