The cordis preset moved `bash-env`, the `subagents` registry, and its
spawn/fork backends into entry-local realms. A host row that injects a service
is the criterion for host-plane ownership: `apps/cli/src/web.ts` injects
`bash-env`, and `dsh-host-apiproxy` injects `subagents` to answer the
browser's cross-session queries, so both waited forever for a service only
sessions provided. A provider name also registers once, so the second session
would have collided regardless.
This layer introduces the preset, so it is where the plane belongs — a later
layer already corrected it, which left this layer and the docs one unmountable
on their own. The composition test stops disabling `api-gateway` with it: the
row whose pending injection names the break cannot be the row the test turns
off, so the boot audit now covers the whole host-plane injection graph.
Same required field as the standard preset: master made
`allowParallelInProgress` mandatory on dsh-tool-todo, and a preset that names
the row owns the choice.
A third built-in preset: the standard coding agent plus the self-referential
Cordis toolset, a persona that explains the two-plane split, and a skill
teaching composition authoring. It exists so a person can ask an agent to
author another agent.
The skill ships INSIDE the preset directory rather than in the user's skill
root, and the root is derived from the preset's own `baseUrl` — the loader
evaluates `!!js` with `with (ctx)`, so a composition can locate itself. A
preset is the unit that gets copied and edited, so its documentation should
travel with it.
The skill leads with the rule that actually bites: a row publishing a service
may not sit loose in a preset, whether a row publishes one is not visible from
its name (`tool-bash` provides `bashEnv`), and a consumer left outside its
provider's isolate group resolves the host registry and then contributes
nothing — the quietest failure this design has.
Writing the test surfaced a consequence worth stating: an entry-local realm
makes the service invisible to the agent's own scope too, not just to the host.
Only rows inside that group resolve it, which is precisely what makes
`tool-skill` this agent's own rather than a shared one. The test asserts what
is actually observable from outside instead of reaching for the isolated
service.
TRUST: `cordis_mount` evaluates model-written JavaScript against the live
runtime, and a composition this agent writes becomes a preset other sessions
mount. Both the preset header and the toolset's own documentation say to treat
this as shell access. The tools stay opt-in per session — a test pins that they
are absent from every other preset.
