@azure-id/orc 1.9.1 → 1.9.2

package/CHANGELOG.md

@@ -10,6 +10,75 @@ Format: `### v<version> — <title> _(<date>)_`.
 
 ---
 
+### v1.9.2 — the code graph gets its own tab, and Opus 5 becomes Opus 5.5 _(2026-09-23)_
+
+**Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`
+is the pre-v0.56.0 one and cannot install itself. Full detail in the CAUTION at
+the top of this file.
+
+- **Step 1 - release the command from the old package:** `npm uninstall -g orc`
+- **Step 2 - install the current package:** `npm i -g @azure-id/orc`
+- **Step 3 - re-apply it to your project:** `orc update`
+
+**Do not use `npm i -g -f`.** Full detail in v0.56.0 below.
+
+**The code graph has its own tab.** Before this release the graph was one card
+on the Knowledge ▸ Wiki tab: fourteen rows of exact numbers and no picture of
+what any of them meant. `orc ui` ▸ Knowledge now has a sixth tab, **Code
+graph**, and the card on the Wiki tab is gone. The tab reads top to bottom:
+
+- **Where your code graph is now.** The four states `OFF` · `NONE` · `FRESH`
+  · `DRIFTED` as a ladder, with the action that moves the graph from one to
+  the next on each connector. The current state is lit and sends a ring
+  outward. Below it is the ONE action that state needs: the config command for
+  OFF (copy-able, never a button), the free `orc graph update` button for NONE
+  and DRIFTED, nothing for FRESH. The line a lane prints into the chat
+  (`line`) is shown verbatim.
+- **How the code graph works.** Five stations — your code, the parser, the
+  map, the questions, the short card — with dots that run between them. The
+  first three are marked free; the card is marked as what costs context tokens.
+  The optional notes layer, the only part that can cost a model, is a separate
+  line with the current `code_graph_notes` value.
+- **What a code graph looks like (an example, not your code).** Four files from
+  a made-up shop drawn as an SVG: files, symbols, calls (a pulse runs caller to
+  callee), refs and imports. Point at a dot, or Tab to it, and its edges light
+  up while a caption says what `orc graph ctx` would answer. A legend names
+  every mark.
+- **Your graph, in numbers.** Files, symbols, symbols per file and generation
+  as tiles that count up to the CLI's own value; the added · changed · deleted
+  counts; and the density as a bar, per language when the CLI sent
+  `density.by_lang`.
+- **What the graph cost, and what it probably saved.** `paid` (four stacked
+  parts) and `avoided` (solid to its low end, striped to its high end) on ONE
+  scale. Every read in `read_set`, in the CLI's order, with its count and one
+  line on what it answers; a read never asked keeps its slot, muted.
+- **All the numbers, as the CLI sent them.** The old card, unchanged, minus the
+  chip and the button the ladder now carries.
+- **What each word means.** Every term on the tab in four groups.
+
+The pictures derive nothing: every number is `orc graph status --json` or
+`orc graph gain --json`, drawn to scale. `prefers-reduced-motion` removes all
+three new infinite animations with `display: none` and every finite one with
+`animation: none`, and the tiles skip their count-up. The `graph-drifted`
+doctor finding on Overview now opens the Code graph tab.
+
+**Every Opus 5 agent now runs Opus 5.5 (`claude-opus-5-5`).** Every agent and
+generated executor that shipped as `model: claude-opus-5` now ships as
+`model: claude-opus-5-5`, and the prose that named "Opus 5" now names
+"Opus 5.5". Opus 5.5 is cheaper than Opus 5, so the same pipeline costs less.
+`bin/pricing.json` gains the `claude-opus-5-5` row ($4 input · $5 cache write
+· $0.20 cache read · $20 output per million tokens, from the Claude pricing
+page), and `orc budget` prices its forecasts against it.
+
+What did NOT change: the agent NAMES (`orc-executor-opus-5-med` and the rest),
+the `opus5_only` key and its "Opus 5-only" mode name. `claude-opus-5` stays
+in the known-model list and keeps its price row, so an existing config and old
+traces still validate and still price.
+
+**What you have to do:** `orc update`, to install the new agent files.
+
+---
+
 ### v1.9.1 — the graph that was paid for and never asked _(2026-09-23)_
 
