tillerhand 3.43.0 → 3.47.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (185) hide show
  1. package/.claude/agents/board-chair.md +20 -20
  2. package/.claude/agents/code-reviewer.md +20 -20
  3. package/.claude/agents/council-advisor.md +14 -14
  4. package/.claude/agents/security-auditor.md +30 -30
  5. package/.claude/agents/test-writer.md +22 -22
  6. package/.claude/board/board-ai.md +25 -25
  7. package/.claude/board/board-api.md +25 -25
  8. package/.claude/board/board-architect.md +28 -28
  9. package/.claude/board/board-devops.md +25 -25
  10. package/.claude/board/board-mobile.md +25 -25
  11. package/.claude/board/board-performance.md +24 -24
  12. package/.claude/board/board-privacy.md +25 -25
  13. package/.claude/board/board-product.md +26 -26
  14. package/.claude/board/board-qa.md +28 -28
  15. package/.claude/board/board-ux.md +26 -26
  16. package/.claude/board/council.md +76 -76
  17. package/.claude/board/rules.md +61 -61
  18. package/.claude/claude-security-guidance.md +10 -10
  19. package/.claude/commands/adopt.md +70 -69
  20. package/.claude/commands/ask-mode.md +9 -9
  21. package/.claude/commands/board.md +15 -15
  22. package/.claude/commands/build.md +47 -47
  23. package/.claude/commands/dashboard.md +17 -17
  24. package/.claude/commands/design.md +31 -31
  25. package/.claude/commands/findings-all.md +14 -14
  26. package/.claude/commands/findings-business.md +7 -7
  27. package/.claude/commands/findings-legal.md +7 -7
  28. package/.claude/commands/findings-perf.md +7 -7
  29. package/.claude/commands/findings-security.md +9 -9
  30. package/.claude/commands/findings-tech.md +7 -7
  31. package/.claude/commands/findings-ux.md +7 -7
  32. package/.claude/commands/fix-bug.md +15 -15
  33. package/.claude/commands/freeze.md +8 -8
  34. package/.claude/commands/handoff.md +38 -38
  35. package/.claude/commands/kit-update.md +17 -14
  36. package/.claude/commands/language.md +13 -0
  37. package/.claude/commands/maintain.md +19 -19
  38. package/.claude/commands/plan-task.md +32 -32
  39. package/.claude/commands/qa.md +17 -17
  40. package/.claude/commands/release.md +40 -40
  41. package/.claude/commands/research.md +31 -31
  42. package/.claude/commands/retro.md +32 -32
  43. package/.claude/commands/review-changes.md +15 -15
  44. package/.claude/commands/rollback.md +24 -24
  45. package/.claude/commands/start.md +116 -113
  46. package/.claude/commands/tools.md +11 -11
  47. package/.claude/commands/user-feedback.md +11 -11
  48. package/.claude/commands/wrap-up.md +18 -18
  49. package/.claude/findings/lenses/business.md +24 -24
  50. package/.claude/findings/lenses/legal.md +29 -29
  51. package/.claude/findings/lenses/perf.md +19 -19
  52. package/.claude/findings/lenses/security.md +30 -30
  53. package/.claude/findings/lenses/tech.md +23 -23
  54. package/.claude/findings/lenses/ux.md +19 -19
  55. package/.claude/findings/protocol.md +54 -54
  56. package/.claude/findings/report-template.md +30 -30
  57. package/.claude/hooks/budget.mjs +7 -7
  58. package/.claude/hooks/checkpoint.mjs +12 -12
  59. package/.claude/hooks/commit-gate.mjs +38 -37
  60. package/.claude/hooks/cost.mjs +2 -2
  61. package/.claude/hooks/council.mjs +3 -3
  62. package/.claude/hooks/dashboard-data.mjs +4 -3
  63. package/.claude/hooks/dashboard.mjs +164 -149
  64. package/.claude/hooks/destructive-guard.mjs +74 -64
  65. package/.claude/hooks/edit-rounds.mjs +3 -3
  66. package/.claude/hooks/flow.mjs +10 -10
  67. package/.claude/hooks/freeze-guard.mjs +27 -23
  68. package/.claude/hooks/gate.mjs +25 -25
  69. package/.claude/hooks/guard-secrets.mjs +11 -11
  70. package/.claude/hooks/lang.mjs +114 -0
  71. package/.claude/hooks/messages.mjs +495 -0
  72. package/.claude/hooks/models.mjs +14 -11
  73. package/.claude/hooks/notify.mjs +3 -2
  74. package/.claude/hooks/package-gate.mjs +17 -15
  75. package/.claude/hooks/plugins-sync.mjs +9 -9
  76. package/.claude/hooks/prefs.mjs +19 -19
  77. package/.claude/hooks/preview.mjs +11 -11
  78. package/.claude/hooks/progress.mjs +14 -14
  79. package/.claude/hooks/qa-report.mjs +11 -10
  80. package/.claude/hooks/reminder.mjs +6 -3
  81. package/.claude/hooks/session-start.mjs +23 -17
  82. package/.claude/hooks/shared.mjs +1 -1
  83. package/.claude/hooks/status-read.mjs +5 -4
  84. package/.claude/hooks/statusline.mjs +14 -11
  85. package/.claude/hooks/structure-guard.mjs +9 -9
  86. package/.claude/hooks/test-guard.mjs +12 -12
  87. package/.claude/hooks/tools.mjs +28 -29
  88. package/.claude/hooks/usage.mjs +18 -15
  89. package/.claude/output-styles/anlatici.md +28 -28
  90. package/.claude/security-patterns.json +3 -3
  91. package/.claude/settings.json +2 -0
  92. package/.claude/skills/logo-design/SKILL.md +42 -42
  93. package/.claude/skills/motion-video/SKILL.md +52 -52
  94. package/.claude/skills/source-research/SKILL.md +35 -35
  95. package/.claude/skills/ui-motion/SKILL.md +38 -38
  96. package/.github/workflows/kit-tests.yml +7 -7
  97. package/.github/workflows/npm-publish.yml +16 -16
  98. package/AGENTS.md +56 -56
  99. package/CHANGELOG.md +7 -7
  100. package/CLAUDE.md +5 -5
  101. package/README.md +199 -172
  102. package/README.tr.md +292 -0
  103. package/docs/architecture/overview.md +31 -31
  104. package/docs/architecture/stack.md +2 -2
  105. package/docs/archive/README.md +4 -4
  106. package/docs/decisions/adr-template.md +14 -14
  107. package/docs/decisions/log.md +10 -10
  108. package/docs/findings/README.md +13 -13
  109. package/docs/findings/config.md +13 -13
