tillerhand 3.43.0 → 3.47.0
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.
- package/.claude/agents/board-chair.md +20 -20
- package/.claude/agents/code-reviewer.md +20 -20
- package/.claude/agents/council-advisor.md +14 -14
- package/.claude/agents/security-auditor.md +30 -30
- package/.claude/agents/test-writer.md +22 -22
- package/.claude/board/board-ai.md +25 -25
- package/.claude/board/board-api.md +25 -25
- package/.claude/board/board-architect.md +28 -28
- package/.claude/board/board-devops.md +25 -25
- package/.claude/board/board-mobile.md +25 -25
- package/.claude/board/board-performance.md +24 -24
- package/.claude/board/board-privacy.md +25 -25
- package/.claude/board/board-product.md +26 -26
- package/.claude/board/board-qa.md +28 -28
- package/.claude/board/board-ux.md +26 -26
- package/.claude/board/council.md +76 -76
- package/.claude/board/rules.md +61 -61
- package/.claude/claude-security-guidance.md +10 -10
- package/.claude/commands/adopt.md +70 -69
- package/.claude/commands/ask-mode.md +9 -9
- package/.claude/commands/board.md +15 -15
- package/.claude/commands/build.md +47 -47
- package/.claude/commands/dashboard.md +17 -17
- package/.claude/commands/design.md +31 -31
- package/.claude/commands/findings-all.md +14 -14
- package/.claude/commands/findings-business.md +7 -7
- package/.claude/commands/findings-legal.md +7 -7
- package/.claude/commands/findings-perf.md +7 -7
- package/.claude/commands/findings-security.md +9 -9
- package/.claude/commands/findings-tech.md +7 -7
- package/.claude/commands/findings-ux.md +7 -7
- package/.claude/commands/fix-bug.md +15 -15
- package/.claude/commands/freeze.md +8 -8
- package/.claude/commands/handoff.md +38 -38
- package/.claude/commands/kit-update.md +17 -14
- package/.claude/commands/language.md +13 -0
- package/.claude/commands/maintain.md +19 -19
- package/.claude/commands/plan-task.md +32 -32
- package/.claude/commands/qa.md +17 -17
- package/.claude/commands/release.md +40 -40
- package/.claude/commands/research.md +31 -31
- package/.claude/commands/retro.md +32 -32
- package/.claude/commands/review-changes.md +15 -15
- package/.claude/commands/rollback.md +24 -24
- package/.claude/commands/start.md +116 -113
- package/.claude/commands/tools.md +11 -11
- package/.claude/commands/user-feedback.md +11 -11
- package/.claude/commands/wrap-up.md +18 -18
- package/.claude/findings/lenses/business.md +24 -24
- package/.claude/findings/lenses/legal.md +29 -29
- package/.claude/findings/lenses/perf.md +19 -19
- package/.claude/findings/lenses/security.md +30 -30
- package/.claude/findings/lenses/tech.md +23 -23
- package/.claude/findings/lenses/ux.md +19 -19
- package/.claude/findings/protocol.md +54 -54
- package/.claude/findings/report-template.md +30 -30
- package/.claude/hooks/budget.mjs +7 -7
- package/.claude/hooks/checkpoint.mjs +12 -12
- package/.claude/hooks/commit-gate.mjs +38 -37
- package/.claude/hooks/cost.mjs +2 -2
- package/.claude/hooks/council.mjs +3 -3
- package/.claude/hooks/dashboard-data.mjs +3 -2
- package/.claude/hooks/dashboard.mjs +164 -149
- package/.claude/hooks/destructive-guard.mjs +74 -64
- package/.claude/hooks/edit-rounds.mjs +3 -3
- package/.claude/hooks/flow.mjs +10 -10
- package/.claude/hooks/freeze-guard.mjs +27 -23
- package/.claude/hooks/gate.mjs +25 -25
- package/.claude/hooks/guard-secrets.mjs +11 -11
- package/.claude/hooks/lang.mjs +114 -0
- package/.claude/hooks/messages.mjs +495 -0
- package/.claude/hooks/models.mjs +14 -11
- package/.claude/hooks/notify.mjs +3 -2
- package/.claude/hooks/package-gate.mjs +17 -15
- package/.claude/hooks/plugins-sync.mjs +9 -9
- package/.claude/hooks/prefs.mjs +19 -19
- package/.claude/hooks/preview.mjs +11 -11
- package/.claude/hooks/progress.mjs +14 -14
- package/.claude/hooks/qa-report.mjs +11 -10
- package/.claude/hooks/reminder.mjs +6 -3
- package/.claude/hooks/session-start.mjs +23 -17
- package/.claude/hooks/shared.mjs +1 -1
- package/.claude/hooks/status-read.mjs +5 -4
- package/.claude/hooks/statusline.mjs +14 -11
- package/.claude/hooks/structure-guard.mjs +9 -9
- package/.claude/hooks/test-guard.mjs +12 -12
- package/.claude/hooks/tools.mjs +28 -29