 **Still on the unscoped `orc` package?** Do this once first - your `orc upgrade`

package/README-id.md

@@ -7,13 +7,13 @@
 *Terima permintaan → pahami → rencanakan → beri nilai → kerjakan paralel → periksa → uji → kirim.*
 
 ![npm](https://img.shields.io/npm/v/%40azure-id%2Forc?style=for-the-badge&color=cb3837&logo=npm)
-![Version](https://img.shields.io/badge/version-1.9.1-blue.svg?style=for-the-badge)
+![Version](https://img.shields.io/badge/version-1.9.2-blue.svg?style=for-the-badge)
 ![License](https://img.shields.io/badge/license-MIT-green.svg?style=for-the-badge)
 ![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg?style=for-the-badge)
 ![Claude Code](https://img.shields.io/badge/Claude_Code-Skills-purple.svg?style=for-the-badge)
 ![Dependencies](https://img.shields.io/badge/dependencies-zero-lightgrey.svg?style=for-the-badge)
 
-**Versi terbaru: v1.9.1** · diperbarui 23-09-2026 · [daftar perubahan lengkap](CHANGELOG.md)
+**Versi terbaru: v1.9.2** · diperbarui 23-09-2026 · [daftar perubahan lengkap](CHANGELOG.md)
 
 **Ada di npm: [`@azure-id/orc`](https://www.npmjs.com/package/@azure-id/orc)** — `npm i -g @azure-id/orc`
 
@@ -271,7 +271,7 @@ pemakaian 5 jam, pemakaian mingguan, dan beberapa hal lain.
 | Perintah | Kegunaannya | Contoh jalannya |
 |---|---|---|
 | **`/orc`** | Alur penuh: terima → rencana → gelombang paralel bernilai → periksa → uji → kirim. Rajin menyimpan titik simpan; bisa dilanjutkan di sesi baru. | [lihat](mock-run/orc.md) |
-| **`/orc-ultra`** | Sama, ditambah penasihat Opus 5 **xhigh** dan tiga gerbang penilaian. Analisis dalam, pola kode, tes, dan keamanan dipaksa menyala. Memang mahal. | [lihat](mock-run/orc-ultra.md) |
+| **`/orc-ultra`** | Sama, ditambah penasihat Opus 5.5 **xhigh** dan tiga gerbang penilaian. Analisis dalam, pola kode, tes, dan keamanan dipaksa menyala. Memang mahal. | [lihat](mock-run/orc-ultra.md) |
 | **`/orc-mini`** | Satu agen Sonnet 5, satu pemeriksaan build + tes, lalu kirim. Melewati review penuh dan pengujian. Satu baris **pembacaan kompleksitas** berisi angka menawarkan lane penuh kalau perubahannya lebih luas dari satu area. Bisa pindah ke alur penuh di tengah jalan kalau diminta. | [lihat](templates/skills/orc-mini/examples/mini-run-mock.md) |
 | **`/orc-fast`** | Lane tercepat. Butuh wiki yang masih segar **dan** pola kode yang sudah tersimpan; kalau ada, ia melewati tahap analis dan perencana sepenuhnya. Kalau salah satu syarat tidak ada, ia mundur ke `/orc-mini` — obrolan tidak pernah berhenti. | [lihat](mock-run/orc-fast.md) |
 | **`/orc-quick`** | Minta apa saja: perbaikan kecil, pertanyaan, mencari bug, menaikkan versi dependensi, komentar PR. Lihat → tanya sekali → kerjakan. **Selalu bertanya agen mana yang mau dipakai**, dan tidak ada pengaturan yang bisa mengubah itu. Satu **defect direproduksi merah dulu sebelum diperbaiki**. | [lihat](mock-run/orc-quick.md) |
@@ -786,45 +786,44 @@ Bacalah sebagai catatan putaran itu, bukan sebagai audit terkini:
 **Riwayat lengkap: [CHANGELOG.md](CHANGELOG.md)** — atau `orc changelog`, yang
 hanya mencetak yang lebih baru dari versi yang Anda punya.
 