  110. package/docs/legal/privacy-kvkk.md +1 -1
  111. package/docs/operations/accounts.md +25 -25
  112. package/docs/operations/deploy-setup.md +64 -64
  113. package/docs/operations/feature-flags.md +17 -17
  114. package/docs/operations/maintenance.md +48 -48
  115. package/docs/operations/release-checklist.md +61 -61
  116. package/docs/operations/spend-alarms.md +28 -28
  117. package/docs/product/feedback.md +9 -8
  118. package/docs/product/glossary.md +16 -16
  119. package/docs/product/launch.md +28 -28
  120. package/docs/product/prd.md +43 -42
  121. package/docs/product/roadmap.md +31 -30
  122. package/docs/product/specs/_template.md +13 -12
  123. package/docs/product/unit-economics.md +23 -22
  124. package/docs/quality/metrics.md +14 -14
  125. package/docs/quality/retros.md +11 -11
  126. package/docs/quality/test-plan.md +48 -48
  127. package/docs/security/checklist.md +57 -57
  128. package/docs/workflow/board.md +7 -7
  129. package/docs/workflow/cost-log.md +4 -4
  130. package/docs/workflow/decision-protocol.md +70 -70
  131. package/docs/workflow/learning.md +4 -4
  132. package/docs/workflow/mcp-catalog.md +31 -31
  133. package/docs/workflow/models.md +35 -35
  134. package/docs/workflow/progress.md +7 -7
  135. package/docs/workflow/skills.md +108 -108
  136. package/docs/workflow/usage-limits.md +62 -62
  137. package/kit/CHANGELOG.md +882 -841
  138. package/kit/VERSION +1 -1
  139. package/kit/guide.html +713 -477
  140. package/kit/guide.tr.html +1328 -0
  141. package/kit/kit.mjs +56 -54
  142. package/kit/project/README.md +29 -29
  143. package/kit/project/gitignore +12 -12
  144. package/kit/templates/addons/ai/.env.example.append +5 -5
  145. package/kit/templates/addons/ai/ai/evals/README.md +11 -11
  146. package/kit/templates/addons/ai/ai/evals/cases.jsonl +2 -2
  147. package/kit/templates/addons/ai/ai/prompts/README.md +8 -8
  148. package/kit/templates/addons/ai/docs/ai/guide.md +56 -56
  149. package/kit/templates/backend/.claude/hooks/format.mjs +1 -1
  150. package/kit/templates/backend/.claude/structure.json +1 -1
  151. package/kit/templates/backend/.env.example +6 -6
  152. package/kit/templates/backend/.github/dependabot.yml +1 -1
  153. package/kit/templates/backend/.github/workflows/ci.yml +13 -13
  154. package/kit/templates/backend/.github/workflows/claude-ci-fix.yml +19 -19
  155. package/kit/templates/backend/.github/workflows/claude-maintenance.yml +18 -18
  156. package/kit/templates/backend/.github/workflows/live-monitoring.yml +14 -14
  157. package/kit/templates/backend/.pre-commit-config.yaml +3 -3
  158. package/kit/templates/backend/docs/architecture/stack.md +98 -98
  159. package/kit/templates/backend/docs/architecture/structure.md +34 -34
  160. package/kit/templates/mobile/.claude/structure.json +1 -1
  161. package/kit/templates/mobile/.env.example +6 -6
  162. package/kit/templates/mobile/.github/dependabot.yml +2 -2
  163. package/kit/templates/mobile/.github/workflows/ci.yml +18 -18
  164. package/kit/templates/mobile/.github/workflows/claude-ci-fix.yml +19 -19
  165. package/kit/templates/mobile/.github/workflows/claude-maintenance.yml +18 -18
  166. package/kit/templates/mobile/.gitignore.append +2 -2
  167. package/kit/templates/mobile/docs/architecture/stack.md +113 -113
  168. package/kit/templates/mobile/docs/architecture/structure.md +33 -33
  169. package/kit/templates/mobile/docs/design/design-guide.md +37 -37
  170. package/kit/templates/mobile/tests/security/rls.mjs +22 -22
  171. package/kit/templates/web-saas/.claude/structure.json +1 -1
  172. package/kit/templates/web-saas/.env.example +11 -11
  173. package/kit/templates/web-saas/.github/dependabot.yml +3 -3
  174. package/kit/templates/web-saas/.github/workflows/ci.yml +20 -20
  175. package/kit/templates/web-saas/.github/workflows/claude-ci-fix.yml +19 -19
  176. package/kit/templates/web-saas/.github/workflows/claude-maintenance.yml +18 -18
  177. package/kit/templates/web-saas/.github/workflows/live-monitoring.yml +12 -12
  178. package/kit/templates/web-saas/docs/architecture/stack.md +116 -116
  179. package/kit/templates/web-saas/docs/architecture/structure.md +44 -44
  180. package/kit/templates/web-saas/docs/design/design-guide.md +38 -38
  181. package/kit/templates/web-saas/tests/live/smoke.spec.ts +4 -4
  182. package/kit/templates/web-saas/tests/security/rls.mjs +22 -22
  183. package/kit/tools/codex/.codex/hooks.json +1 -1
  184. package/package.json +2 -2
  185. package/README.en.md +0 -267
@@ -1,7 +1,7 @@
1
- # Kitin npm paketini (tillerhand) yayınlar: v* tag'i push edilince. Projelere kopyalanmaz (kit/kit.mjs → KIT_ONLY).
2
- # Token yok: npm Trusted Publishing (OIDC). npmjs.com → tillerhand → Settings → Trusted Publisher: GitHub Actions,
3
- # burakdogrul / TillerHand / npm-publish.yml / environment: npm. Kaynak: docs.npmjs.com/trusted-publishers (2026-10-06).
4
- # Action'lar commit SHA'sına sabit (checkout v7.0.1, setup-node v7.1.0); yeni sürüme geçerken SHA'yı github.com/actions/<ad>/releases'tan al.
1
+ # Publishes the kit's npm package (tillerhand) when a v* tag is pushed. Not copied into projects (kit/kit.mjs → KIT_ONLY).
2
+ # No token: npm Trusted Publishing (OIDC). npmjs.com → tillerhand → Settings → Trusted Publisher: GitHub Actions,
3
+ # burakdogrul / TillerHand / npm-publish.yml / environment: npm. Source: docs.npmjs.com/trusted-publishers (2026-10-06).
4
+ # Actions are pinned to a commit SHA (checkout v7.0.1, setup-node v7.1.0); when moving to a new version, take the SHA from github.com/actions/<name>/releases.
5
5
  name: npm-publish
6
6
 
