claude-dev-env 2.16.0 → 2.18.0

package/.agents/skills-archived/AGENTS.md

@@ -0,0 +1,45 @@
+# skills-archived
+
+Versioned archive of retired Claude Code skills. These trees stay in the repository for reference and history but are not shipped to users.
+
+## Layout
+
+Each subdirectory is one retired skill with its historical `SKILL.md`, reference docs, scripts, and tests. Live runtime helpers for convergence and Codex review live under `packages/claude-dev-env/_shared/pr-loop/scripts/` — not in these trees.
+
+## Installer behavior
+
+`bin/install.mjs` copies skills only from `.agents/skills/`. This directory is outside that path and outside the `.claude/skills` lookup pointer, so archived skills never install to `~/.agents/skills/`.
+
+`bin/ever-shipped-skills.mjs` still lists retired skill names so a full install prunes stale copies from prior releases.
+
+## Archived skills
+
+| Skill | Role |
+|---|---|
+| `anthropic-plan` | Source-grounded plan packet workflow |
+| `auditing-claude-config` | Claude Code startup instruction audit |
+| `beat-sheet` | Single-line beat formatting |
+| `bugteam` | Open PR audit-fix loop |
+| `closeout` | Session obstacle harvest to GitHub issues |
+| `codex-review` | Local Codex PR reviewer (runtime scripts in `_shared`) |
+| `comments` | PR review comment guide |
+| `condensing-instructions` | Instruction slimming for Claude 5 |
+| `copilot-finding-triage` | Copilot gate finding tiering |
+| `copilot-review` | Copilot reviewer babysitter |
+| `descriptions` | PR description guide |
+| `emergencies` | Emergency change guide |
+| `grokify` | Grok Build handoff prompt |
+| `plan-to-pr` | Plan packet to PR workflow |
+| `pr-converge` | Paced PR convergence loop (runtime scripts in `_shared`) |
+| `pr-fix-protocol` | Reviewer finding fix protocol |
+| `pr-loop-cloud-transport` | Cloud session gh-to-MCP transport |
+| `pr-loop-lifecycle` | PR-loop open and close |
+| `recall` | Obsidian vault recall |
+| `release-notes-html` | Session release-notes HTML page |
+| `remember` | Obsidian vault remember |
+| `reviewer-gates` | External reviewer availability gates |
+| `reviews` | Code review guide |
+| `show` | Inline visual explanations |
+| `split-pr` | PR split analyzer |
+
+Prompt-generator dependency skills (`agent-prompt`, `pmin`, `pmax`, `pmid`, `prompt-generator`) shipped via the `@jl-cmd/prompt-generator` npm package and never had source trees in this repository.

package/.agents/{skills → skills-archived}/anthropic-plan/AGENTS.md

@@ -19,7 +19,7 @@ Creates a repo-local plan packet under `docs/plans/<slug>/` by running the `plan
 | `SKILL.md` | Entry point. Full planning protocol, workflow contract, packet shape, and validation rules. |
 | `workflow/plan-packet.mjs` | Main workflow script. Reads repo context, writes the packet, runs the validator, spawns `plan-packet-validator`, runs the reuse audit, builds the visual HTML, and returns the packet path. |
 | `workflow/plan-packet.contract.test.mjs` | Contract tests for the workflow script. |
-| `packages/claude-dev-env/.agents/skills/anthropic-plan/scripts/validate_packet.py` | Deterministic validator: checks required files, open questions, source-map strength, TDD coverage, and `packet.json` consistency. Exits with code 2 on failure. |
+| `packages/claude-dev-env/.agents/skills-archived/anthropic-plan/scripts/validate_packet.py` | Deterministic validator: checks required files, open questions, source-map strength, TDD coverage, and `packet.json` consistency. Exits with code 2 on failure. |
 | `templates/visual-plan.template.html` | Template for the single-file offline visual HTML the workflow builds after validation. |
 
 ## Entry point

package/.agents/{skills → skills-archived}/bugteam/scripts/reflow_skill_md.py

@@ -1,16 +1,16 @@
-"""Reflow packages/claude-dev-env/.agents/skills/bugteam/SKILL.md to 80 columns.
+"""Reflow packages/claude-dev-env/.agents/skills-archived/bugteam/SKILL.md to 80 columns.
 
 Merge soft line breaks outside fenced blocks (space join; URL path fragments
 joined without a space only inside unfinished markdown link targets), then
 wrap with textwrap. Preserves fenced blocks verbatim.
 
-Same algorithm as ``packages/claude-dev-env/.agents/skills/pr-converge/scripts/reflow_skill_md.py``
+Same algorithm as ``packages/claude-dev-env/.agents/skills-archived/pr-converge/scripts/reflow_skill_md.py``
 from https://github.com/jl-cmd/claude-dev-env/pull/349 (branch
 ``cursor/pr-converge-skill-line-wrap-ecd1``); ``SKILL_PATH`` points at bugteam
 ``SKILL.md``. Link reference definitions (``[id]: url``) are treated as logical
 line starts so they are not merged with prior paragraphs.
 