-### v1.9.1 - graf yang dibayar tetapi tidak pernah ditanya _(23-09-2026)_
-
-Graf kode lebih sering dirawat daripada ditanya, dan bagian yang ditanya lebih
-mahal daripada yang dicatat meterannya. Di satu proyek Vue nyata, 416 dari 429
-berkas `.vue` tidak punya simbol, dan panel menulis `0 hook updates` setelah 35.
-
-**Jawaban lebih kecil.** `--brief` menyimpan kartu, baris dan setiap hitungan,
-lalu membuang baris yang tidak pernah dicetak lane: 74 % sampai 87 % lebih
-kecil, dan setiap panggilan lane memakainya. CLI sekarang menghitung baris
-blast-radius `/orc-quick` dan baris kompleksitas `/orc-mini` dalam satu
-panggilan, bukan lane yang menghitung baris-barisnya.
-
-**Meterannya jujur.** Pembaruan oleh hook selalu tercatat 0, dan `paid`
-menghitung kartu padahal lane menerima 4 sampai 8 kali lebih banyak. Keduanya
-diperbaiki: baris `hook-update`, dan `paid.envelope` di samping kartu.
-Meterannya juga menulis pembacaan yang belum pernah dilakukan proyek ini.
-
-**Peta memberi tahu kapan ia tipis, dan kenapa** — `THIN` di `orc graph
-status`, dan `orc graph audit` baru yang menulis berkas kosong per bahasa,
-yang terpanjang lebih dulu.
-
-**Parser membaca Vue Options API** (mesin `graph@6`). Komponen, mixin dan modul
-Vuex menjadi class dengan method; `mixins` menjadi basisnya; konstanta yang
-diekspor dan komponen `<script setup>` diberi nama. Store 1.9.0 memperbarui
-dirinya sendiri satu kali, di preflight berikutnya. Tidak ada yang perlu
-dilakukan.
-
-**Pembacaan berbayar membawa isinya:** `ctx --callers-source` (enam baris di
-sekitar setiap titik panggil yang pasti), `lsp_at` untuk language server jika
-kartu menulis `AMBIGUOUS`, dan hitungan pembacaan berkas lebar yang tidak
-diberi petunjuk.
-
-**Tidak diukur di sini:** evaluasi sesi langsung tidak dijalankan, dan gerbang
-Vue (di bawah 20 % berkas `.vue` kosong) diukur di proyek Anda sendiri.
-CHANGELOG menyebut setiap batasnya.
+### v1.9.2 - graf kode mendapat tab sendiri, dan Opus 5 menjadi Opus 5.5 _(23-09-2026)_
+
+**Graf kode punya tab sendiri.** `orc ui` ▸ Knowledge ▸ **Code graph**
+menggantikan satu kartu di tab Wiki. Tab ini menunjukkan, berurutan:
+
+- **Posisi graf Anda sekarang** — empat status (OFF · NONE · FRESH · DRIFTED)
+  sebagai tangga. Status saat ini menyala, dan satu tindakan yang dibutuhkan
+  ada di bawahnya.
+- **Cara kerja graf kode** — lima langkah beranimasi, dari file Anda sampai
+  kartu singkat yang dibaca agent. Tiga langkah pertama gratis.
+- **Seperti apa graf kode** — contoh graf (bukan kode Anda). Arahkan pointer ke
+  sebuah titik untuk melihat pemanggil dan yang dipanggilnya.
+- **Graf Anda, dalam angka** — file, simbol, kepadatan per bahasa, dan apa yang
+  berubah sejak pembuatan terakhir.
+- **Biaya graf, dan perkiraan hematnya** — dibayar (persis) dan dihindari
+  (perkiraan, digambar sebagai rentang) pada satu skala, dan pertanyaan yang
+  diajukan lane.
+- **Arti setiap kata** — setiap istilah di tab ini, dengan kata sederhana.
+
+Temuan DRIFTED di Overview sekarang membuka tab ini. Reduced motion menghapus
+semua animasi.
+
+**Setiap agent Opus 5 sekarang memakai Opus 5.5.** Model id-nya
+`claude-opus-5-5` (sebelumnya `claude-opus-5`): executor, scout, analis,
+planner, reviewer, verifier, judge, dan setiap agent Opus lainnya. Opus 5.5
+lebih murah: $4 input, $5 cache write, $0,20 cache read, dan $20 output per
+sejuta token. `bin/pricing.json` punya baris baru, dan `orc budget`
+memakainya.
+
+**Yang harus Anda lakukan:** jalankan `orc update` untuk memasang file agent
+yang baru. NAMA agent tidak berubah, jadi `rubric_bands_override`,
+`fixed_executor` dan `opus5_only` tetap berjalan. Config yang masih menyebut
+`claude-opus-5` tetap valid.
 