7
7
  on:
@@ -12,7 +12,7 @@ permissions:
12
12
  contents: read
13
13
 
14
14
  jobs:
15
- # Repo kodu (testler) yayın yetkisi olmadan koşar
15
+ # Repo code (tests) runs without publish permission
16
16
  test:
17
17
  runs-on: ubuntu-latest
18
18
  steps:
@@ -23,18 +23,18 @@ jobs:
23
23
  with:
24
24
  node-version: 24
25
25
  package-manager-cache: false # no cache in a release workflow (cache poisoning)
26
- - name: Tag main'deki bir commit'i mi gösteriyor
27
- run: git merge-base --is-ancestor "$GITHUB_SHA" origin/main || { echo "Tag main dalında değil, yayın durdu."; exit 1; }
28
- - name: Sürümler aynı mı (tag, package.json, kit/VERSION)
26
+ - name: Does the tag point to a commit on main
27
+ run: git merge-base --is-ancestor "$GITHUB_SHA" origin/main || { echo "The tag is not on main, publish stopped."; exit 1; }
28
+ - name: Are the versions the same (tag, package.json, kit/VERSION)
29
29
  run: |
30
30
  tag="${GITHUB_REF_NAME#v}"
31
31
  pkg=$(node -p "require('./package.json').version")
32
32
  kit=$(cat kit/VERSION)
33
33
  echo "tag=$tag package.json=$pkg kit/VERSION=$kit"
34
- [ "$tag" = "$pkg" ] && [ "$tag" = "$kit" ] || { echo "Sürümler farklı, yayın durdu."; exit 1; }
34
+ [ "$tag" = "$pkg" ] && [ "$tag" = "$kit" ] || { echo "The versions differ, publish stopped."; exit 1; }
35
35
  - run: node --test "kit/tests/*.test.mjs"
36
36
 
37
- # Sadece yayın: repo kodu çalıştırmaz, OIDC yetkisi yalnız burada
37
+ # Publish only: runs no repo code, the OIDC permission exists only here
38
38
  publish:
39
39
  needs: test
40
40
  runs-on: ubuntu-latest
@@ -49,19 +49,19 @@ jobs:
49
49
  node-version: 24
50
50
  package-manager-cache: false # no cache in a release workflow (cache poisoning)
51
51
  registry-url: https://registry.npmjs.org
52
- - name: npm sürümü (Trusted Publishing 11.5.1+ ister)
52
+ - name: npm version (Trusted Publishing needs 11.5.1+)
53
53
  run: node -e "const [a,b,c]=process.argv[1].split('.').map(Number); process.exit(a>11||(a===11&&(b>5||(b===5&&c>=1)))?0:1)" "$(npm --version)"
54
- # İlk yayını hesap sahibi elle yapar (2FA ile); bu sürüm zaten yayındaysa (elle yayınlandıysa) tekrar denenmez.
55
- # Sadece 404 "yok" sayılır; ağ veya sunucu hatası koşuyu durdurur.
56
- - name: Yayınlanacak mı
54
+ # The account owner does the first publish by hand (with 2FA); if this version is already published (by hand), it is not tried again.
55
+ # Only a 404 counts as "does not exist"; a network or server error stops the run.
56
+ - name: Should it be published
57
57
  id: check
58
58
  run: |
59
59
  v=$(node -p "require('./package.json').version")
60
60
  if out=$(npm view "tillerhand@$v" version 2>&1); then
61
- echo "::notice::tillerhand@$v zaten yayında; atlandı."
61
+ echo "::notice::tillerhand@$v is already published; skipped."
62
62
  elif echo "$out" | grep -q E404; then
63
63
  if npm view tillerhand name >/dev/null 2>&1; then echo "go=1" >> "$GITHUB_OUTPUT"
64
- else echo "::warning::tillerhand npm'de yok; ilk yayın elle yapılır, bu koşu atlandı."; fi
64
+ else echo "::warning::tillerhand does not exist on npm; the first publish is done by hand, this run was skipped."; fi
65
65
  else
66
66
  echo "$out"; exit 1
67
67
  fi
package/AGENTS.md CHANGED
@@ -1,67 +1,67 @@
1
1
  # [PROJE ADI]
2
2
 