-Run: python3 packages/claude-dev-env/.agents/skills/bugteam/scripts/reflow_skill_md.py
+Run: python3 packages/claude-dev-env/.agents/skills-archived/bugteam/scripts/reflow_skill_md.py
 """
 
 from __future__ import annotations

package/.agents/{skills → skills-archived}/codex-review/test_skill_scaffold.py

@@ -15,7 +15,7 @@ PACKAGE_ROOT = SKILL_DIRECTORY.parents[2]
 PYPROJECT_PATH = PACKAGE_ROOT / "pyproject.toml"
 EVER_SHIPPED_SKILLS_PATH = PACKAGE_ROOT / "bin" / "ever-shipped-skills.mjs"
 CONSTANTS_PACKAGE_NAME = "codex_review_scripts_constants"
-CONSTANTS_PACKAGE_DIR = ".agents/skills/codex-review/scripts/codex_review_scripts_constants"
+CONSTANTS_PACKAGE_DIR = "_shared/pr-loop/scripts/codex_review_scripts_constants"
 SKILL_NAME = "codex-review"
 MAXIMUM_SKILL_BODY_LINE_COUNT = 500
 

package/.agents/{skills → skills-archived}/copilot-finding-triage/SKILL.md

@@ -124,7 +124,7 @@ present when the caller has not selected a pacer):
 - **Portable pacer** (`pacer=portable`, or no durable wake): do not call
   `ScheduleWakeup` or `send_later`. Hold with an in-session deadline poll, or
   write handoff and stop, per
-  [`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md).
+  [`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md).
   Callers may override this step after the ntfy page and apply their own
   portable hold.
 

package/.agents/{skills → skills-archived}/pr-converge/SKILL.md

@@ -15,7 +15,7 @@ Bugbot and Copilot run as terminal confirmation gates, until all are clean on
 the same `HEAD` and mergeable. On `pacer=schedule_wakeup`, one tick runs per
 invocation and the next tick is scheduled. On `pacer=portable`, ticks run
 continuously in-session (see
-[`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md)).
+[`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md)).
 
 ## Transport check (before any GitHub step)
 
@@ -50,7 +50,7 @@ python "$HOME/.claude/skills/_shared/pr-loop/scripts/select_converge_pacer.py" \
 - `pacer=schedule_wakeup` — native tick pacing via `ScheduleWakeup` (see
   [`workflows/schedule-wakeup-loop.md`](workflows/schedule-wakeup-loop.md)).
 - `pacer=portable` — continuous in-session driver on
-  [`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md).
+  [`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md).
   **Do not abort** because `ScheduleWakeup` is missing.
 
 ### Worktree isolation
@@ -62,7 +62,7 @@ working directory contains `.claude/worktrees/`. If `EnterWorktree` fails,
 report the failure and stop.
 
 When `EnterWorktree` is absent, isolate with git worktree machinery per
-[`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md)
+[`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md)
 § Isolation and worktree, then run strict
 `preflight_worktree.py` for the PR's owner/repo. Fail closed only when the
 checkout is not the PR's repo on the PR head ref.
@@ -110,7 +110,7 @@ auto-fix; code-concern verify then confirmed / refuted / inconclusive).
     `send_later` 45-minute hold across ticks; persist the deadline so each tick
     reads it on entry).
   - **`pacer=portable`** — in-session deadline poll or handoff per
-    [`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md);
+    [`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md);
     never `ScheduleWakeup` or `send_later`.
   Act on the user's direction inside the window; on timeout, teardown and report
   the findings un-reviewed.
@@ -444,7 +444,7 @@ round as converged. This rule holds every tick, every loop, every PR.
 | `copilot-finding-triage` | Tier, verify, and route each Copilot finding |
 | `bugteam` | Full-diff bug audit in Step 6 (Skill invocation mandatory) |
 | `pr-loop-cloud-transport` | When `gh` is unavailable or unauthenticated |
-| [`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md) | Continuous in-session pacer when `ScheduleWakeup` is absent |
+| [`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md) | Continuous in-session pacer when `ScheduleWakeup` is absent |
 | [`../../_shared/pr-loop/fix-protocol.md`](../../_shared/pr-loop/fix-protocol.md) | Shared 13-step fix sequence (TDD, commit, push, reply, resolve) |
 | [`reference/fix-protocol.md`](reference/fix-protocol.md) | pr-converge deltas on the shared fix protocol |
 
@@ -466,4 +466,4 @@ round as converged. This rule holds every tick, every loop, every PR.
 | `reference/obstacles/` | Per-obstacle fix runbooks |
 | `scripts/` | Convergence helpers, Copilot fetch, fix-reply poster, tests |
 | `workflows/schedule-wakeup-loop.md` | ScheduleWakeup pacing (`pacer=schedule_wakeup`) |
-| [`../_shared/pr-loop/portable-driver.md`](../_shared/pr-loop/portable-driver.md) | Portable continuous pacer (`pacer=portable`) |
+| [`../../skills/_shared/pr-loop/portable-driver.md`](../../skills/_shared/pr-loop/portable-driver.md) | Portable continuous pacer (`pacer=portable`) |

package/.agents/{skills → skills-archived}/pr-converge/pr_converge_skill_constants/AGENTS.md

@@ -23,4 +23,4 @@ Importable Python constants module for the `pr-converge` skill. Script-specific
 ## Conventions
 
