Have the lead settle an issue's questions before a smaller-model agent builds it, two at a time

Five agents at once, each stopping on an undecided design question and restarting, spent a
week's allowance in a night. Also write down the lessons of feature 57: never land on a red
check, a new manifest word lands with the controller that reads it, and review the tree that
is pushed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

00-META/process/07-feature-branches.md

@@ -82,9 +82,24 @@ reviews and delivers at the end. The agents never push.
   runs the repository's tests and `merge-check.sh` in its own worktree, then fast-forwards the
   feature branch under a lock (`flock <feature worktree>.lock git -C <feature worktree> merge
   --ff-only <its branch>`). If another agent landed first, it merges again and repeats.
-- **At most five issues are being fixed at once.** When one lands, the next ready issue starts at
+- **The lead decides, a fixing agent builds.** Before an issue goes to an agent, the lead reads it and
+  the code it touches, finds every open question and settles it: decided on the issue, through the
+  knowledge base, or by the operator. An agent that meets an undecided design question stops, and its
+  whole run is spent again when it restarts. The issue the agent gets then says, in its own text:
+  - the repository and the files it changes, one repository where it can be (split an issue along
+    repository lines rather than send one agent through three);
+  - the decisions it builds with, quoted, never "read notes 8 to 12";
+  - the test to write first, which fails before the change;
+  - its done-when, in one sentence;
+  - what it must not touch, and what is landing beside it.
+  An agent that finds the code differs from its issue stops and reports; it does not design around it.
+- **Spend the operator's allowance on judgement.** Every agent the mesh runs draws on one weekly
+  allowance shared by every session. A fixing agent runs on the smaller model (Sonnet); the lead, the
+  independent reviews and the decision records run on the larger one, where judgement is the work.
+- **At most two issues are being fixed at once.** When one lands, the next ready issue starts at
   once; an issue is ready when every issue its `depends-on` links name has landed on the feature
-  branch.
+  branch and the lead has settled its open questions. (Five at once, with restarts, spent a week's
+  allowance in a night.)
 - **An issue partly done goes back to `open`** with a note naming the commits that landed and what
   is left, linked `depends-on` to what it waits for. An issue is never left in `fixing` while
   nobody works on it. A finished issue's agent is gone, so the lead takes it over in `fixing` (its
@@ -96,7 +111,16 @@ reviews and delivers at the end. The agents never push.
 - **Fetch by name.** In a shared clone a plain `git fetch` may update only `main`. Fetch the
   feature branch with an explicit refspec before branching from it or comparing against it, or an
   agent merges a stale copy.
-- **Report every ten minutes,** short, as a tree or a table: the issues done (of the total), each
+- **Never land on a red check.** Run the checks, read the result, then land in a separate step; a
+  command that checks and lands anyway is how a red branch lands. A manifest claiming a new seat or
+  a new manifest word lands only with, or after, the controller change that understands it.
+- **Review the tree that is pushed.** Before the local review, bring each feature branch up to the
+  current trunk (fetch by name, then merge or rebase), so the reviewed tree is the pushed tree.
+  Where an agent session pushes through the forge tool `gitea_commit` (it puts one commit on a branch
+  through the forge, as step 4's push), that commit is a new one on the forge's current base: the
+  reviewer confirms the forge commit's tree equals the reviewed one before posting its verdict on the
+  pull request.
+- **Report every ten minutes, and at once when something lands or needs the operator,** short, as a tree or a table: the issues done (of the total), each
   issue being fixed with its active time (minutes since its agent was sent, from a start time
   written down then, never guessed), the issues ready next, the ones waiting, and anything that
   needs the operator. Times are local and absolute.