 <details>
-<summary><strong>Rilis sebelumnya</strong> — 120 rilis, hanya judulnya. Teks lengkapnya (dalam bahasa Inggris) ada di <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
+<summary><strong>Rilis sebelumnya</strong> — 121 rilis, hanya judulnya. Teks lengkapnya (dalam bahasa Inggris) ada di <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
 
+- **v1.9.1** — the graph that was paid for and never asked · _2026-09-23_
 - **v1.9.0** — the lean lanes learn to look before they leap · _2026-09-21_
 - **v1.8.2** — the map that finds what a grep cannot · _2026-09-21_
 - **v1.8.1** — the guard that only failed on Windows · _2026-09-16_

package/README.md

@@ -7,14 +7,14 @@
 *Intake → analyze → plan → score → parallel subagents → review → verify → ship.*
 
 ![npm](https://img.shields.io/npm/v/%40azure-id%2Forc?style=for-the-badge&color=cb3837&logo=npm)
-![Version](https://img.shields.io/badge/version-1.9.1-blue.svg?style=for-the-badge)
+![Version](https://img.shields.io/badge/version-1.9.2-blue.svg?style=for-the-badge)
 ![License](https://img.shields.io/badge/license-MIT-green.svg?style=for-the-badge)
 ![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg?style=for-the-badge)
 ![Claude Code](https://img.shields.io/badge/Claude_Code-Skills-purple.svg?style=for-the-badge)
 ![Dependencies](https://img.shields.io/badge/dependencies-zero-lightgrey.svg?style=for-the-badge)
 ![GitHub stars](https://img.shields.io/github/stars/azure-id/orc?style=for-the-badge&color=yellow)
 
-**Latest: v1.9.1** · updated 2026-09-23 · [full changelog](CHANGELOG.md)
+**Latest: v1.9.2** · updated 2026-09-23 · [full changelog](CHANGELOG.md)
 
 **On npm: [`@azure-id/orc`](https://www.npmjs.com/package/@azure-id/orc)** — `npm i -g @azure-id/orc`
 
@@ -250,7 +250,7 @@ ORC have terminal hook to see: Context Window %, 5 Hour usage %, Weekly usage %
 | Command | What it does | Mocked run |
 |---|---|---|
 | **`/orc`** | The full pipeline: intake → plan → scored parallel waves → review → verify → ship. Checkpoints eagerly; resumes in a fresh session. | [see it](mock-run/orc.md) |
-| **`/orc-ultra`** | The same, plus an Opus 5 **xhigh** advisor and three judgment gates. Deep analysis, patterns, tests and security forced on. Costly by design. | [see it](mock-run/orc-ultra.md) |
+| **`/orc-ultra`** | The same, plus an Opus 5.5 **xhigh** advisor and three judgment gates. Deep analysis, patterns, tests and security forced on. Costly by design. | [see it](mock-run/orc-ultra.md) |
 | **`/orc-mini`** | One Sonnet 5 executor, a build + test smoke gate, ship. Skips full review and verify. A one-line **complexity read** with counts behind it offers the full lane when the change is wider than one area. Switches to the full flow mid-run on request. | [see it](templates/skills/orc-mini/examples/mini-run-mock.md) |
 | **`/orc-fast`** | The fastest lane. Needs a fresh wiki **and** a cached code pattern; then it skips the analyst and planner entirely. A missing prerequisite falls back to `/orc-mini` — the chat never stops. | [see it](mock-run/orc-fast.md) |
 | **`/orc-quick`** | Ask for anything: a fix, a question, a defect hunt, a dependency bump, PR comments. Look → ask once → do. **It always asks which agent to dispatch**, and no setting can change that. A defect is **reproduced red before it is fixed**. | [see it](mock-run/orc-quick.md) |
@@ -728,41 +728,42 @@ a current audit: [EVAL-REPORT.md](EVAL-REPORT.md).
 **Full history: [CHANGELOG.md](CHANGELOG.md)** — or `orc changelog`, which prints
 only what is newer than the version you have.
 