 - All path templates use `str.format(**kwargs)` with keys `owner`, `repo`, `number`.
-- `packages/claude-dev-env/.agents/skills/pr-converge/scripts/pr_converge_scripts_constants/pr_converge_constants.py` re-exports everything here via `from pr_converge_skill_constants.constants import ...` so scripts can import from either location.
+- `packages/claude-dev-env/.agents/skills-archived/pr-converge/scripts/pr_converge_scripts_constants/pr_converge_constants.py` re-exports everything here via `from pr_converge_skill_constants.constants import ...` so scripts can import from either location.

package/.agents/{skills → skills-archived}/pr-converge/pr_converge_skill_constants/constants.py

@@ -2,7 +2,7 @@
 
 All runtime and API constants live here. Script-specific constants
 (CLI args, markdown patterns, reflow settings) stay in
-``packages/claude-dev-env/.agents/skills/pr-converge/scripts/pr_converge_scripts_constants/pr_converge_constants.py``,
+``packages/claude-dev-env/.agents/skills-archived/pr-converge/scripts/pr_converge_scripts_constants/pr_converge_constants.py``,
 which imports from here.
 """
 

package/.agents/{skills → skills-archived}/pr-converge/reference/multi-pr-orchestration.md

@@ -216,7 +216,7 @@ When bugfix (clean-coder) subagent completes after push:
 5. Advance the pacer: on `pacer=schedule_wakeup`, call `ScheduleWakeup`
    with the appropriate delay; on `pacer=portable`, continue or poll
    in-session per
-   [`../../_shared/pr-loop/portable-driver.md`](../../_shared/pr-loop/portable-driver.md)
+   [`../../../skills/_shared/pr-loop/portable-driver.md`](../../../skills/_shared/pr-loop/portable-driver.md)
    (no `ScheduleWakeup`).
 6. Nothing else.
 

package/.agents/{skills → skills-archived}/pr-converge/reference/per-tick.md

@@ -19,7 +19,7 @@ Run every tick in the parent harness session. Pacing depends on the selected
 pacer from pre-flight (`select_converge_pacer.py`):
 
 - `schedule_wakeup` — [`../workflows/schedule-wakeup-loop.md`](../workflows/schedule-wakeup-loop.md)
-- `portable` — [`../../_shared/pr-loop/portable-driver.md`](../../_shared/pr-loop/portable-driver.md)
+- `portable` — [`../../../skills/_shared/pr-loop/portable-driver.md`](../../../skills/_shared/pr-loop/portable-driver.md)
 
 See [Pacing workflow](#pacing-workflow).
 
@@ -42,7 +42,7 @@ When `pacer=schedule_wakeup`, read
 [`../workflows/schedule-wakeup-loop.md`](../workflows/schedule-wakeup-loop.md)
 (installed copy under `$HOME/.claude/skills/pr-converge/workflows/`) before
 Step 4. When `pacer=portable`, read
-[`../../_shared/pr-loop/portable-driver.md`](../../_shared/pr-loop/portable-driver.md)
+[`../../../skills/_shared/pr-loop/portable-driver.md`](../../../skills/_shared/pr-loop/portable-driver.md)
 and skip `ScheduleWakeup` calls.
 
 - **`/pr-converge`** (default): loops until convergence. After each tick
@@ -546,7 +546,7 @@ Do **not** call `ScheduleWakeup`. After writing state and handoff:
   `/pr-converge <PR URL>` and the persisted phase.
 
 Full portable rules:
-[`../../_shared/pr-loop/portable-driver.md`](../../_shared/pr-loop/portable-driver.md).
+[`../../../skills/_shared/pr-loop/portable-driver.md`](../../../skills/_shared/pr-loop/portable-driver.md).
 
 ## Bugteam execution
 

package/.agents/{skills → skills-archived}/pr-converge/scripts/reflow_skill_md.py

@@ -1,10 +1,10 @@
-"""Reflow packages/claude-dev-env/.agents/skills/pr-converge/SKILL.md to 80 columns.
+"""Reflow packages/claude-dev-env/.agents/skills-archived/pr-converge/SKILL.md to 80 columns.
 
 Merge soft line breaks outside fenced blocks (space join; URL path fragments
 joined without a space only inside unfinished markdown link targets), then
 wrap with textwrap. Preserves fenced blocks verbatim.
 
-Run: python3 packages/claude-dev-env/.agents/skills/pr-converge/scripts/reflow_skill_md.py
+Run: python3 packages/claude-dev-env/.agents/skills-archived/pr-converge/scripts/reflow_skill_md.py
 """
 
 from __future__ import annotations

package/.agents/{skills → skills-archived}/pr-converge/test_portable_pacer_gate.py

@@ -9,7 +9,11 @@ SKILL_ROOT = Path(__file__).resolve().parent
 SKILL_MARKDOWN_PATH = SKILL_ROOT / "SKILL.md"
 PER_TICK_MARKDOWN_PATH = SKILL_ROOT / "reference" / "per-tick.md"
 PORTABLE_DRIVER_PATH = (
-    SKILL_ROOT.parent / "_shared" / "pr-loop" / "portable-driver.md"
+    SKILL_ROOT.parents[1]
+    / "skills"
+    / "_shared"
+    / "pr-loop"
+    / "portable-driver.md"
 )
 