3
- > [Tek cümle: Bu proje kimin için, hangi problemi çözüyor?]
3
+ > [One sentence: who is this project for, and what problem does it solve?]
4
4
 
5
- Bu dosya projenin ortak kurallarıdır; Claude Code, Codex ve Antigravity okur. Claude Code'a özel ekler `CLAUDE.md`'de.
5
+ This file holds the shared rules of the project. Claude Code, Codex and Antigravity read it. Claude Code-only additions are in `CLAUDE.md`.
6
6
 
7
- **Kurulum durumu:** Kökte `kit/` klasörü varsa ve `.kit.json` yoksa, ya da `.kit.json` → `type` boşsa (`null`) proje henüz kurulmamıştır. Kullanıcıya yeni projede `/start [fikir]`, klasörde var olan kod varsa `/adopt` öner; kurulum bitmeden kod yazma.
7
+ **Setup status:** The project is not set up yet if a `kit/` folder exists in the root and `.kit.json` does not, or if `.kit.json` → `type` is empty (`null`). Suggest `/start [idea]` to the user for a new project, and `/adopt` if the folder already has code. Do not write code before setup is done.
8
8
 
9
- **Oturum başı:** `docs/workflow/progress.md`'yi oku (güncel durum, sıradaki adım). Claude Code bunu kendisi yükler.
9
+ **Session start:** Read `docs/workflow/progress.md` (current state, next step). Claude Code loads it by itself.
10
10
 
11
- ## Temel kurallar (her zaman geçerli)
11
+ ## Core rules (always apply)
12
12
 