-### v1.9.1 — the graph that was paid for and never asked _(2026-09-23)_
-
-The code graph was maintained far more than it was consulted, and the part that
-was consulted cost more than the meter said. On one real Vue project, 416 of
-429 `.vue` files had no symbol, and the panel said `0 hook updates` after 35.
-
-**Answers are smaller.** `--brief` keeps the card, the line and every count and
-drops the rows a lane never prints: 74 % to 87 % smaller, and every lane call
-uses it. The CLI now computes `/orc-quick`'s blast-radius line and
-`/orc-mini`'s complexity line in one call, instead of the lane counting rows.
-
-**The meter tells the truth.** Hook updates were always counted as 0, and
-`paid` counted the card while the lane received 4 to 8 times more. Both are
-fixed: a `hook-update` row, and `paid.envelope` beside the cards. The meter
-also lists the reads this project has never made.
-
-**The map says when it is thin, and why** — `THIN` on `orc graph status`, and
-a new `orc graph audit` that lists the empty files by language, longest first.
-
-**The parser reads the Vue Options API** (engine `graph@6`). A component, a
-mixin and a Vuex module are a class with methods; `mixins` are its bases;
-exported constants and `<script setup>` components are named. A 1.9.0 store
-upgrades itself once, at the next preflight. Nothing to do.
-
-**The paid reads carry what they were paid for:** `ctx --callers-source` (six
-lines around each confident call site), `lsp_at` for a language server when a
-card says `AMBIGUOUS`, and a count of the wide whole-file reads no hint named.
-
-**Not measured here:** the live-session evaluation did not run, and the Vue gate
-(under 20 % empty `.vue` files) is measured on your own project. The CHANGELOG
-names every limit.
+### v1.9.2 — the code graph gets its own tab, and Opus 5 becomes Opus 5.5 _(2026-09-23)_
+
+**The code graph has its own tab.** `orc ui` ▸ Knowledge ▸ **Code graph**
+replaces the one card on the Wiki tab. The tab shows, in this order:
+
+- **Where your graph is now** — the four states (OFF · NONE · FRESH · DRIFTED)
+  as a ladder. The current state is lit, and the one action it needs is below.
+- **How the code graph works** — five animated steps, from your files to the
+  short card an agent reads. The first three are free.
+- **What a code graph looks like** — an example graph (not your code). Put the
+  pointer on a dot to see its callers and callees.
+- **Your graph, in numbers** — files, symbols, density per language, and what
+  changed since the last build.
+- **What the graph cost, and what it probably saved** — paid (exact) and
+  avoided (an estimate, drawn as a range) on one scale, and which reads lanes
+  asked.
+- **What each word means** — every term on the tab, in plain words.
+
+A DRIFTED finding on Overview now opens this tab. Reduced motion removes every
+animation.
+
+**Every Opus 5 agent now runs Opus 5.5.** The model id is `claude-opus-5-5`
+(was `claude-opus-5`): executors, scouts, the analyst, the planner, the
+reviewer, the verifier, the judges and every other Opus agent. Opus 5.5 costs
+less: $4 input, $5 cache write, $0.20 cache read and $20 output per million
+tokens. `bin/pricing.json` has the new row, and `orc budget` uses it.
+
+**What you have to do:** run `orc update` to install the new agent files. The
+agent NAMES did not change, so `rubric_bands_override`, `fixed_executor` and
+`opus5_only` keep working. A config that still names `claude-opus-5` is still
+valid.
 