 SELECT_CONVERGE_PACER_SCRIPT = "select_converge_pacer.py"
@@ -18,7 +22,7 @@ PACER_SCHEDULE_WAKEUP_TOKEN = "pacer=schedule_wakeup"
 ABORT_ONLY_PHRASE = "pr-converge requires ScheduleWakeup; aborting"
 PORTABLE_DRIVER_DOC = "portable-driver.md"
 PORTABLE_DRIVER_LINK_PATTERN = re.compile(
-    r"\((?P<relative>(?:\.\./)+_shared/pr-loop/portable-driver\.md)\)"
+    r"\((?P<relative>(?:\.\./)+skills/_shared/pr-loop/portable-driver\.md)\)"
 )
 
 

package/.agents/{skills → skills-archived}/pr-converge/workflows/schedule-wakeup-loop.md

@@ -2,7 +2,7 @@
 
 Load this document when pre-flight selects `pacer=schedule_wakeup`. When
 `pacer=portable`, use
-[`../../_shared/pr-loop/portable-driver.md`](../../_shared/pr-loop/portable-driver.md)
+[`../../../skills/_shared/pr-loop/portable-driver.md`](../../../skills/_shared/pr-loop/portable-driver.md)
 instead. Shared bugbot / bugteam / Fix protocol steps stay in the main
 `SKILL.md`.
 

package/.agents/{skills → skills-archived}/split-pr/reference/proposal-format.md

@@ -12,4 +12,4 @@ Each slice carries `id`, `title` (exactly one conventional prefix), `layer`
 (one of `config` / `backend` / `frontend` / `tests` / `docs` / `other`), and
 `all_paths`. Every path in `all_changed_paths` is assigned to exactly one
 slice. Titles are normalized with `split_pr_title.normalize_split_title`.
-Layer tokens follow `ALL_LAYER_ORDER` in `packages/claude-dev-env/.agents/skills/split-pr/scripts/config/plan_constants.py`.
+Layer tokens follow `ALL_LAYER_ORDER` in `packages/claude-dev-env/.agents/skills-archived/split-pr/scripts/config/plan_constants.py`.

package/AGENTS.md

@@ -1,14 +1,23 @@
 # Scope
 
-  Every rule in this file governs all text everywhere: chat replies, tool-call sentences, plans, questions you ask, code, code comments, test names, commit subjects, pull request and issue bodies, documentation, and every file you write. No rule stops at the edge of a chat message.
+## User-facing language hierarchy
 
-  A rule that names a form in order to forbid it passes its own check, and so does a two-column table that teaches a rewrite.
+ELI5 owns beginner framing and beginner-friendly presentation, large visuals, minimal text, one stable self-contained HTML artifact, update-in-place continuity, and sharing when a response needs that presentation.
+
+`rules/asd-ste100-language.md` owns sentence-level word choice, grammar, tone, punctuation, exact labels, and prose form in every user-facing response and every ELI5 page.
+
+Named capability rules own evidence, questions, current-state documentation, completion, code documentation, durable artifacts, and runtime enforcement. They apply ASD sentence rules and use ELI5 presentation when their user-facing output needs that envelope.
+
+Raw tool output, machine payloads, code, and native repository artifacts keep their required formats. Their user-visible explanations follow the ASD rule.
+
+A responsible human verifies technical accuracy, terminology, safety, confidentiality, and intended meaning.
 
 Ask when ambiguity materially changes scope or implementation. Collect credentials through secure UI only; never request secrets in chat.
 
 ## Documentation
 
-Describe only the current system state. Keep documentation self-contained and free of historical, transitional, conversational, or version-transition language. Never use negative prose or antipatterns. Always state what to do, specifically.
+Describe the current system state. Keep documentation self-contained. Apply `rules/asd-ste100-language.md` for sentence-level prose.
+
 Code and tests
 
 Tests must exercise real behavior, real data, and production paths. Test theater is forbidden.
@@ -18,6 +27,8 @@ For multi-step code tasks:
 Coders consult a warm session-advisor when blocked (Sol xHigh).
 Repair reported findings when that review mode is selected.
 
+Use `~/.claude/agents/session-advisor.md` for advisor selection and consultation protocol.
+
 Research and delegation
 Delegate fact extraction when multiple files or search patterns are required. Request precise file-and-line answers.
 
@@ -31,79 +42,42 @@ Scope every es.exe search.
 
 Never scan an entire drive or network share.
 
+Use `~/.claude/skills/everything-search/SKILL.md` for scoped filesystem searches that require Everything.
+
 Task tracking
 Track every task using `update_plan`.
 
 ## Definitions
 Warm agent: Any agent who has acted within the past 30 minutes.
 
-  # Response and working style
-
-  Mid-run and closing narration follow `rules/opus5-communication-contract.md` (`opus5-communication-contract-v1`): first progress update is one sentence; later updates only for important discoveries or direction changes; the final starts with the outcome.
+# Response and working style
 
-  Keep responses focused, brief, and concise. Keep disclaimers and caveats short, and spend most of the response on the main answer. When asked to explain something, give a high-level summary unless an in-depth explanation is specifically requested.
+ELI5 presentation sets beginner framing, useful visuals, concise detail, stable HTML continuity, and sharing when that capability applies.
 
-  # Word budget
+Sentence-level language follows `rules/asd-ste100-language.md`.
 
-  Say it in the fewest words that stay accurate and complete. Before sending, cut every sentence that does not change what the reader thinks or does.
+Progress and final structure follow the named completion contract.
 