13
- 1. **Kararı kullanıcı verir.** Ürün, teknik, tasarım, içerik, veri, güvenlik ve maliyet kararlarında AskUserQuestion ile sor. 2-4 seçenek sun; önerin ilk sırada ve "(Önerilen)" etiketli olsun. Her seçenekte ne zaman daha iyi olduğunu ve bedelini yaz. Tasarım kararları görsel önizlemeyle sorulur. Soru modunda kapalı konularda önerileni seç ve "otomatik" diye kaydet. **İlk karar sorusundan önce `docs/workflow/decision-protocol.md`'yi oku.** Daha önce verilmiş kararlar `docs/decisions/log.md`'de; onları tekrar sorma. Her kararı tek yönlü / çift yönlü kapı olarak sınıfla; tek yönlülerde (veritabanı, auth, ödeme, veri modeli) önce kurul görüşü al.
14
- 2. **Uzman kurulu denetler** (`docs/workflow/board.md`, kurallar `.claude/board/rules.md`). Plan onayından önce, görev bitince, her commit'te (hafif) ve faz sonunda ilgili üyeler toplanır. Kurul danışmandır; RET (kritik bulgu) varsa iş bitmez, kullanıcıya sorulur.
15
- 3. **Doğru kaynak.** Sürüm, fiyat, kota, mevzuat, API gibi değişebilen bilgiyi hafızadan kullanma: `source-research` skill'i (önce birincil kaynak, her iddiaya kaynak ve tarih). Kütüphane kullanırken önce **Context7** MCP ile güncel dokümanı getir.
16
- 4. **Az token harca.** Kod haritası (codebase-memory-mcp) bağlıysa kodu keşfederken önce onu sorgula (`get_architecture`, `search_graph`, `trace_path`, `get_code_snippet`). Dosyaları toptan okuma. Dokümanları sadece gerektiğinde oku (tablo aşağıda).
17
- 5. **Yapıya uy (zorunlu).** Yeni dosyayı `.claude/structure.json` haritasındaki yerine yaz (özellik bazlı: `features/<özellik>/`); açıklaması `docs/architecture/structure.md`. Harita dışı yazım sorulur, dağınıklık dosyaları (`*.bak`, `*-old.*`, kopya) engellenir. Geçici ve deneme işleri `sandbox/`, artık geçerli olmayan dokümanlar `docs/archive/`. Haritayı değiştirmek teknik bir karardır.
18
- 6. **Önce plan, sonra kod.** 2'den fazla dosyaya dokunan iş `/plan-task`'dan geçer. Tek seferde tek görev. Kapsamı genişletme. Dört ilke: (1) varsayımını söyle, belirsizse sor; (2) en sade çözüm, istenmeyen esneklik yok; (3) sadece görevin gerektirdiği satırlara dokun; (4) işe başlarken doğrulanabilir başarı ölçütünü yaz.
19
- 7. **Kök neden, kanıt, test.** Kabul testleri (kriter kimliği test adında, `Ö-01.1`) ve saldırgan testleri koddan önce yazılır ve önce kırmızı olur. Testi kodu yazan değil, ayrı bir ajan (`test-writer`, test rolünün modeliyle) yazar; kodu yazan test dosyasına dokunmaz (test koruması engeller). Riskli özellik bayrak arkasında yayınlanır (`docs/operations/feature-flags.md`). Hata düzeltirken önce yeniden üret. "Bitti" demeden çalıştığını göster. Aynı hatada 2 denemede çözemezsen dur ve yön iste.
20
- 8. **Her cevabın sonunda durum bloğu** (kısa). Biçim:
13
+ 1. **The user decides.** Ask with AskUserQuestion for product, technical, design, content, data, security and cost decisions. Offer 2-4 options; put your recommendation first and label it "(Recommended)". For each option, state when it is better and what it costs. Ask design decisions with a visual preview. In question mode, pick the recommended option on closed topics and record it as `otomatik` in the decision log ("Auto decisions" in the status block). **Read `docs/workflow/decision-protocol.md` before the first decision question.** Earlier decisions are in `docs/decisions/log.md`; do not ask them again. Classify every decision as a one-way or two-way door; for one-way doors (database, auth, payment, data model), get the board's opinion first.
14
+ 2. **The expert board reviews** (`docs/workflow/board.md`, rules in `.claude/board/rules.md`). The relevant members meet before plan approval, when a task ends, at every commit (light) and at the end of a phase. The board only advises; if there is a RET (critical finding), the work is not done and the user is asked.
15
+ 3. **Right source.** Do not use information that can change from memory: versions, prices, quotas, regulation, APIs. Use the `source-research` skill (primary source first, every claim with source and date). When using a library, first fetch the current docs with the **Context7** MCP.
16
+ 4. **Spend few tokens.** If the code map (codebase-memory-mcp) is connected, query it first when exploring code (`get_architecture`, `search_graph`, `trace_path`, `get_code_snippet`). Do not read files in bulk. Read docs only when needed (table below).
17
+ 5. **Follow the structure (mandatory).** Write each new file to its place in the `.claude/structure.json` map (by feature: `features/<feature>/`); it is explained in `docs/architecture/structure.md`. Writing outside the map is asked about; clutter files (`*.bak`, `*-old.*`, copies) are blocked. Temporary and trial work goes to `sandbox/`, outdated docs to `docs/archive/`. Changing the map is a technical decision.
18
+ 6. **Plan first, then code.** Work that touches more than 2 files goes through `/plan-task`. One task at a time. Do not widen the scope. Four principles: (1) state your assumption, ask if unsure; (2) simplest solution, no flexibility nobody asked for; (3) touch only the lines the task needs; (4) write a verifiable success criterion when you start.
19
+ 7. **Root cause, evidence, tests.** Acceptance tests (criterion id in the test name, `Ö-01.1`) and adversarial tests are written before the code and are red first. A separate agent (`test-writer`, with the test role's model) writes the tests, not the one who writes the code; the code writer does not touch test files (test protection blocks it). Risky features ship behind a feature flag (`docs/operations/feature-flags.md`). When fixing a bug, reproduce it first. Show that it works before saying "done". If you cannot fix the same error in 2 attempts, stop and ask for direction.
20
+ 8. **A status block at the end of every answer** (short). Format:
21
21
 
22
22
  ```
23
- ── Durum ──────────────────────
24
- Aşama: … · Görev: … (x/y) · Soru modu: … · Limit: 5s %… hf %…
25
- Yapıldı: … · Kurul: … · Otomatik kararlar: …
26
- Sıradaki: … · bekleyen karar: …
23
+ ── Status ──────────────────────
24
+ Phase: … · Task: … (x/y) · Question mode: … · Limit: 5h %… weekly %…
25
+ Done: … · Board: … · Auto decisions: …
26
+ Next: … · pending decision: …
27
27
  ```
28
28
 
29
- 9. **Kullanıcıyı tanı.** Oturum başında gelen "Kişisel tercihler"e uy (proje kuralı önce gelir). Kullanıcı bir davranışını düzeltirse ya da nasıl çalışmak istediğini söylerse (konuşma, soru sıklığı, rapor biçimi, kod tarzı, kaçınılacaklar) kısaca not al; akışı bölme. Görev sonunda (`/build`) ve oturum sonunda (`/wrap-up`) notları AskUserQuestion ile çoklu seçim olarak sor ("Tercih olarak kaydedeyim mi?"). Seçilenleri `node .claude/hooks/prefs.mjs --add <konusma|sorular|raporlar|kod|kacin> "<tercih>"` ile yaz. Onaysız yazma. Sır, kişisel veri ya da proje adı yazma. Projeye özgü kural bu dosyaya değil "Öğrenilen kurallar"a gider.
29
+ 9. **Know the user.** Follow the "Personal preferences" that arrive at session start (project rules come first). If the user corrects a behavior or says how they want to work (conversation, question frequency, report format, code style, things to avoid), note it briefly; do not break the flow. At the end of a task (`/build`) and at the end of a session (`/wrap-up`), ask about the notes with AskUserQuestion as a multi-select ("Save as a preference?"). Write the selected ones with `node .claude/hooks/prefs.mjs --add <konusma|sorular|raporlar|kod|kacin> "<preference>"`. Do not write without approval. Do not write secrets, personal data or the project name. A project-specific rule goes to "Öğrenilen kurallar" (learned rules), not to this file.
30
30
 
