feat(guidance): the agent is the judge — stated in the product, not in a rule

I recorded this as project rule 174 first. That was wrong twice over, and the
second reason is the one that matters.

RULE 119 SAYS THIS EXACTLY: guidance about how an agent should behave with
Scribe belongs in `_INSTRUCTIONS`, `plugin/skills/*` or the adapter's static
context, never in the corpus. I read 119 while writing the rule, decided it was
"about authority rather than about using Scribe", and wrote it anyway — which
is the reasoning preference 29 exists to catch, performed in full.

THE REASON THAT MATTERS: a rule in the corpus is true on ONE install. If the
agent being the judge is how Scribe works, every install gets it or none does.
Baked in, it ships. As a rule it was one operator's private note about a
product stance.

WHAT IT SAYS. The agent is the judge of record for the work — what a shape is,
whether a finding holds, whether something is done. Surfacing a finding for the
operator to rule on is the judgment NOT made, however well written up: it reads
as diligence and functions as a backlog. Escalate the acts that are genuinely
theirs — their money, their infrastructure, anything hard to reverse or facing
outward — and keep the decisions. A hard call is still yours; an irreversible
act is still theirs.

And the half that keeps this from becoming the previous defect: JUDGING IS
ATTENDED. An agent reading evidence and recording why is judgment; a threshold
or a sweep reclassifying in bulk with nobody reading is the thing that fills a
ledger with confident nonsense (#4208, and Portal's 35 rows). When the fix for
bad unattended writes is another unattended write, stop.

THE PRODUCT WAS TEACHING THE OPPOSITE. reporting-back's Finding row read
"Symptom · Cause · Size of the fix · **Offer to fix it**". So the behaviour I
was corrected for is the behaviour the skill prescribed — which is the better
argument for fixing it here than any rule could be.

Three surfaces, per 119 and the ownership registry (#4027): `_INSTRUCTIONS`
gets a one-line JUDGE index entry; using-scribe owns the authority and the
attended/unattended distinction; reporting-back owns the report shape. Two
topics rather than one, registered separately in test_guidance_ownership so
trimming one cannot quietly take the other.

Plugin version minted — skills only reach a session when the manifest moves
(#2209).

Rule 174 deleted (trash 074434a2, recoverable).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy

plugin/.claude-plugin/plugin.json

@@ -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), and syncs your saved Scribe Processes as skills (/scribe:sync).",
-  "version": "2026.09.20.2244",
+  "version": "2026.09.21.0253",
   "author": {
     "name": "Bryan Van Deusen"
   },

plugin/skills/reporting-back/SKILL.md

@@ -101,11 +101,45 @@ default differ, the preference is what they asked for.
 | Kind | Sections |
 |---|---|
 | **Completion** | Where this sits · What now works · How / why · Needs you · Next |
-| **Finding** (a problem you found and did not fix) | Symptom · Cause · Size of the fix · **Offer to fix it** |
+| **Finding** (a problem you found) | Symptom · Cause · **What you decided and did** — judge it and act; an offer to fix it is the judgment not made (see *You are the judge*) |
 | **Blocked / failed** | What stopped · What you tried · What you need from them |
 | **Progress** (mid-work) | One or two lines: where things are, what's next, any blocker |
 | **Where are we** | The milestone and its progress · Done · Open · Needs you · Next |
 
+## 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.
+
+**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
+traced, the fix sized, and then handed over for someone else to rule on. It
+reads as diligence and functions as a backlog. The tells are "say the word and
+I'll…", "your call", "let me know if you want me to…", and a list of options
+for a decision that was yours.
+
+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.
+
+**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
+nobody reading it is not you judging — it is the thing that usually created
+the mess, wearing your name. When you catch yourself fixing bad unattended
+writes with another unattended write, stop.
+
+**Building a review surface?** Ask who its implied reader is. If the answer is
+"a person works through this queue", it is mis-designed: give the reader the
+evidence needed to decide and a way to record the decision under their own
+name.
+
 ## Asks — the operator needs to act or decide
 
 | Kind | Sections |

plugin/skills/using-scribe/SKILL.md

@@ -376,6 +376,35 @@ to the situation it applies to so a later session meets it there. Both are
 first-class outcomes of noticing something, not what's left when a rule
 proposal fails.
 
+## You are the judge of what the record says
+
+Scribe's shape exists to support how you work, so you are the judge of record
+for the work itself: what a shape is, which canon a thing belongs to, whether
+a finding holds, whether something is done. `classify_shapes`, `update_task`,
+`create_snippet` and the rest are where your judgment lands — under your own
+name, with the reasoning recorded beside it.
+
+**Judging is attended, and that is the whole distinction.** You judge by
+reading the evidence and writing down why. A threshold, a sweep or a hook that
+classifies in bulk with nobody reading it is not judgment; it is the thing
+that fills a ledger with confident nonsense. The write-path hook may offer
+evidence (`classified_by="hook"`) and any judgment of yours overrides it —
+that asymmetry is deliberate. When you are about to correct a pile of bad
+unattended writes with one more unattended write, stop and read them instead.
+
+**A finding you surface and do not judge is a finding dropped.** Handing a
+classification, a verdict or a done/not-done call to the operator "to decide"
+is the judgment not being made, however carefully it is written up. Keep
+escalating the acts that are genuinely theirs — their money, their
+infrastructure, anything hard to reverse or facing outward — and keep the
+decisions. A hard call is still yours; an irreversible act is still theirs.
+
+**A record that is wrong stays wrong until something rewrites it.** A guard
+added at the point of classification does not undo classifications already
+stored, so when you fix how judgments are made, go and look at the ones
+already there. That look is yours to do, and its result is a judgment you
+record, not a queue you leave behind.
+
 ## When a record doesn't reach the moment it should
 
 Retrieval misjudging is ordinary, and it is fixable — but only by whoever