fix(skill): self-review — operator detection и continuation framing

- Зачем:
  - Round 1 adversarial self-review нашёл 6 находок (3 high, 3 medium).
    Артефакт первой итерации содержал противоречия между SKILL и README,
    неточности про upstream-механики (Codex continuation, Agent Teams
    gating SendMessage), и оставлял undefined load-bearing branch
    "Operator available?". Без фиксов скилл вводил пользователей без
    Agent Teams в ступор при Round 2.
- Что:
  - SKILL Step 2: уточнено, что SendMessage gated на Agent Teams; Task
    spawn без Agent Teams one-shot; Codex поддерживает intra-session
    continuation.
  - SKILL Step 4: "REQUIRED SUB-SKILL ... if available" заменено на
    "Use ... when available" с явным fallback на inlined принципы.
  - SKILL Step 6: добавлена continuation-support table по хостам,
    восстановлена секция "Detecting an operator" с heuristic
    (interactive если direct human message + user-facing channel).
  - README: переписан Agent Teams блок под operator-gated модель; Codex
    section — корректное описание intra-session continuation через /agent.
  - EXPERIMENT.md: добавлен banner о предшествии редизайну и устаревших
    ссылках на adversarial-reviewer.md.
- Проверка:
  - Прогнать /claude-team-review в новой сессии с Agent Teams enabled
    (env var добавлен в ~/.claude/settings.json) — Round 2 для проверки
    continuation через SendMessage и operator-gating паттерна.

EXPERIMENT.md

@@ -1,5 +1,14 @@
 # Эксперимент: как две модели ревьюят один и тот же план
 
+> **Note (2026-05-15):** This write-up predates the cross-platform
+> redesign of `claude-team-review`. It refers to artifacts that no
+> longer exist in their original form — specifically `adversarial-
+> reviewer.md` (a Claude Code agent definition that has been replaced
+> by `reviewer-prompt.md`, a host-agnostic briefing template). The
+> historical descriptions below are preserved as-is for the experiment
+> record; for the current skill structure, see `SKILL.md` and
+> `reviewer-prompt.md`.
+
 Opus и GPT-5.4 получили одинаковый план и одинаковую adversarial
 установку. Нашли разные проблемы. Этот документ — полный ход
 эксперимента: от наивного запуска до контролируемого сравнения.

README.md

@@ -62,8 +62,10 @@ the same host as the lead.
 ```
 
 The lead tries to **continue the same reviewer** for re-review when the
-host supports it (cheaper — context is preserved). When continuation is
-unavailable (Codex, or Claude Code without Agent Teams), or when the
+host supports it (cheaper — context is preserved). Codex supports
+intra-session continuation natively; Claude Code requires Agent Teams
+(`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`) for the `SendMessage`-based
+continuation path. When continuation is unavailable, or when the
 previous reviewer is no longer reachable, the lead asks the operator
 before spawning a fresh subagent — full project re-read is expensive,
 and the operator may prefer to conclude the review unverified. Headless
@@ -129,8 +131,9 @@ ln -s "$(pwd)" ~/.claude/skills/claude-team-review
 Claude Code watches `~/.claude/skills/` for changes and will pick the
 skill up without a restart.
 
-**Optional — enable Agent Teams for cheaper re-review** (continuation
-between rounds instead of fresh-spawn). Add to your Claude Code settings:
+**Recommended — enable Agent Teams** for cheaper re-review. Continuation
+across rounds uses `SendMessage`, which is gated on Agent Teams. Add to
+your Claude Code settings:
 
 ```json
 {
@@ -140,9 +143,11 @@ between rounds instead of fresh-spawn). Add to your Claude Code settings:
 }
 ```
 
-The skill works fine without Agent Teams — it falls back to a fresh
-subagent each round, with the previous-rounds context block packed into
-the briefing.
+Without Agent Teams, the Task-tool spawn is one-shot — every Round 2+
+re-review goes through the operator-gated fresh-spawn path (the operator
+decides between spawning a fresh subagent that re-reads the project, or
+concluding the review unverified). Headless runs without an operator
+conclude as `NOT VERIFIED`.
 
 ### Codex
 
@@ -155,11 +160,12 @@ mkdir -p ~/.codex/skills
 ln -s "$(pwd)" ~/.codex/skills/claude-team-review
 ```
 
