Fix the loop stalling after compaction, add an external registry

The compaction bug, which is the important one:

beta.2 taught the pruner to drop any assistant part whose reasoning item it had
removed. That was right about the 400 and wrong about everything else. On a
reasoning model every tool call carries a provider itemId, so past the threshold
the model could no longer see what it had already run, and re-ran the same tools
until maxSteps ended the turn. Reproduced at 12 model calls for a job needing 4,
with nothing but the user message reaching the wire.

The dependency is not the part, it is the itemId. A part carrying one is
serialised as `{ type: 'item_reference', id }`, a pointer to an item stored
provider-side that depends on its reasoning item. Without the itemId the same
content goes out inline and carries no dependency at all. Verified against the
provider's own serialiser: `text` with an itemId becomes item_reference, the
identical part without one becomes output_text.

So `dropOrphanedItems` becomes `detachOrphanedItems`: strip the itemId, keep the
content. Compaction may shorten the history; it must not blank it. The new test
asserts behaviour rather than shape — the loop must end because the model chose
to, and every call after the first must still carry the earlier exchange. A shape
assertion passed the whole time the model was losing its memory.

Registry, via `/registry [list|search|add|remove|installed]`:

Skills and plugins are treated differently on purpose. A skill is prompt text, so
installing one puts a stranger's words into the system prompt of every future
session in this project; the install shows the body first and the origin is
recorded, so /skills always says where an instruction came from. A plugin is a
JSON manifest of deny rules, evaluated by compiled code identical for every
install. Loading TypeScript from a URL is declined outright: a plugin that can
block tool calls could otherwise lie about blocking them.

Validated before anything is written: https only (file: and data: rejected), name
matched against ^[a-z0-9][a-z0-9-]*$ so it cannot escape its directory, size
caps on index and body, every regex compiled, pattern length capped since it runs
on every tool call, and the body's own name checked against the index. Installed
skills rank below your own, so an install can never shadow a skill you wrote.

Interface:
- Context is a percentage of the compaction threshold, amber from two thirds and
  red at 90. A turn about to lose history now says so beforehand.
- Aligned command menu and registry tables; /skills and /plugins name origins.

538 tests, up from 488. The registry is tested against a real local HTTP server,
and the guard is proven to refuse a .env write end to end rather than assumed to.

TODO.md

@@ -10,23 +10,15 @@ Longer-term direction lives in [ROADMAP.md](ROADMAP.md).
 
 ### Summarize the pruned span
 
-Compaction tells the model the history was pruned but not what was in it, so it can
-confidently contradict a decision it made forty messages ago.
+Compaction now keeps the model's memory of a turn, but it still tells the model nothing about
+the messages it dropped, so a decision from forty messages ago can be contradicted with
+confidence.
 
 - [ ] Summarize the discarded messages before dropping them
 - [ ] Inject the summary in place of the count
 - [ ] Budget it: a summary that grows with the session defeats the point
 - [ ] Test: a pruned decision is still recoverable from the summary
 
-### A cheaper model for subagents
-
-The subagent shares the parent's model. An `explore` run is search, not reasoning, and it
-currently pays the parent's per-token rate.
-
-- [ ] `subagentModel` in config, defaulting to the parent
-- [ ] `/cost` separates parent from subagent spend
-- [ ] Test: the subagent's calls go to the configured model, the parent's do not
-
 ### A spend ceiling
 
 A headless run that loops costs real money with nothing to stop it.
@@ -36,20 +28,28 @@ A headless run that loops costs real money with nothing to stop it.
 - [ ] Headless exits non-zero with the ceiling named, rather than stopping silently
 - [ ] Test: a session past its ceiling refuses the next turn and says why
 
+### A cheaper model for subagents
+
+The subagent shares the parent's model. An `explore` run is search, not reasoning, and it
+currently pays the parent's per-token rate.
+
+- [ ] `subagentModel` in config, defaulting to the parent
+- [ ] `/cost` separates parent from subagent spend
+- [ ] Test: the subagent's calls go to the configured model, the parent's do not
+
+### Hot-reload an installed entry
+
+`/registry add` writes the file and says to restart. The skill catalogue and the guard chain
+are both assembled at boot, so a mid-session install does nothing until then.
+
+- [ ] Rebuild the skill list and plugin host after an install or removal
+- [ ] Leave a turn in flight alone: its rules must not change underneath it
+- [ ] Test: a skill installed mid-session is callable in the next turn without a restart
+
 ---
 
 ## Next
 
-### Summarize the pruned span
-
-Compaction tells the model the history was pruned but not what was in it, so it can
-confidently contradict a decision it made forty messages ago.
-
-- [ ] Summarize the discarded messages before dropping them
-- [ ] Inject the summary in place of the count
-- [ ] Budget it: a summary that grows with the session defeats the point
-- [ ] Test: a pruned decision is still recoverable from the summary
-
 ### `web_fetch`
 
 - [ ] URL to markdown, size-capped
@@ -106,6 +106,11 @@ Not bugs exactly, but things that will bite someone.
   how far a half-run migration got.
 - **`@` completion lists files, not directories.** `@src/` narrows correctly, but you cannot
   complete to `src/` itself, because the walker only yields files.
+- **An installed skill is a stranger's words in your system prompt.** The install shows the
+  body first and `/skills` records the origin, but nothing re-checks it later: a registry that
+  changes a URL's contents affects the next install, not one already on disk.
+- **A registry index is trusted for its contents, not its authorship.** There are no
+  signatures. `registryUrl` is the whole trust decision.
 
 ---
 
@@ -127,3 +132,10 @@ Kept for one release, then deleted.
 - [x] `ctrl-c` kills the running command and keeps the turn. The kill takes the whole process
       tree: killing `cmd /c` alone left the real command holding both pipes open, so the
       interrupt appeared to do nothing for 19 seconds
+- [x] **Compaction no longer stops the loop.** Pruning used to drop any assistant part whose
+      reasoning item it removed, which on a reasoning model is every tool call. The model lost
+      its record of what it had run and re-ran it until the step limit. The repair strips the
+      provider `itemId` instead of the part, so the same content is sent inline
+- [x] `/registry`: browse, search, install, and remove external skills and plugins. Skills are
+      shown in full before install; plugins are a validated manifest of deny rules, never code
+- [x] Context shown as a percentage of the compaction threshold, amber at two thirds, red at 90