-  Cut these on sight:
+# Word budget
 
-  - Deliberation. State the decision, not the reasoning that reached it, unless the reader has to weigh it themselves.
-  - Why you did not do something. Say what you did; add the reason only if the reader must decide whether to do it.
-  - Incidental findings from your own process. Report one only when the reader must act on it, and give it one line.
-  - Any sentence that restates a fact already stated in a heading, a list, or an earlier line.
+Keep ELI5 pages concise and useful. Use the ASD rule's 20-word procedure target and 25-word descriptive target when the technical content allows.
 
-  When you have more than two facts of the same kind, use a list or a table. Prose paragraphs hide facts; rows expose them.
+# No contrast framing
 
-  # No contrast framing
+Use direct claims and direct actions. The canonical rule owns sentence form; capability contracts own exceptions needed to explain a concrete failure.
 
-  Write the claim. Never prop it up against what it is not.
+# Naming
 
-  The banned shape is a claim paired with a rejected alternative, in any wording:
+Use full capability names for files, modules, functions, variables, branches, and tests. Name reusable components for the capability they provide. Keep workflow words on driver surfaces.
 
-  | Banned | Write instead |
-  |---|---|
-  | Verified against the remote, not just locally | Verified against the remote |
-  | This is a design flaw, not a typo | This is a design flaw |
-  | Not a copy of the shared script, but an ad |
-  | Rather than patching the caller, the fix moves into the helper | The fix moves into the helper |
-  | Instead of three passes, it runs one | It runs one pass |
-  | It is not only faster; it is correct | It is correct and faster |
-  | This is less a bug than a missing feature
-  | Let me read the log rather than guessing | Reading the log. |
-  | I'll patch the helper instead of the caller | Patching the helper. |
-
-  Every wording of the shape is banned, including `X, not Y`, `not Y but X`, `rather than Y, X`, `instead of Y, X`, `X over Y`, `not just X — Y`, `less X than Y`, and a negated sentence followed by its po
-  ──── (152 lines hidden) ─────────────────────────────────────────────────────────────────────────────────────────────
-  the name.
-
-  | Written on the day | Named for the subject |
-  |---|---|
-  | `august_cert_failures.py` | `cert_rejections.py` |
-  | `fix_august_bug()` | `normalize_calendar_color()` |
-  | `AUGUST_REJECTION_CODES` | `REJECTION_CODE
-  | `test_august_failures` | `test_rejects_wrong_calendar_color` |
-  | `jira4821_validator.py` | `manifest_validator.py` |
-  | `q3_migration/` | `add_tenant_id_column/` |
-  | `v2_client.py` | `retrying_client.py` |
-  | `legacy_export.py` | `csv_export.py` |
-  | `temp_fix.py` | `unicode_path_workaround.p
-  | "Fix August cert failures" | "Fix calendar color mismatch in cert export" |
-
-  A branch name is a name. It carries no date,ither. Someone reads it to decide whether to check the branch out, so it has to say what the work does.
-
-  | Written on the day | Named for the subject |
-  |---|---|
-  | `fix/cert-2026-08-b3-calendar-widget-color` | `fix-calendar-widget-color` |
-  | `parse-rejection-emails-cert-2026-08-b3` |
+  # Change size
 
-  One prefix spreads. Once `august_` sits in one name, the next name matches it for consistency, and within a week the month reads as a real domain concept that forty places depend on. Rename it the hour you notice it.
 
-  # Change size
 
   When planning work or opening a pull request, size the change first: one self-contained change, around 100 lines, with its tests. Read the small-changelists guide for the numbers, the allowed exceptions, and how to split.
 
+Use `~/.claude/skills/small-cl/SKILL.md` for change-size guidance and review-sized boundaries.
+
 ## Execution and delegation
 
 Delegate all task work to Tier 3 agents.
@@ -126,10 +100,12 @@ Warm agent: An agent that has acted within the past 30 minutes. Reuse warm agent
 
   When you use a tool, you may say a brief sentence first. If no tool can express what the user asked for, say so. Do not include internal or system XML tags in your response.
 
+Use the named review workflow for code-review response reporting.
+
   # Code review
 
   When reviewing code, report everything you find. Filtering belongs in a separate pass.
 
-  <tone_preference>
-  Keep outputs reasonably concise.
-  </tone_preference>
+<tone_preference>
+ELI5 sets beginner-friendly presentation when it applies. ASD sets sentence-level wording and tone.
+</tone_preference>

package/_shared/AGENTS.md

@@ -2,6 +2,8 @@
 
 Cross-cutting runtime assets shared by multiple skills. The PR-loop skills (`bugteam`, `pr-converge`, `findbugs`, `fixbugs`) are one such cluster; other clusters live here too. Files here are installed into `~/.claude/_shared/` by `bin/install.mjs` alongside the skill directories that import them.
 
+Shared assets use `~/.claude/rules/asd-ste100-language.md` for user-facing word choice, sentence style, tone, punctuation, and prose form. Each asset keeps its workflow-specific structure.
+
 ## Contents
 
 | Entry | Description |

package/_shared/advisor/AGENTS.md

@@ -2,21 +2,21 @@
 
 Warm-advisor bind-and-consult protocol shared by `team-advisor`, `orchestrator`, `orchestrator-refresh`, and every executor subagent `orchestrator` routes work to. Changes here affect all of these simultaneously — treat this as a breaking-change surface.
 