31
31
  <!-- kit:other-tools -->
32
- ## Codex ve Antigravity'de
32
+ ## In Codex and Antigravity
33
33
 
34
- Kit Claude Code için yazıldı; bu iki araçta şu karşılıklar geçerli:
34
+ The kit was written for Claude Code; these equivalents apply in these two tools:
35
35
 
36
- - **Komutlar** (`/start`, `/build`…) `.agents/skills/` altında skill olarak durur: Codex'te `$start` ya da `/skills`, Antigravity'de `/start`. Kaynakları `.claude/commands/`; skill kopyaları kit güncellemesinde yeniden üretilir, düzenleme kaynakta yapılır.
37
- - **AskUserQuestion** geçen her yerde: Antigravity'de `ask_question` aracı. Seçenekli soru aracı yoksa (Codex) seçenekleri numaralı liste olarak yaz, önerileni ilk sıraya koy ve "(Önerilen)" diye işaretle, cevabı bekle. Karar yine kullanıcınındır.
38
- - **Alt ajanlar** (kurul üyeleri, konsey, inceleme ajanları `.claude/agents/`): Çalıştıramıyorsan ilgili tanımı oku, o rolle kendin değerlendir ve raporda "tek model" diye belirt. Test ayrımı (kural 7) burada hook ile zorlanamaz: testleri `test-writer` tanımıyla, kodu düşünmeden önce yaz ve kırmızıyı göster; kodu yazarken test dosyasını değiştirme.
39
- - **Model ve effort** (`docs/workflow/models.md`): Alt ajanı rolün karşılığıyla başlat (Codex: istemde model ve reasoning effort; Antigravity: `inherit`, `flash` ya da `pro`). Yapamıyorsan rolü kendin yürüt, modeli metinle öner.
40
- - **Korumalar** (sır engeli, yıkıcı komut kalkanı, yapı koruyucu, düzenleme kilidi, test koruması, düzenleme turu sayacı, paket kapısı ve Claude Code izin listesinin karşılığı) hook olarak çalışır: Codex `.codex/hooks.json`, Antigravity `.agents/hooks.json`. Kural ve koruma dosyalarına (`AGENTS.md`, `.claude/`, `.codex/`, `.agents/hooks.json`) yazma onaya bağlıdır. Engellenen işlemi başka yoldan (örneğin kabuk komutuyla) yapmaya çalışma; nedenini kullanıcıya söyle.
41
- - Claude Code eklentilerine ait skill'ler (adı `eklenti:skill` biçiminde) bu araçlarda yok: o adımı atla. Limit okuma ve durum çubuğu da yok: durum bloğunda limit "-" kalır.
36
+ - **Commands** (`/start`, `/build`…) live under `.agents/skills/` as skills: in Codex `$start` or `/skills`, in Antigravity `/start`. Their sources are in `.claude/commands/`; skill copies are regenerated on kit update, so edit the source.
37
+ - **Wherever AskUserQuestion appears:** in Antigravity, the `ask_question` tool. If there is no question tool with options (Codex), write the options as a numbered list, put the recommended one first and mark it "(Recommended)", then wait for the answer. The decision is still the user's.
38
+ - **Subagents** (board members, council, review agents in `.claude/agents/`): If you cannot run them, read the matching definition, assess as that role yourself and state "single model" in the report. The test separation (rule 7) cannot be enforced here by a hook: write the tests with the `test-writer` definition, before you think about the code, and show the red run; do not change the test file while writing the code.
39
+ - **Model and effort** (`docs/workflow/models.md`): Start the subagent with the role's equivalent (Codex: model and reasoning effort in the prompt; Antigravity: `inherit`, `flash` or `pro`). If you cannot, run the role yourself and suggest the model in text.
40
+ - **Protections** (secret block, destructive command shield, structure guard, edit lock, test protection, edit round counter, package gate and the equivalent of the Claude Code permission list) run as hooks: Codex `.codex/hooks.json`, Antigravity `.agents/hooks.json`. Writing to rule and protection files (`AGENTS.md`, `.claude/`, `.codex/`, `.agents/hooks.json`) needs approval. Do not try another route (for example a shell command) around a blocked action; tell the user why.
41
+ - Skills that belong to Claude Code plugins (named `plugin:skill`) do not exist in these tools: skip that step. There is also no limit reading and no status line: the limit stays "-" in the status block.
42
42
  <!-- /kit:other-tools -->
43
43
 