 <details>
-<summary><strong>Earlier releases</strong> — 120 of them, titles only. Full text in <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
+<summary><strong>Earlier releases</strong> — 121 of them, titles only. Full text in <a href="CHANGELOG.md">CHANGELOG.md</a>.</summary>
 
+- **v1.9.1** — the graph that was paid for and never asked · _2026-09-23_
 - **v1.9.0** — the lean lanes learn to look before they leap · _2026-09-21_
 - **v1.8.2** — the map that finds what a grep cannot · _2026-09-21_
 - **v1.8.1** — the guard that only failed on Windows · _2026-09-16_

package/bin/build-agents.js

@@ -1,109 +1,109 @@
-#!/usr/bin/env node
-"use strict";
-/**
- * Executor-agent generator. The 6 executor agent files differ ONLY in
- * frontmatter (name/model/effort + score band); their body is one shared
- * contract. This script is the single source of truth: edit
- * agents-src/executor.template.md (or the VARIANTS table), run
- * `npm run build:agents`, and every copy is stamped out identically.
- *
- * Modes:
- *   node bin/build-agents.js          write templates/agents/orc-executor-*.md
- *   node bin/build-agents.js --check  fail if any generated file drifted from
- *                                     the template (runs in `npm run verify`
- *                                     and prepack — a hand-edit to a generated
- *                                     executor file fails the build)
- */
-const fs = require("fs");
-const path = require("path");
-
-const ROOT = path.join(__dirname, "..");
-const TEMPLATE = path.join(ROOT, "agents-src", "executor.template.md");
-const OUT_DIR = path.join(ROOT, "templates", "agents");
-
-// Score→model bands mirror templates/agents/MODEL-MAPPING.md and the single
-// score→model table in skills/orc/config.md (documented drift — change
-// together). `effort: null` = a model with NO effort ladder (haiku): the
-// generator omits the `effort:` frontmatter line entirely.
-//
-// v1.0.0 W4 — the table is SIX bands, not eight, and the `opus5_only` ladder is
-// TWO, not three. Four of these agents are named by NO default row:
-// names them, and they ship anyway (D14). They stay reachable through
-// `rubric_bands_override`, `orc diy` `fixed_executor` and `extra_fallback_agent`,
-// and deleting a generated file that no row happens to name today would be a
-// rename-shaped migration for what is only a table change. Their `band` string
-// says so rather than naming a range that no longer exists — a band label that
-// lies is worse than one that admits it is unreachable by default.
-const VARIANTS = [
-  { name: "orc-executor-opus-5-med",     model: "claude-opus-5",     effort: "medium", band: "highest-complexity [90,100]" },
-  { name: "orc-executor-opus-5-low",     model: "claude-opus-5",     effort: "low",    band: "upper-complexity [65,90)" },
-  { name: "orc-executor-sonnet-5-high",  model: "claude-sonnet-5",  effort: "high",   band: "mid-complexity [55,65)" },
-  { name: "orc-executor-sonnet-4-6-high", model: "claude-sonnet-4-6", effort: "high",  band: "low-mid-complexity [40,55)" },
-  { name: "orc-executor-sonnet-4-6-med", model: "claude-sonnet-4-6", effort: "medium", band: "low-complexity [30,40)" },
-  { name: "orc-executor-haiku-4-5",      model: "claude-haiku-4-5",  effort: null,     band: "lowest-complexity [0,30)" },
-  // NAMED BY NO BAND since v1.0.0 W4 (D14) — kept on disk, dispatched only when a
-  // user names one explicitly.
-  { name: "orc-executor-opus-5-high",    model: "claude-opus-5",    effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-  { name: "orc-executor-opus-4-8-high",  model: "claude-opus-4-8",  effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-  { name: "orc-executor-opus-4-7-high",  model: "claude-opus-4-7",  effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-  { name: "orc-executor-opus-4-7-med",   model: "claude-opus-4-7",  effort: "medium", band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
-];
-
-// Line endings are NOT content here: .gitattributes stores these files with LF
