docs(skill): синхронизация README, фикс рекомендации Codex sandbox

- Зачем:
  - README отстал от SKILL.md после двух раундов self-review — формы инвокации, /agent, disallowedTools описаны неверно.
  - Рекомендация Codex sandbox_mode = "read-only" была ошибочной: она запрещает не только запись, но и exec — ревьюер не сможет запускать тесты, линтеры, git, MCP-запросы (а это основа верификации находок).
- Что:
  - README и SKILL.md: блок «Tool restrictions» переписан — briefing-only по умолчанию на обоих хостах; жёсткая sandbox упомянута как опция с явным trade-off (на Codex теряется exec).
  - README: Usage block обновлён — добавлены code-vs-plan и code-vs-plan <plan-path>, явное правило bare <file-path> → plan, xhigh как ортогональный effort flag.
  - README: новая короткая секция Language (ответы ревьюера на языке оператора, без флага).
  - README: bullet про structural-only паузы оператора в «What the lead does».
  - README: /agent в Codex section переформулирован как CLI оператора, а не tool лида.
- Проверка:
  - git diff main..HEAD -- README.md SKILL.md
  - Прочитать README целиком и убедиться, что нет противоречий с SKILL.md.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

README.md

@@ -81,6 +81,13 @@ runs without operator access conclude unverified.
 
 Mode is auto-detected from context, or you can force it with an argument.
 
+### Language
+
+The skill detects the operator's session language from recent
+conversation and instructs the reviewer to respond in it. No flag,
+no configuration. If you write to Claude in Russian, the reviewer's
+findings come back in Russian.
+
 ### What the reviewer can do
 
 - **Read** any file in the repository
@@ -89,9 +96,24 @@ Mode is auto-detected from context, or you can force it with an argument.
 - **Inspect git history** — blame, log, diff
 
 The reviewer **must not** create, edit, or delete project files. The
-briefing forbids it. If your host supports an enforced read-only sandbox
+briefing forbids it — that's the primary control on both hosts and the
-(Claude Code `disallowedTools`, Codex `sandbox_mode = "read-only"`), the
+default the skill ships with. The reason for keeping it briefing-only
-skill recommends applying it on top.
+is that the reviewer also needs to **run things** (tests, linters, git,
+MCP queries) to verify findings — hard sandboxes that block writes tend
+to block exec too, which would gut the reviewer.
+
+If you accept that trade-off and want enforced no-write on top, both
+hosts have an option:
+
+- **Claude Code:** define a custom subagent (e.g.
+  `~/.claude/agents/adversarial-reviewer.md`) with
+  `disallowedTools: Write, Edit` and dispatch that agent type. The
+  built-in `general-purpose` agent has no invocation-time
+  tool-restriction knob, so this path requires the custom definition.
+- **Codex:** `sandbox_mode = "read-only"` applies natively, but it also
+  disables shell exec for the subagent — the reviewer will not be able
+  to run tests or commands. Use only when you specifically want a
+  read-only audit and are willing to give up empirical verification.
 
 ### What the lead does (and does NOT do)
 
@@ -104,6 +126,12 @@ applied/re-scoped/rejected-with-reasoning format.
 number, make confident tool-mechanic claims without empirical testing,
 stay silent about rejections.
 
+**Pauses the operator** only on **structural** fixes — changes to the
+invocation grammar, output contract, workflow states, or the meaning of
+public options. Wording and factual fixes apply silently; the operator
+sees the full breakdown in the round summary. One pause per round at
+most, never one per finding.
+
 The skill explicitly invokes `superpowers:receiving-code-review` for the
 evaluation step (and inlines its key principles for portability).
 
@@ -160,30 +188,35 @@ mkdir -p ~/.codex/skills
 ln -s "$(pwd)" ~/.codex/skills/claude-team-review
 ```
 
-Codex supports intra-session continuation natively — the lead can send
+Codex supports intra-session continuation natively — the lead addresses
-follow-up instructions to a running subagent thread (use `/agent` to
+the running subagent thread by name in its next instruction and Codex's
-switch between active threads). The skill uses this for cheap re-review.
+orchestration routes the message there. The skill uses this for cheap
-When the previous subagent thread is no longer active, Round 2+ goes
+re-review. (As an operator, you can use the `/agent` CLI command to
-through the operator-gated fresh-spawn path (operator decides: spawn
+inspect or switch between active threads — it's a terminal tool, not
-fresh with a full project re-read, or conclude unverified).
+something the lead invokes.) When the previous subagent thread is no
+longer active, Round 2+ goes through the operator-gated fresh-spawn
+path (operator decides: spawn fresh with a full project re-read, or
+conclude unverified).
 
 ## Usage
 
 ```bash
-# Auto-detect what to review
+# Auto-detect what to review (from git state + conversation context)
 /claude-team-review
 
-# Review a plan
+# Force a specific mode
 /claude-team-review plan
-
-# Review code changes
 /claude-team-review code
+/claude-team-review code-vs-plan                    # uses the plan most recently shown in the conversation
+/claude-team-review code-vs-plan path/to/plan.md    # explicit plan file
 
-# Review a specific file
+# A bare file path is treated as a plan to review
 /claude-team-review path/to/plan.md
 
-# Use maximum reasoning effort for the reviewer
+# xhigh is an effort flag, orthogonal to mode — combine with any of the above
 /claude-team-review xhigh
+/claude-team-review plan xhigh
+/claude-team-review code-vs-plan path/to/plan.md xhigh
 ```
 
 ## Files in this skill

SKILL.md

@@ -145,19 +145,25 @@ prose, reasoning, descriptions, recommendations — in
 The verbatim reply from the reviewer is shown to the operator as-is — do
 not translate it back; it should already be in the operator's language.
 
-**Tool restrictions:** the briefing's "must NOT modify files" rule is
+**Tool restrictions.** The briefing's "must NOT modify files" rule is
-the primary control on the read path. The built-in `general-purpose`
+the primary control on both hosts and the default. **Do not reach for
-subagent on Claude Code has no tool-restriction knob the lead can pass
+host-level sandboxes by reflex** — the reviewer also needs to run
-at invocation time, so the briefing rule is the only control there. If
+things (tests, linters, git, MCP queries) to verify findings, and
-you want enforced sandboxing on top, that requires going off the
+hard sandboxes that block writes typically block exec too, which guts
-default path:
+the reviewer.
+
+If the operator explicitly wants enforced no-write on top and accepts
+the trade-off, both hosts have an option:
 
 - **Claude Code:** define a custom subagent (e.g.
   `~/.claude/agents/adversarial-reviewer.md`) with frontmatter
   `disallowedTools: Write, Edit`, and dispatch that agent type instead
-  of `general-purpose`.
+  of `general-purpose`. The built-in `general-purpose` has no
-- **Codex:** the host's `sandbox_mode = "read-only"` applies to the
+  invocation-time tool-restriction knob.
-  spawned subagent natively.
+- **Codex:** `sandbox_mode = "read-only"` applies natively, **but also
+  disables shell exec for the subagent** — the reviewer will not be
+  able to run tests or commands. Use only when the operator wants a
+  read-only audit and is willing to give up empirical verification.
 
 ---