docs(skills): repair five semantic minors in the axis-weighting/batch encoding (#14779)

Five in-place, zero-net-line corrections to the escalation decision frame's
four copies and the decision-analysis reference:

1. The class-2/3 live-presentation route in the internal PM skill restated a
   stale per-batch cap; it now points at the single home that rules the batch
   size, so the two cannot drift apart again.
2. The standing adjudication batch flow had no legal move for a final partial
   batch (an exact-size rule plus a drain-the-inbox rule forbade both
   presenting short and holding the remainder). The short last batch is now
   presented as-is.
3. Every weighting clause hard-coded "the other three", an axis-count minus one
   that the frame-sync gate's MENTION_PATTERNS structurally cannot see. All six
   sites are now count-free, so no derived count can go stale.
4. Published entry: the shrink-not-grow reading no longer cites an axis
   definition that does not state it, and the embedded dev template regains
   "and contract accretion" — the term the zero-pull argument turns on.
5. The lead-with-long-term duty is now unconditional in all five encodings;
   conflict-scoping is kept only on the cannot-outvote consequence.


Claude-Session: https://claude.ai/code/session_01LraLgQVGq8egUwfYZpbYt1

Co-authored-by: Claude <noreply@anthropic.com>

Author: os-litant

.claude/agents/os-dev.md

@@ -415,7 +415,7 @@ not decoration:**
   implementation-first 处置,已发布零消费的能力不因沉没成本获得豁免。
 
 Your recommendation must be justified on all four axes;长远合理性权重恒 ≥50%(2026-09-01
-裁「四维分析中，长期合理应该权重最高，至少50%」):推荐以它领起,另三轴合起来投不翻
+裁「四维分析中，长期合理应该权重最高，至少50%」):推荐以它领起,其余各轴合起来投不翻
 它,按本义读(缩小而非扩大特例/契约增生),⛔ 不为投机扩张背书;四轴冲突时推荐按拉动排
 序:实测拉动→长远,零拉动→不扩散,防错破平,安全与难逆恒人工(权重与序都只排推荐,⛔
 不授权、不移人工地板);权衡如实呈现交维护者拍板。`main` 在你脚下碎了、依赖未合并、CI

.claude/skills/pm-dispatch/SKILL.md

@@ -451,7 +451,7 @@ pin 前置等运维细则见 `references/seat-post-protocol.md`)。** 判据二
   裁决评论引本通道 + ①的权威,随后状态转移与现场裁过的卡同型(录裁 + 转 `pm:queue`,
   ⛔ 裁不派);每场召唤收尾呈一张**摘要表(卡 · 权威 · 方向)**供维护者追认,
   被推翻的行以该卡新裁决评论 + 状态转移执行。
-  二类(边界:带一个可报点)与三类(地板)照旧现场呈报,走每批 ≤5 与详细写法纪律。
+  二类(边界:带一个可报点)与三类(地板)照旧现场呈报,走常设决裁批流程与详细写法纪律。
 - **回翻条款**:代裁卡实施中发现契约终究要动 ⇒ dev 停手,
   卡回`needs-user-decision` —— 报告分叉,⛔ 永不静默重裁。
 - **请示纪律(维护者 2026-08-25:「不要不停的弹出来让我确认,很浪费时间」)**:①方向性授权
@@ -901,8 +901,8 @@ finding 定级换结果态,永不留挂)/ `Blocked-by:` 活性现验(合并一
 ⛔ 此序只排推荐:分歧块照旧升级,四棱同向置信门与代裁面不变,
 细则见 `references/decision-analysis.md`。
 **长远合理性权重恒 ≥50%**(维护者 2026-09-01 裁,逐
-字:「四维分析中，长期合理应该权重最高，至少50%」):四轴冲突时推荐以长远的读数领
-起,另三轴合起来投不翻它;权重按该轴本义读 —— 缩小而非扩大特例与契约增生 —— ⛔
+字:「四维分析中，长期合理应该权重最高，至少50%」):推荐以长远的读数领起,四轴冲突时
+其余各轴合起来投不翻它;权重按该轴本义读 —— 缩小而非扩大特例与契约增生 —— ⛔
 不据它为投机扩张背书。与分歧推荐序 compose 不取代:后者按拉动定指向,本条定下限。⛔ 权
 重是推荐规则不是授权规则:50% 不把人工地板的事变成可派发的事,安全/权限边界与破坏性
 难逆动作照旧恒交维护者。

