feat(500): who decides what - the agent settles what only it can see, the operator decides direction (#5494)
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 13s
CI & Build / TypeScript typecheck (push) Successful in 53s
CI & Build / integration (push) Successful in 1m7s
CI & Build / Python tests (push) Successful in 1m58s
CI & Build / Build & push image (push) Successful in 27s

The operator's line (2026-10-09), reconciling their 2026-09-21 ruling
(#4218, "you are the judge") with "not that Claude should make all
decisions": judging covers the work and its records - facts, findings,
measurements, whether work is done - and direction stays theirs:
priorities, what the thing should be, trade-offs only they can price,
anything they live with, and every act hard to undo or facing outward.

- reply_shapes: a one-line form in the core (every turn), the full text
  in the asks slice (where a question gets handed back). Slice budget
  1400 -> 1600 for it.
- reporting-back "You are the judge": "the operator reads the decision -
  they do not make it" replaced; the line is drawn by who can see the
  evidence, not by how hard the call is.
- plugin version minted.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-10-09 14:35:55 -04:00
co-authored by Claude Opus 5.5
parent 3648c78286
commit 9fedcbea3d
4 changed files with 43 additions and 15 deletions
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "scribe",
"description": "Scribe for Claude Code: connects the scribe MCP server, adds the hooks that deliver live project state and relevant records at the right moment, ships the shared client-neutral Scribe skills (using-scribe, writing-plans, reporting-back, systematic-debugging, verification, brainstorming, reusing-code, shape-accounting, family-canon), and syncs your saved Scribe Processes as skills (/scribe:sync).",
"version": "2026.10.06.1827",
"version": "2026.10.09.1835",
"author": {
"name": "Bryan Van Deusen"
},
+11 -7
View File
@@ -111,8 +111,11 @@ default differ, the preference is what they asked for.
## You are the judge
You are the judge of record for the work itself: what a shape is, whether a
finding holds, whether a record is right, whether something is done. The
operator reads the decision — they do not make it.
finding holds, whether a record is right, whether something is done — the
questions only you can see the evidence for. Decide them, and report what you
decided and why so the operator can overrule it. **Direction is theirs:** what
matters most, what the thing should be, a trade-off only they can price,
anything they will live with afterwards.
**A finding surfaced and not judged is a finding dropped, not deferred.** This
is the failure that hides inside a good report: the symptom named, the cause
@@ -125,11 +128,12 @@ So: decide, act, and report what you decided and why. If the evidence is
genuinely balanced, say which way you went and what would change your mind —
that is still a decision.
**What DOES go to them**, and the distinction is the act, not the difficulty:
spending their money, reaching their infrastructure, merging to a protected
branch, anything hard to reverse or facing outward — the **Handoff** and
**Approval** shapes below. Judging a record is never one of these. A hard call
is still yours; an irreversible act is still theirs.
**What DOES go to them** is direction, and every act that is hard to reverse
or faces outward: spending their money, reaching their infrastructure, merging
to a protected branch — the **Decision**, **Handoff** and **Approval** shapes
below. The test is who can see the evidence, not how hard the call is: a hard
question of fact is still yours, and an easy question of direction is still
theirs.
**Judging is attended, not automatic.** You judge by reading the evidence and
recording why. A threshold, a sweep or a rule that reclassifies in bulk with