review: verdicts record a disposition per lifted claim

The change the 2026-08-18 falsified-by efficacy review recommended
(agent_failure_modes.md item 6 Outcome): across 22 ship gates the ledger
could not distinguish a healthy adversarial claim pass from a skipped
one — both wrote a bare 'review CLEAN'. Now, when the ReviewSurface
lifts any 'claims to falsify', the verdict carries one disposition line
per claim (basis-cited / idle / FINDING unverified-claim), written by
the reviewer at verdict time; a bare CLEAN over a non-empty claims
surface is malformed evidence. An empty surface requires nothing, so
the 74-95% of ships that lift no claims gain no busywork.

Surfaces: faculty AGENTS.md step 2a + verdict mapping; _review.py
human-emit epilogue (printed only when claims lifted); AUTONOMY.md
autonomous-ship-gate review leg; ship_library reference.md gate
evidence line. No trigger-vocabulary change (measured as neither empty
nor saturated). 2 new pinning tests; suite 351 passed.

Co-Authored-By: Claude <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WH4NizvBK2jki2Uh5TMABh

Author: claude

AUTONOMY.md

@@ -158,7 +158,10 @@ applicability rule so "n/a" is a stated fact, never an assumption:
    feel stronger.
 3. **Review** — review-faculty verdict **CLEAN**
    (`agents/faculties/review/AGENTS.md`). FINDINGS → resolve and re-review, or
-   park to a human checkpoint; BLOCKED → park.
+   park to a human checkpoint; BLOCKED → park. When the surface lifted any
+   `claims to falsify`, CLEAN carries one disposition line per claim
+   (basis-cited / idle / finding — faculty AGENTS.md step 2a); a bare CLEAN
+   over a non-empty claims surface is malformed evidence, not CLEAN.
 4. **Heart** — verdict **GREEN** or **STALE**, or **YELLOW whose reason set is
    contained in the set the human acknowledged at launch**. Heart observes
    organism state, not the branch (the audit confirmed its legs never see

agents/faculties/review/AGENTS.md

@@ -62,11 +62,21 @@ Heart and the agent reasons over the verdict.
    category `unverified-claim` — the author asserted an effect they did not
    show. Scope it to genuinely load-bearing claims (an effect that, if wrong,
    ships a bug); an idle turn of phrase is not a finding — say so and move on,
-   so the pass does not decay into rote noise.
+   so the pass does not decay into rote noise. **Record a disposition per
+   claim**: the verdict carries one line per lifted claim —
+   `claim: "<lifted line>" → basis-cited: <the test/measurement/diff that shows it> | idle | FINDING (unverified-claim)`
+   — written by the reviewer at verdict time, never by the author. This is
+   what makes the pass auditable: the 2026-08-18 efficacy review
+   (`docs/agent_failure_modes.md` item 6 Outcome) found that across 22 ship
+   gates a healthy pass and a skipped one wrote the identical ledger row.
+   An empty surface requires nothing.
 3. Map the outcome to the verdict: any unresolved must-fix → **FINDINGS**
    (ranked list, file:line, failure scenario) — including any
    `unverified-claim` from step 2a; nothing → **CLEAN**; could not
-   complete steps 1–2 → **BLOCKED** (say why).
+   complete steps 1–2 → **BLOCKED** (say why). A CLEAN over a non-empty
+   `claims to falsify` surface **must** carry the step-2a disposition lines —
+   without them the evidence is malformed, not CLEAN (the ship-checkpoint
+   reader can see the omission; that is the reader-enforcement).
 
 ## Run
 

agents/faculties/review/_review.py

@@ -190,6 +190,12 @@ def emit_human(surfaces: list[dict]) -> None:
     print("file:line, failure scenario) | BLOCKED (could not review — say why).")
     print("A load-bearing claim above with no falsified-by basis in the branch is")
     print("a FINDING (unverified-claim) — see the faculty AGENTS.md.")
+    if any(s.get("claims_to_falsify") for s in surfaces):
+        print("Record ONE disposition line per lifted claim in the verdict:")
+        print('  claim: "<lifted line>" -> basis-cited: <test/measurement/diff>'
+              " | idle | FINDING (unverified-claim)")
+        print("A CLEAN over a non-empty claims surface without dispositions is")
+        print("malformed evidence, not CLEAN (faculty AGENTS.md step 2a).")
 
 
 def main(argv=None) -> int:

docs/agent_failure_modes.md

@@ -179,9 +179,11 @@ Each: catalogue entries caught → why it fires at the decisive moment → cost
    agent's verdict gains a one-line disposition per lifted claim
    (basis-cited / idle / finding) recorded in the ship evidence, so a rote
    pass becomes visible ledger drift per this doc's own ranking (detecting
-   beats reminding). Filed: PyAutoMind
-   `draft/feature/pyautobrain/review_claim_dispositions.md`; full numbers in
-   PyAutoMind `complete/2026/08/falsified-by-checkpoint-efficacy-review.md`.
+   beats reminding). Implemented 2026-08-18: faculty AGENTS.md step 2a + the
+   surface epilogue + the AUTONOMY.md review leg + the ship evidence format
+   (record: PyAutoMind `complete/2026/08/review-claim-dispositions.md`); full
+   numbers in PyAutoMind
+   `complete/2026/08/falsified-by-checkpoint-efficacy-review.md`.
 
 ## 6. The memory system, attacked honestly
 

skills/ship_library/reference.md

@@ -62,7 +62,8 @@ what the human validates instead of the pre-approval they didn't give:
 - Effective level: safe (header: <level>, cap: <work-type> → <cap>)
 - Plan: on the issue (#<n>), written at start, unmodified since
 - Gate: tests <pass counts / n-a + why> · smoke <result / n-a + why> ·
-  review CLEAN · Heart <GREEN | YELLOW within launch ack>
+  review CLEAN <+ one disposition per lifted claim, when the surface lifted
+  any — faculty AGENTS.md step 2a> · Heart <GREEN | YELLOW within launch ack>
 - [ ] Human: plan sound in hindsight?
 - [ ] Human: diff matches plan (no scope creep)?
 - [ ] Human: merge, amend, or reject — then log the outcome

tests/test_review_claims.py

@@ -58,3 +58,32 @@ def test_verified_and_safe_to_delete_are_claims():
     claims = load_bearing_claims(text)
     j = " ".join(claims).lower()
     assert "verified" in j and "safe to delete" in j and "zero diff" in j
+
+
+def test_emit_human_demands_dispositions_when_claims_lifted(capsys):
+    from _review import emit_human
+
+    surface = {
+        "repo": "PyAutoDemo", "path": "/tmp/x", "branch": "feature/x",
+        "base": "abc123def456", "commits_ahead": 1, "commits": ["abc fix"],
+        "shortstat": "1 file changed", "files": ["M\tf.py"],
+        "risk_flags": [], "claims_to_falsify": ["This change is a no-op for CI."],
+    }
+    emit_human([surface])
+    out = capsys.readouterr().out
+    assert "ONE disposition line per lifted claim" in out
+    assert "malformed evidence" in out
+
+
+def test_emit_human_no_disposition_demand_on_empty_surface(capsys):
+    from _review import emit_human
+
+    surface = {
+        "repo": "PyAutoDemo", "path": "/tmp/x", "branch": "feature/x",
+        "base": "abc123def456", "commits_ahead": 1, "commits": ["abc fix"],
+        "shortstat": "1 file changed", "files": ["M\tf.py"],
+        "risk_flags": [], "claims_to_falsify": [],
+    }
+    emit_human([surface])
+    out = capsys.readouterr().out
+    assert "disposition" not in out.lower()