-Host profile (Claude vs third-party) is detected first; Claude walks the multi-tier Agent spawn ladder (CLI chain as fallback), a third-party host binds a max-tier Claude advisor through the CLI Claude-chain (fail closed when the chain cannot serve) with a separate executor paste block.
+Host profile is resolved from session identity first (Claude, Codex, or neither). Claude walks Fable then Sol in-session (CLI chain as the Fable fallback). Codex walks Sol in-session. A third-party host binds Fable through the CLI Claude-chain (fail closed when Fable and Sol cannot serve) with a separate executor paste block.
 
 ## Key documents
 
 | File | Purpose |
 |---|---|
-| `advisor-protocol.md` | Router with a moment-keyed read map: host profiles first, model floor, warm-up and consult standing rules, lifecycle ownership, Advisor-block assembly rule, and the shared CLI Claude-chain — each with a stub pointing at its `reference/` detail file |
+| `advisor-protocol.md` | Router with a moment-keyed read map: session identity and host profiles first, model floor, warm-up and consult standing rules, lifecycle ownership, Advisor-block assembly rule, and the shared CLI Claude-chain — each with a stub pointing at its `reference/` detail file |
 
 ## Subdirectory
 
 | Entry | Description |
 |---|---|
-| `scripts/` | `model_tier_run_validator.py` (spawn-walk log checks, including optional Sol), `codex_sol_advisor.py` (read-only Sol xhigh bind and resume), `tier_model_ids.py` (Claude aliases, Codex model ids, and host detection), and `advisor_scripts_constants` under `scripts/config/` (ladder, bind tokens, aliases, host profiles, and SendMessage wait bound) |
-| `reference/` | Progressive-disclosure detail behind protocol stub sections: `warm-up.md`, `third-party-bind.md`, `sol-rung.md`, `consult-format.md`, `advisor-block.md`, `lifecycle.md`, `cli-chain.md`, and `spawn-walk-log.md` |
+| `scripts/` | `model_tier_run_validator.py` (spawn-walk log checks, including Codex Sol-first and optional Sol), `codex_sol_advisor.py` (read-only Sol bind and resume at shared `ADVISOR_EFFORT`), `tier_model_ids.py` (Claude aliases, Codex model ids, session identity, and host detection), and `advisor_scripts_constants` under `scripts/config/` (ladder, bind tokens, aliases, host profiles, identity tokens, shared effort, and SendMessage wait bound) |
+| `reference/` | Progressive-disclosure detail behind protocol stub sections: `identity.md`, `warm-up.md`, `third-party-bind.md`, `sol-rung.md`, `consult-format.md`, `advisor-block.md`, `lifecycle.md`, `cli-chain.md`, and `spawn-walk-log.md` |
 
 ## Breaking-change rule
 
-A change to host detection, the model-floor rule, the charter template, either host's Advisor block, or lifecycle ownership in `advisor-protocol.md` requires updating every consuming skill (`team-advisor`, `orchestrator`, `orchestrator-refresh`) in the same commit.
+A change to session identity, host detection, the model-floor rule, the charter template, any host's Advisor block, or lifecycle ownership in `advisor-protocol.md` requires updating every consuming skill (`team-advisor`, `orchestrator`, `orchestrator-refresh`) in the same commit.

package/_shared/advisor/advisor-protocol.md

@@ -2,8 +2,9 @@
 
 Shared spawn-once, consult-by-message protocol for a warm advisor. Two skills depend on this: `team-advisor` (binds the advisor for its own consulting session) and `orchestrator` (binds the same advisor and lets its own routed executor subagents consult it too). Executor spawn prompts are a third consumer, via the assembled Advisor block.
 
-**First step of every bind:** detect the host profile (next section).
-Walk the model-floor ladder, spawn `session-advisor`, or open the CLI fallback only after the host is known.
+**First step of every bind:** name the session identity and resolve the host profile (next section).
+Walk the model-floor ladder, spawn the in-session advisor, or open the CLI fallback only after the host is known.
+On a Codex host, skip straight to **Host profiles → Codex host**.
 On a third-party host, skip straight to **Host profiles → Third-party host**.
 On Claude, continue with **Model floor** and the rest of this document.
 
@@ -13,9 +14,11 @@ The sections below hold the standing rules; open a reference file at the moment
 
 | Moment | Open |
 |---|---|
+| Naming the session identity | [`reference/identity.md`](reference/identity.md) — Claude, Codex, or neither |
 | Binding on a Claude host | [`reference/warm-up.md`](reference/warm-up.md) — spawn fields, Fable token, charter |
+| Binding on a Codex host | [`reference/identity.md`](reference/identity.md) — in-session Sol spawn |
 | Binding from a third-party host | [`reference/third-party-bind.md`](reference/third-party-bind.md) — CLI bind steps, fail-closed rule |
-| `ADVISOR_SOL_XHIGH` is set | [`reference/sol-rung.md`](reference/sol-rung.md) — preflight, bind, fallback |
+| Fable is out of usage | [`reference/sol-rung.md`](reference/sol-rung.md) — Sol fallback at shared effort |
 | Composing a consult | [`reference/consult-format.md`](reference/consult-format.md) — packet, new-evidence and report-back rules |
 | Assembling an executor spawn prompt | [`reference/advisor-block.md`](reference/advisor-block.md) — the paste parts |
 | Advisor drifts, dies, or the task pivots | [`reference/lifecycle.md`](reference/lifecycle.md) — re-spawn and re-bind steps |
@@ -24,59 +27,75 @@ The sections below hold the standing rules; open a reference file at the moment
 