-// and checks them out native, so a Windows worktree is CRLF and a Linux one LF.
-// The injected frontmatter line therefore borrows the TEMPLATE's own ending, and
-// --check compares LF-normalized text — otherwise the guard fails on Windows for
-// a difference git itself does not record.
-const eolOf = (s) => (/\r\n/.test(s) ? "\r\n" : "\n");
-const lf = (s) => s.replace(/\r\n/g, "\n");
-
-function render(template, v) {
-  const effortDesc = v.effort ? `, ${v.effort} effort` : " (no effort ladder)";
-  const effortFm = v.effort ? `effort: ${v.effort}${eolOf(template)}` : "";
-  return template
-    .replace(/\{\{NAME\}\}/g, v.name)
-    .replace(/\{\{MODEL\}\}/g, v.model)
-    .replace(/\{\{EFFORT_DESC\}\}/g, effortDesc)
-    .replace(/\{\{EFFORT_FM\}\}/g, effortFm)
-    .replace(/\{\{BAND\}\}/g, v.band);
-}
-
-function main() {
-  const checkMode = process.argv.includes("--check");
-  const template = fs.readFileSync(TEMPLATE, "utf8");
-  if (/\{\{(?!NAME|MODEL|EFFORT_DESC|EFFORT_FM|BAND)\w/.test(template)) {
-    console.error("❌ build-agents: unknown {{placeholder}} in executor.template.md");
-    process.exit(1);
-  }
-
-  let drifted = 0;
-  for (const v of VARIANTS) {
-    const out = render(template, v);
-    const dest = path.join(OUT_DIR, v.name + ".md");
-    if (checkMode) {
-      const current = fs.existsSync(dest) ? fs.readFileSync(dest, "utf8") : null;
-      if (current === null || lf(current) !== lf(out)) {
-        drifted++;
-        console.error(
-          `❌ generated agent drifted: templates/agents/${v.name}.md\n` +
-            `   Executor agents are GENERATED — edit agents-src/executor.template.md\n` +
-            `   (or bin/build-agents.js VARIANTS) and run: npm run build:agents`
-        );
-      }
-    } else {
-      fs.writeFileSync(dest, out);
-      console.log(`  gen  templates/agents/${v.name}.md`);
-    }
-  }
-
-  if (checkMode) {
-    if (drifted) process.exit(1);
-    console.log(`✅ ORC executor agents OK — ${VARIANTS.length} files match the template.`);
-  }
-}
-
-// Required by test/payload.test.js, which checks the line-ending rule above
-// without writing to templates/agents/.
-module.exports = { VARIANTS, render, lf, eolOf };
-
-if (require.main === module) main();
+#!/usr/bin/env node
+"use strict";
+/**
+ * Executor-agent generator. The 6 executor agent files differ ONLY in
+ * frontmatter (name/model/effort + score band); their body is one shared
+ * contract. This script is the single source of truth: edit
+ * agents-src/executor.template.md (or the VARIANTS table), run
+ * `npm run build:agents`, and every copy is stamped out identically.
+ *
+ * Modes:
+ *   node bin/build-agents.js          write templates/agents/orc-executor-*.md
+ *   node bin/build-agents.js --check  fail if any generated file drifted from
+ *                                     the template (runs in `npm run verify`
+ *                                     and prepack — a hand-edit to a generated
+ *                                     executor file fails the build)
+ */
+const fs = require("fs");
+const path = require("path");
+
+const ROOT = path.join(__dirname, "..");
+const TEMPLATE = path.join(ROOT, "agents-src", "executor.template.md");
+const OUT_DIR = path.join(ROOT, "templates", "agents");
+
+// Score→model bands mirror templates/agents/MODEL-MAPPING.md and the single
+// score→model table in skills/orc/config.md (documented drift — change
+// together). `effort: null` = a model with NO effort ladder (haiku): the
+// generator omits the `effort:` frontmatter line entirely.
+//
+// v1.0.0 W4 — the table is SIX bands, not eight, and the `opus5_only` ladder is
+// TWO, not three. Four of these agents are named by NO default row:
+// names them, and they ship anyway (D14). They stay reachable through
+// `rubric_bands_override`, `orc diy` `fixed_executor` and `extra_fallback_agent`,
+// and deleting a generated file that no row happens to name today would be a