-Codex spawns subagents without context continuation across spawns. The
-skill treats every re-review on Codex as an operator-gated decision —
-the lead asks whether to spawn a fresh subagent (full project re-read,
-expensive) or conclude without verification. Continuation can be added
-later if Codex grows that feature.
+Codex supports intra-session continuation natively — the lead can send
+follow-up instructions to a running subagent thread (use `/agent` to
+switch between active threads). The skill uses this for cheap re-review.
+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
 

SKILL.md

@@ -63,11 +63,18 @@ message "Plan mode is active" → mode = `plan`, skip git.
 pass it the briefing assembled from `reviewer-prompt.md`.
 
 - **Claude Code:** Task tool with `general-purpose` type, OR — if Agent
-  Teams is enabled — spawn a teammate. Teammates support continuation
-  between rounds, which makes re-review cheaper. Both work; pick what's
-  available.
+  Teams is enabled — spawn a teammate. Note: **only Agent Teams supports
+  continuation between rounds** (via `SendMessage`, which is gated on
+  `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`). Without Agent Teams, the
+  Task tool spawn is one-shot — Round 2+ has to go through the operator-
+  gated fresh-spawn path in Step 6.
 - **Codex:** native subagent spawn (host orchestrates spawn/wait/consolidate).
-- **Other hosts:** equivalent subagent mechanism.
+  Codex supports intra-session continuation — the lead can send follow-up
+  instructions to a running subagent thread, and `/agent` switches between
+  active threads.
+- **Other hosts:** equivalent subagent mechanism. The skill works as long
+  as the host can spawn a subagent and (optionally) route follow-up
+  messages to it.
 
 The reviewer is a full agent session — it explores the repo, runs git
 commands, and reads files on its own. **Do not pre-collect diffs or file
@@ -120,9 +127,10 @@ This step exists because the reviewer may be technically wrong — and
 applying its findings blindly causes real damage (large structural edits
 based on cited issues that turn out to be feature requests, not bugs).
 
-**REQUIRED SUB-SKILL:** Use `superpowers:receiving-code-review` if it's
-available on the host. The key principles are inlined below for portability;
-the full skill has more depth.
+**Use `superpowers:receiving-code-review` when available** — it has the
+full discipline for this step. The key principles are inlined below as
+the always-available fallback (so the matrix step works on any host,
+even where Superpowers is not installed).
 
 ### Build the evaluation matrix
 
@@ -269,11 +277,20 @@ digraph re_review {
 }
 ```
 
+**Continuation support, by host (verify against current docs before
+relying on this):**
+
+| Host | Continuation | Mechanism |
+|---|---|---|
+| Claude Code + Agent Teams (`CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`) | yes | `SendMessage` to the teammate inbox |
+| Claude Code without Agent Teams | **no** — Task spawn is one-shot | — |
+| Codex | yes — intra-session | follow-up message to a running thread; `/agent` to switch |
+
 Two routes lead to the "ask operator" step:
-- The host has no continuation mechanism (e.g. Codex) — every round
-  after Round 1 lands here
+- The host has no continuation mechanism for our use case (Claude Code
+  without Agent Teams) — every round after Round 1 lands here
 - The host has continuation but the previous reviewer is no longer
-  reachable (process ended, inbox dead)
+  reachable (process ended, thread closed, inbox dead)
 
 **Detecting a dead reviewer (continuation-supporting hosts).** When the
 send call returns only a routing acknowledgment (e.g. `{"success": true,
@@ -282,6 +299,16 @@ the reviewer process has ended; the message went to a dead inbox. Do not
 wait. Treat the reviewer as unreachable, fall through to the operator
 question.
 
+**Detecting an operator.** Treat the run as **interactive** (operator
+available) only if both conditions hold:
+
+1. The current conversation has a direct human message — not just an
+   automated trigger, hook, scheduled run, or CI invocation
+2. The host exposes a user-facing channel to surface the question
+
+When in doubt, default to **presenting the choice** — pausing once is
+cheaper than concluding unverified by mistake.
+
 **Asking the operator.** Present the choice plainly:
 
 ```