 ## Host profiles
 
-Detect the host profile **before** any model-floor walk. Source of truth for names and detection: `HOST_PROFILE_CLAUDE`, `HOST_PROFILE_THIRD_PARTY`, `ALL_HOST_PROFILES`, and `detect_host_profile(...)` in `$HOME/.claude/_shared/advisor/scripts/config/advisor_scripts_constants/model_tier_run_validator_constants.py` and `tier_model_ids.py`.
+Name the session identity **before** any model-floor walk. Source of truth for names and detection: `HOST_PROFILE_CLAUDE`, `HOST_PROFILE_CODEX`, `HOST_PROFILE_THIRD_PARTY`, `ALL_HOST_PROFILES`, `resolve_session_identity(...)`, and `detect_host_profile(...)` in `$HOME/.claude/_shared/advisor/scripts/config/advisor_scripts_constants/model_tier_run_validator_constants.py` and `tier_model_ids.py`.
+Identity tokens and bind paths: [`reference/identity.md`](reference/identity.md).
 
-Detection order:
+Session identity:
 
-1. `ADVISOR_HOST_PROFILE=ThirdParty` or `=Claude` (explicit override; any letter case).
+1. Call `resolve_session_identity` with the session's named identity.
+2. A `codex` token selects Codex. A `claude` token selects Claude. Any other identity selects ThirdParty.
+3. When both tokens appear, Codex wins.
+
+Mechanical override for scripts:
+
+1. `ADVISOR_HOST_PROFILE=ThirdParty` or `=Claude` or `=Codex` (explicit override; any letter case).
 2. `THIRD_PARTY=1` (or `true` / `yes` / `on`) — a third-party (non-Claude) harness.
 3. Default: Claude.
 
-### Sol rung — any host
+### Shared effort — any host
+
+Fable and Sol both read `ADVISOR_EFFORT` (`low`, `medium`, `high`, `xhigh`, `max`). The default is `low`.
+Pass `--effort <level>` on the Sol helper to set effort for that Sol run.
+Pass `--effort <level>` on the Claude CLI bind for Fable. An unset or unrecognized value uses `low`.
+
+### Sol rung
 
-An optional **sol xhigh** rung sits above the Claude ladder on every host, switched by the flag `ADVISOR_SOL_XHIGH=1` (or `true` / `yes` / `on`), set in the environment or by the consuming skill's invocation.
-Flag off: the walk starts at the host's Claude ladder, Fable first.
-Flag on: run the Codex preflight and bind per [`reference/sol-rung.md`](reference/sol-rung.md); a failed preflight falls back to the Claude ladder.
+On Claude and ThirdParty: when Fable is out of usage, bind Sol through the Codex helper.
+Open that attempt with `ADVISOR_SOL=1` (or `true` / `yes` / `on`) in the environment, or pass `--enable-sol` on the helper invocation.
+Flag off both ways: fail closed when Fable did not bind.
+Flag on: run the Codex preflight and bind per [`reference/sol-rung.md`](reference/sol-rung.md); a failed preflight fails closed when Fable did not bind.
+
+On Codex: Sol is the in-session default. The `ADVISOR_SOL` flag is not required. Fail closed when that spawn does not bind.
 
 ### Claude host
 
-Use the **Model floor** ladder below (sol when flagged, then Fable → Opus).
+Use the **Model floor** ladder below (Fable first, then Sol when Fable is out of usage).
 Warm-up spawns `subagent_type: session-advisor` via the Agent tool; consults go through `SendMessage` to that warm agent.
 Assemble and paste each executor's Advisor block per the **Advisor block** section.
 
+### Codex host
+
+Spawn a native in-session Sol subagent at `resolve_codex_model_id("Sol")`.
+Walk `candidate_tiers = ["Sol"]`. Record `{tier: "Sol", result: "spawned"}` on success.
+**Fail closed:** when Sol does not bind, set `selected_tier = null` and a `fallback_reason`, report that the advisor is unreachable, and **stop**.
+Do not walk Fable on a Codex host. Consults stay in-session with that Sol subagent.
+Assemble and paste each executor's Advisor block per the **Advisor block** section.
+
 ### Third-party host
 
-On a third-party (non-Claude) harness, the shared CLI Claude-chain is the one path to a Claude advisor: bind a **max-tier Claude advisor** through it, per [`reference/third-party-bind.md`](reference/third-party-bind.md).
+On a third-party (non-Claude, non-Codex) harness, the shared CLI Claude-chain is the one path to a Claude advisor: bind Fable through it, per [`reference/third-party-bind.md`](reference/third-party-bind.md).
 The bound Claude session is the advisor; this third-party session stays the executor.
-Floor **Opus**; walk `candidate_tiers = ["Fable", "Opus"]` with `own_tier = Opus`; the sol rung binds ahead of the chain when open.
+Walk `candidate_tiers = ["Fable"]`. When Fable is out of usage, the sol rung binds after Fable (`candidate_tiers = ["Fable", "Sol"]`).
 **Fail closed:** when every candidate fails, set `selected_tier = null` and a `fallback_reason`, report that the advisor is unreachable, and **stop** — ENDORSE / CORRECTION / PLAN / STOP come only from a bound advisor.
 Executors report to the orchestrating session; that session consults the bound advisor and relays the four-signal reply.
 