+// rename-shaped migration for what is only a table change. Their `band` string
+// says so rather than naming a range that no longer exists — a band label that
+// lies is worse than one that admits it is unreachable by default.
+const VARIANTS = [
+  { name: "orc-executor-opus-5-med",     model: "claude-opus-5-5",     effort: "medium", band: "highest-complexity [90,100]" },
+  { name: "orc-executor-opus-5-low",     model: "claude-opus-5-5",     effort: "low",    band: "upper-complexity [65,90)" },
+  { name: "orc-executor-sonnet-5-high",  model: "claude-sonnet-5",  effort: "high",   band: "mid-complexity [55,65)" },
+  { name: "orc-executor-sonnet-4-6-high", model: "claude-sonnet-4-6", effort: "high",  band: "low-mid-complexity [40,55)" },
+  { name: "orc-executor-sonnet-4-6-med", model: "claude-sonnet-4-6", effort: "medium", band: "low-complexity [30,40)" },
+  { name: "orc-executor-haiku-4-5",      model: "claude-haiku-4-5",  effort: null,     band: "lowest-complexity [0,30)" },
+  // NAMED BY NO BAND since v1.0.0 W4 (D14) — kept on disk, dispatched only when a
+  // user names one explicitly.
+  { name: "orc-executor-opus-5-high",    model: "claude-opus-5-5",    effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
+  { name: "orc-executor-opus-4-8-high",  model: "claude-opus-4-8",  effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
+  { name: "orc-executor-opus-4-7-high",  model: "claude-opus-4-7",  effort: "high",   band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
+  { name: "orc-executor-opus-4-7-med",   model: "claude-opus-4-7",  effort: "medium", band: "no default band — reachable via rubric_bands_override, orc diy fixed_executor, or extra_fallback_agent" },
+];
+
+// Line endings are NOT content here: .gitattributes stores these files with LF
+// and checks them out native, so a Windows worktree is CRLF and a Linux one LF.
+// The injected frontmatter line therefore borrows the TEMPLATE's own ending, and
+// --check compares LF-normalized text — otherwise the guard fails on Windows for
+// a difference git itself does not record.
+const eolOf = (s) => (/\r\n/.test(s) ? "\r\n" : "\n");
+const lf = (s) => s.replace(/\r\n/g, "\n");
+
+function render(template, v) {
+  const effortDesc = v.effort ? `, ${v.effort} effort` : " (no effort ladder)";
+  const effortFm = v.effort ? `effort: ${v.effort}${eolOf(template)}` : "";
+  return template
+    .replace(/\{\{NAME\}\}/g, v.name)
+    .replace(/\{\{MODEL\}\}/g, v.model)
+    .replace(/\{\{EFFORT_DESC\}\}/g, effortDesc)
+    .replace(/\{\{EFFORT_FM\}\}/g, effortFm)
+    .replace(/\{\{BAND\}\}/g, v.band);
+}
+
+function main() {
+  const checkMode = process.argv.includes("--check");
+  const template = fs.readFileSync(TEMPLATE, "utf8");
+  if (/\{\{(?!NAME|MODEL|EFFORT_DESC|EFFORT_FM|BAND)\w/.test(template)) {
+    console.error("❌ build-agents: unknown {{placeholder}} in executor.template.md");
+    process.exit(1);
+  }
+
+  let drifted = 0;
+  for (const v of VARIANTS) {
+    const out = render(template, v);
+    const dest = path.join(OUT_DIR, v.name + ".md");
+    if (checkMode) {
+      const current = fs.existsSync(dest) ? fs.readFileSync(dest, "utf8") : null;
+      if (current === null || lf(current) !== lf(out)) {
+        drifted++;
+        console.error(
+          `❌ generated agent drifted: templates/agents/${v.name}.md\n` +
+            `   Executor agents are GENERATED — edit agents-src/executor.template.md\n` +
+            `   (or bin/build-agents.js VARIANTS) and run: npm run build:agents`
+        );
+      }
+    } else {
+      fs.writeFileSync(dest, out);
+      console.log(`  gen  templates/agents/${v.name}.md`);
+    }
+  }
+
+  if (checkMode) {
+    if (drifted) process.exit(1);
+    console.log(`✅ ORC executor agents OK — ${VARIANTS.length} files match the template.`);
+  }
+}
+
+// Required by test/payload.test.js, which checks the line-ending rule above
+// without writing to templates/agents/.
+module.exports = { VARIANTS, render, lf, eolOf };
+
+if (require.main === module) main();