.claude/skills/pm-dispatch/references/decision-analysis.md

@@ -10,7 +10,7 @@
 
 ## 常设决裁批流程(2026-08-26 裁;裁决原话与归席见主文件「升级与决策」)
 
-- 每批**恰好 5 张,呈完即停等回批**(2026-09-01
+- 每批**恰好 5 张(末批不足照呈),呈完即停等回批**(2026-09-01
   裁「每批5张详细解释，不是这样一堆列给我，这个也要写入skills」),⛔ 永不一条消息投多
   批;批序:在飞被阻塞 > 运营阻塞 > 用户可见 > 结构性;每卡 = 六项写法 + 四棱块;回批一行
   式「1A 2B …」,「X, 但…」= 附带条件随执行落地;裁后四件原子执行不再请示,一口气跑
@@ -48,7 +48,7 @@
 **四棱分歧推荐序**(2026-08-27「tong y 4」):②实测拉动⇒荐①长远终态;零拉动⇒荐④不扩散;
 ③破余下平局向响亮/结构;安全与难逆恒人工;⛔ 只排推荐,分歧照旧升级、代裁面不扩。
 **①长远权重下限**(2026-09-01 裁「四维分析中，长期合理应该权重最高，至少50%」):①恒
-≥50%,推荐以①领起,另三轴合起来投不翻①;①按本义读(缩小而非扩大特例/契约增生),⛔ 不
-据它为投机扩张背书;⛔ 只排推荐不授权 —— 50% 不把人工地板的事变成可派发的事。
+≥50%,推荐以①领起,其余各轴合起来投不翻①;①按本义读(缩小而非扩大特例/契约增生),⛔
+不据它为投机扩张背书;⛔ 只排推荐不授权 —— 50% 不把人工地板的事变成可派发的事。
 **应用仓推荐序特例**(2026-08-31 裁「既然是平台缺陷，就应该等待平台处理」):阻塞源是平台
 缺陷 ⇒ 恒荐等待,⛔ 不荐绕行(形状容错/复刻平台规则)、不荐劈半落地。

skills/objectstack-pm-dispatch/SKILL.md

@@ -550,7 +550,7 @@ real deployments use it today. "It reads like it would be useful" does not
 count. This axis **changes verdicts** rather than decorating them: two findings
 of identical technical shape can be ruled opposite ways on it alone — one
 declared surface retired for lack of pull, another kept and made to *reject
-loudly* because a real app proved the direction. On the other three axes they
+loudly* because a real app proved the direction. On the other axes they
 would read the same, and that would be the wrong answer.
 
 **Axis ② — long-term architectural soundness for *this* project.** Which option
@@ -589,11 +589,11 @@ the AI-safety axis breaks remaining ties toward the loud option; security and
 destructive actions stay with the human. The order ranks recommendations
 only — a split still escalates.
 
-**Axis ② carries the highest weight — at least 50%** when the axes conflict:
-lead with the long-term reading, and the other three together cannot outvote
-it. Read that weight through axis ②'s own definition — shrink special-cases
-and contract accretion, never grow them — so it never underwrites speculative
-expansion. It ranks recommendations only, never authority.
+**Axis ② carries the highest weight — at least 50%.** Lead with the long-term
+reading; when the axes conflict, the others together cannot outvote it. Read
+that weight as shrinking special-cases and contract accretion, never growing
+them — so it never underwrites speculative expansion. It ranks recommendations
+only, never authority.
 
 ### 9. Round report, then next round
 
@@ -656,10 +656,10 @@ trade-off and let the maintainer decide, ranking the recommendation pull-first
 (real pull → long-term shape; zero pull → non-proliferation; the AI-safety
 axis breaks ties; security/destructive → always the maintainer); the ranking
 orders recommendations only — a split still escalates. Long-term soundness
-carries the highest weight, at least 50%: lead with it, the other three
-together cannot outvote it, and read it as shrinking special-cases rather than
-as licence to expand speculatively; weight ranks recommendations only, never
-authority.
+carries the highest weight, at least 50%: lead with it, the others together
+cannot outvote it, and read it as shrinking special-cases and contract
+accretion rather than as licence to expand speculatively; weight ranks
+recommendations only, never authority.
 ```
 
 **Report contract.** The JSON in the template's final-message block is the