44
- ## Gerektiğinde oku
44
+ ## Read when needed
45
45
 
46
- | Dosya | Ne zaman |
46
+ | File | When |
47
47
  |---|---|
48
- | `docs/architecture/stack.md` | Kod yazarken: komutlar, kurallar, doğrulama yöntemi |
49
- | `docs/product/prd.md` | Kapsam veya kabul kriteri belirsizse |
50
- | `docs/architecture/overview.md`, `docs/product/glossary.md` | Yeni dosya/tablo/servis/kavram eklerken |
51
- | `docs/product/roadmap.md` | Görev seçerken ve işaretlerken |
52
- | `docs/design/design-guide.md`, `DESIGN.md`, `PRODUCT.md` | Arayüz işinde |
53
- | `docs/quality/test-plan.md`, `docs/security/checklist.md` | Kritik akış, auth, veri, ödeme koduna dokunurken |
54
- | `docs/workflow/models.md` | Alt ajan çağırırken (rolün modeli ve effort'u) |
55
- | `docs/ai/guide.md` (varsa) | Prompt veya model çağrısı işinde |
56
- | `docs/operations/accounts.md`, `docs/product/unit-economics.md` | Yeni dış servis, fiyat veya maliyet kararı |
57
- | `docs/operations/feature-flags.md` | Ödeme, AI, toplu bildirim, veri silen veya büyük arayüz değişikliği |
58
- | `docs/product/feedback.md`, `docs/quality/metrics.md` | Kullanıcı geri bildirimi, retro, bakım |
59
- | `docs/findings/<tür>/latest.md` | İlgili alanda iş yaparken: bilinen bulgular (`/findings-<tür>` raporları) |
48
+ | `docs/architecture/stack.md` | When writing code: commands, rules, verification method |
49
+ | `docs/product/prd.md` | When scope or an acceptance criterion is unclear |
50
+ | `docs/architecture/overview.md`, `docs/product/glossary.md` | When adding a new file/table/service/concept |
51
+ | `docs/product/roadmap.md` | When picking and marking tasks |
52
+ | `docs/design/design-guide.md`, `DESIGN.md`, `PRODUCT.md` | On interface work |
53
+ | `docs/quality/test-plan.md`, `docs/security/checklist.md` | When touching critical flow, auth, data or payment code |
54
+ | `docs/workflow/models.md` | When calling a subagent (the role's model and effort) |
55
+ | `docs/ai/guide.md` (if present) | On prompt or model-call work |
56
+ | `docs/operations/accounts.md`, `docs/product/unit-economics.md` | New external service, price or cost decision |
57
+ | `docs/operations/feature-flags.md` | Payment, AI, bulk notification, data-deleting or large interface change |
58
+ | `docs/product/feedback.md`, `docs/quality/metrics.md` | User feedback, retro, maintenance |
59
+ | `docs/findings/<type>/latest.md` | When working in the relevant area: known findings (`/findings-<type>` reports) |
60
60
 
61
61
  ## Komutlar
62
62
 
63
63
  ```bash
64
- # /start seçilen stack'e göre doldurur
64
+ # /start fills these in for the chosen stack
65
65
  geliştirme: [ ]
66
66
  önizleme: [ ]
67
67
  test: [ ]
@@ -70,27 +70,27 @@ tip kontrol: [ ]
70
70
  build: [ ]
71
71
  ```
72
72
 
73
- ## "Bitti" tanımı
73
+ ## Definition of "done"
74
74
 
75
- - [ ] Kabul kriterleri karşılandı; görevde çıkan kararlar soruldu ve kaydedildi
76
- - [ ] Lint, tip, testler temiz; kritik akışa dokunulduysa test eklendi
77
- - [ ] Hata, boş ve yükleniyor durumları ele alındı; çalıştığına dair kanıt gösterildi (doğrulama komutu bu turda çalıştırıldı ve çıktısı gösterildi; "çalışmalı" kanıt değildir)
78
- - [ ] Arayüz varsa: `DESIGN.md`'ye uygun, Impeccable critique yapıldı, metinler humanizer'dan geçti
79
- - [ ] Görev sonu kurul toplantısında RET yok
80
- - [ ] Kodda sır yok; yeni ortam değişkeni `.env.example`'da; `docs/product/roadmap.md` işaretli
75
+ - [ ] Acceptance criteria are met; decisions that came up in the task were asked and recorded
76
+ - [ ] Lint, types and tests are clean; a test was added if critical flow was touched
77
+ - [ ] Error, empty and loading states are handled; evidence that it works was shown (the verification command ran in this turn and its output was shown; "it should work" is not evidence)
78
+ - [ ] If there is an interface: matches `DESIGN.md`, Impeccable critique done, texts passed through humanizer
79
+ - [ ] No RET in the end-of-task board meeting
80
+ - [ ] No secrets in code; any new environment variable is in `.env.example`; `docs/product/roadmap.md` is marked
81
81
 
82
- ## Asla
82
+ ## Never
83
83
 
84
- - `.env` dosyalarını okuma, yazma, içeriğini ekrana basma. Sırrı koda, loga veya istemci tarafına koyma.
85
- - Onay almadan (soru modundan bağımsız): veri silme/sıfırlama, `git push --force`, `git reset --hard`, toplu dosya silme, prod deploy, para harcatan işlem.
86
- - Testi geçirmek için testi silme veya zayıflatma (test koruması hook'u sorar). Var olmayan API veya paket uydurma.
87
- - Hook'ları (sır engeli, commit kapısı) atlatmaya çalışma. Kullanıcı adına karar verip sonradan bildirme.
88
- - Koda, teste veya belgeye bu makineye özel mutlak yol yazma (`C:\Users\<ad>\…`, `/home/<ad>/…`, proje klasörünün tam yolu). Yolu proje kökünden, betiğin konumundan veya geçici klasörden türet; kapı yakalar. Bilinçli bir örnekse satıra `kit:yol-izinli` yaz.
84
+ - Do not read, write or print `.env` files. Do not put a secret in code, logs or client-side code.
85
+ - Do not do these without approval (regardless of question mode): data deletion/reset, `git push --force`, `git reset --hard`, bulk file deletion, prod deploy, any action that spends money.
86
+ - Do not delete or weaken a test to make it pass (the test protection hook asks). Do not invent APIs or packages that do not exist.
87
+ - Do not try to bypass hooks (secret block, commit gate). Do not decide for the user and report afterwards.
88
+ - Do not write a machine-specific absolute path into code, tests or docs (`C:\Users\<name>\…`, `/home/<name>/…`, the full project folder path). Derive the path from the project root, the script location or a temp folder; the gate catches it. For a deliberate example, write `kit:yol-izinli` on the line.
89
89
 