 ## Model floor
 
-**Claude host:** the advisor's model tier must be at or above the highest tier of any consumer that will reach it. Each consuming skill supplies its own consumer set when computing the floor:
-- `team-advisor`: the sole consumer is the calling session itself, so the floor is the stronger of Opus and that session's own tier.
-- `orchestrator`: the consumer set is the orchestrating session plus every tier named in its routing table, so the floor is the stronger of Opus and the max of those.
-
-Whatever the consumer set, the floor sits at Opus or above — use the stronger of Opus and the strongest consumer tier.
-
-**Third-party host:** the CLI advisor floor is fixed at **Opus** (walk Fable → Opus only), whatever the session's own tier.
-
-Ladder, strongest first: sol (flag-gated, Codex CLI) → `Fable` → `Opus`.
-Advisors bind at Opus or above; `Sonnet` and `Haiku` are executor tiers only.
+On Claude and ThirdParty the advisor ladder is `Fable` first, then sol (flag-gated, Codex CLI) when Fable is out of usage.
+On Codex the walk is Sol only, in-session.
+Opus is not an advisor candidate. `Sonnet` and `Haiku` are executor tiers only.
+Consumer `own_tier` is recorded on the spawn-walk log; it does not add Opus to the advisor walk.
 Tier names are canonical Title Case; the validator accepts any letter case and normalizes to Title Case.
-Read the floor tier — the lower bound only — then try binds top-down, stopping at the floor tier.
-Each try resolves its candidate tier to the short model alias via the tier-to-alias map in [`reference/cli-chain.md`](reference/cli-chain.md).
-The advisor is created at `selected_tier` — the first ladder tier that binds — which may sit above the floor.
-When even the floor tier fails on a Claude host, move to the **CLI chain** fallback below.
-On a third-party host the CLI chain is already the primary path, so floor failure fails closed per **Host profiles → Third-party host**.
+Try binds top-down. Each try resolves its candidate tier to the short model alias via the tier-to-alias map in [`reference/cli-chain.md`](reference/cli-chain.md).
+The advisor is created at `selected_tier` — the first ladder tier that binds.
+When Fable fails on a Claude host, try Sol if the flag is on, else fail closed. The CLI chain is the Fable bind path on a third-party host and the Claude-host fallback for Fable; it does not bind Opus as advisor.
+On a Codex host a failed Sol spawn fails closed per **Host profiles → Codex host**.
+On a third-party host the CLI chain is already the primary path, so a failed Fable (and Sol, when enabled) walk fails closed per **Host profiles → Third-party host**.
 
 Emit a structured spawn-walk log so the walk can be checked mechanically: [`reference/spawn-walk-log.md`](reference/spawn-walk-log.md).
 The validator checks ladder shape only; host policy sits on top.
 
-**Equal-tier pairings.** Bind a same-tier advisor when the goal is an independent second pass.
-For irreversible or security-sensitive work, pair a top-tier executor with a top-tier advisor for independent frontier review.
-The floor rule holds — the advisor sits at or above the strongest consumer's tier — and an equal-tier bind sits inside that bound.
+**Equal-tier pairings.** Bind Fable for an independent second pass on irreversible or security-sensitive work. The advisor is Fable or Sol.
 
 ## Warm-up (once per session)
 
@@ -84,6 +103,8 @@ On a **Claude host**, walk the candidate tiers top-down, spawning `session-advis
 A **Fable**-tier try carries the exact token `FABLE-SPAWN-AUTHORIZED` in its prompt — `hooks/blocking/fable_spawn_gate.py` denies a Fable-tier spawn without it.
 Full spawn fields and the charter template: [`reference/warm-up.md`](reference/warm-up.md).
 
+On a **Codex host**, spawn a native in-session Sol subagent with the same charter. Bind fields: [`reference/identity.md`](reference/identity.md) and [`reference/warm-up.md`](reference/warm-up.md).
+
 On a **third-party host**, bind per [`reference/third-party-bind.md`](reference/third-party-bind.md) and charter the CLI session with the same charter — the reply contract is the same, and consults travel through the CLI runner.
 
 ## Consulting the warm agent
@@ -115,6 +136,8 @@ Modes and failover, the tier-to-alias table, brief piping, and `--resume` sessio
 
 **Third-party host:** the primary bind and consult path; the walk order and fail-closed rule live in [`reference/third-party-bind.md`](reference/third-party-bind.md).
 
+**Codex host:** do not use this runner as the primary path. Sol binds in-session.
+
 **Claude host:** fall back to this runner exactly when one of these holds:
 - The Agent-tool spawn errors at every candidate tier down to the floor — the tool itself is unavailable.
 - `SendMessage` to the shared advisor errors, or draws no reply within the bound in `ADVISOR_SENDMESSAGE_REPLY_WAIT_SECONDS` (120) in `$HOME/.claude/_shared/advisor/scripts/config/advisor_scripts_constants/model_tier_run_validator_constants.py`, and a re-spawn also fails.