90
90
  ## Git
91
91
 
92
- Küçük ve sık commit. Mesaj biçimi: `tür: açıklama` (`feat`, `fix`, `refactor`, `docs`, `test`, `chore`, `wip`). `main` her zaman çalışır olmalı.
92
+ Small, frequent commits. Message format: `type: description` (`feat`, `fix`, `refactor`, `docs`, `test`, `chore`, `wip`). `main` must always work.
93
93
 
94
94
  ## Öğrenilen kurallar
95
95
 
96
- > `/fix-bug` aynı hata sınıfı tekrarlayınca, `/retro` dönem sonunda önerir; sen onaylarsan eklenir. Biçim: `- Kural. (kaynak: … · YYYY-AA-GG)`; tarih eklenme veya son gözden geçirme. En fazla ~10 satır. `/maintain monthly` 90 günden eskileri gözden geçirir.
96
+ > `/fix-bug` suggests when the same error class repeats, `/retro` suggests at the end of a period; added if you approve. Format: `- Rule. (kaynak: … · YYYY-AA-GG)`; the date is when it was added or last reviewed. At most ~10 lines. `/maintain monthly` reviews those older than 90 days.
package/CHANGELOG.md CHANGED
@@ -1,19 +1,19 @@
1
- # Değişiklik Günlüğü
1
+ # Changelog
2
2
 
3
- Biçim: [Keep a Changelog](https://keepachangelog.com/tr-TR/1.1.0/). Sürümleme: `MAJOR.MINOR.PATCH`.
3
+ Format: [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). Versioning: `MAJOR.MINOR.PATCH`.
4
4
 
5
5
  ## [Yayınlanmamış]
6
6
 
7
- ### Eklendi
7
+ ### Added
8
8
  -
9
9
 
10
- ### Değişti
10
+ ### Changed
11
11
  -
12
12
 
13
- ### Düzeltildi
13
+ ### Fixed
14
14
  -
15
15
 
16
16
  ## [0.1.0] - YYYY-AA-GG
17
17
 
18
- ### Eklendi
19
- - Proje iskeleti
18
+ ### Added
19
+ - Project skeleton
package/CLAUDE.md CHANGED
@@ -2,10 +2,10 @@
2
2
 
3
3
  @docs/workflow/progress.md
4
4
 
5
- ## Claude Code'a özel kurallar
5
+ ## Claude Code-specific rules
6
6
 
7
- Ortak kurallar `AGENTS.md`'de (yukarıda içe alındı). Bunlar onlara ektir:
7
+ The shared rules are in `AGENTS.md` (imported above). These are additions to them:
8
8
 
9
- - **Doğru skill'i kullan.** Kod: `ponytail:ponytail`. Kritik akış: `mattpocock-skills:tdd`. Arayüz: seçilen stil skill'i + `impeccable:impeccable`; hareket: `ui-motion`. Logo: `logo-design`. Tanıtım videosu: `motion-video`. Metin: `humanizer:humanizer`. Rapor dili: `caveman:caveman`. Tam tablo (ilk ihtiyaçta oku): `docs/workflow/skills.md`. Çekirdek dışı eklentiler paket olarak kapalı gelir; komut gerektirince açmayı sorar (`/tools`).
10
- - **Limiti ve bağlamı gözet** (`docs/workflow/usage-limits.md`). İş başlamadan limiti oku: masaüstünde `get_usage` aracı, terminalde `node .claude/hooks/usage.mjs`. Sarı/kırmızı seviyede tahmini maliyeti tek satırla söyle. Limit sadece uyarı sebebidir, işi durdurma: %90 hatırlat, %95 uyar ve "Kaldığı yer"i güncelle, %99 "yarım kalabilir" de; kullanıcı "dur" demedikçe devam et. Bağlam %50'yi geçince uygun noktada `/wrap-up` + `/clear` öner.
11
- - **Durum bloğu** caveman dilinde yazılır.
9
+ - **Use the right skill.** Code: `ponytail:ponytail`. Critical flow: `mattpocock-skills:tdd`. Interface: the chosen style skill + `impeccable:impeccable`; motion: `ui-motion`. Logo: `logo-design`. Promo video: `motion-video`. Text: `humanizer:humanizer`. Report language: `caveman:caveman`. Full table (read on first need): `docs/workflow/skills.md`. Non-core plugins come switched off as packages; when a command needs one, ask to switch it on (`/tools`).
10
+ - **Watch the limit and the context** (`docs/workflow/usage-limits.md`). Read the limit before starting work: the `get_usage` tool on desktop, `node .claude/hooks/usage.mjs` in the terminal. At yellow/red level, state the estimated cost in one line. The limit is only a reason to warn, not to stop work: remind at 90%, warn at 95% and update "Kaldığı yer" (where we left off), say "may be left unfinished" at 99%; keep going unless the user says "stop". When the context passes 50%, suggest `/wrap-up` + `/clear` at a suitable point.
11
+ - **The status block** is written in caveman style.