- package/.claude/hooks/usage.mjs +18 -15
- package/.claude/output-styles/anlatici.md +28 -28
- package/.claude/security-patterns.json +3 -3
- package/.claude/settings.json +2 -0
- package/.claude/skills/logo-design/SKILL.md +42 -42
- package/.claude/skills/motion-video/SKILL.md +52 -52
- package/.claude/skills/source-research/SKILL.md +35 -35
- package/.claude/skills/ui-motion/SKILL.md +38 -38
- package/.github/workflows/kit-tests.yml +7 -7
- package/.github/workflows/npm-publish.yml +16 -16
- package/AGENTS.md +56 -56
- package/CHANGELOG.md +7 -7
- package/CLAUDE.md +5 -5
- package/README.md +199 -172
- package/README.tr.md +292 -0
- package/docs/architecture/overview.md +31 -31
- package/docs/architecture/stack.md +2 -2
- package/docs/archive/README.md +4 -4
- package/docs/decisions/adr-template.md +14 -14
- package/docs/decisions/log.md +10 -10
- package/docs/findings/README.md +13 -13
- package/docs/findings/config.md +13 -13
- package/docs/legal/privacy-kvkk.md +1 -1
- package/docs/operations/accounts.md +25 -25
- package/docs/operations/deploy-setup.md +64 -64
- package/docs/operations/feature-flags.md +17 -17
- package/docs/operations/maintenance.md +48 -48
- package/docs/operations/release-checklist.md +61 -61
- package/docs/operations/spend-alarms.md +28 -28
- package/docs/product/feedback.md +9 -8
- package/docs/product/glossary.md +16 -16
- package/docs/product/launch.md +28 -28
- package/docs/product/prd.md +43 -42
- package/docs/product/roadmap.md +31 -30
- package/docs/product/specs/_template.md +13 -12
- package/docs/product/unit-economics.md +23 -22
- package/docs/quality/metrics.md +14 -14
- package/docs/quality/retros.md +11 -11
- package/docs/quality/test-plan.md +48 -48
- package/docs/security/checklist.md +57 -57
- package/docs/workflow/board.md +7 -7
- package/docs/workflow/cost-log.md +4 -4
- package/docs/workflow/decision-protocol.md +70 -70
- package/docs/workflow/learning.md +4 -4
- package/docs/workflow/mcp-catalog.md +31 -31
- package/docs/workflow/models.md +35 -35
- package/docs/workflow/progress.md +7 -7
- package/docs/workflow/skills.md +108 -108
- package/docs/workflow/usage-limits.md +62 -62
- package/kit/CHANGELOG.md +876 -841
- package/kit/VERSION +1 -1
- package/kit/guide.html +713 -477
- package/kit/guide.tr.html +1328 -0
- package/kit/kit.mjs +56 -54
- package/kit/project/README.md +29 -29
- package/kit/project/gitignore +12 -12
- package/kit/templates/addons/ai/.env.example.append +5 -5
- package/kit/templates/addons/ai/ai/evals/README.md +11 -11
- package/kit/templates/addons/ai/ai/evals/cases.jsonl +2 -2
- package/kit/templates/addons/ai/ai/prompts/README.md +8 -8
- package/kit/templates/addons/ai/docs/ai/guide.md +56 -56
- package/kit/templates/backend/.claude/hooks/format.mjs +1 -1
- package/kit/templates/backend/.claude/structure.json +1 -1
- package/kit/templates/backend/.env.example +6 -6
- package/kit/templates/backend/.github/dependabot.yml +1 -1
- package/kit/templates/backend/.github/workflows/ci.yml +13 -13
- package/kit/templates/backend/.github/workflows/claude-ci-fix.yml +19 -19
- package/kit/templates/backend/.github/workflows/claude-maintenance.yml +18 -18
- package/kit/templates/backend/.github/workflows/live-monitoring.yml +14 -14
- package/kit/templates/backend/.pre-commit-config.yaml +3 -3
- package/kit/templates/backend/docs/architecture/stack.md +98 -98
- package/kit/templates/backend/docs/architecture/structure.md +34 -34
- package/kit/templates/mobile/.claude/structure.json +1 -1
- package/kit/templates/mobile/.env.example +6 -6
- package/kit/templates/mobile/.github/dependabot.yml +2 -2
- package/kit/templates/mobile/.github/workflows/ci.yml +18 -18
- package/kit/templates/mobile/.github/workflows/claude-ci-fix.yml +19 -19
- package/kit/templates/mobile/.github/workflows/claude-maintenance.yml +18 -18
- package/kit/templates/mobile/.gitignore.append +2 -2
- package/kit/templates/mobile/docs/architecture/stack.md +113 -113
- package/kit/templates/mobile/docs/architecture/structure.md +33 -33
- package/kit/templates/mobile/docs/design/design-guide.md +37 -37
- package/kit/templates/mobile/tests/security/rls.mjs +22 -22
- package/kit/templates/web-saas/.claude/structure.json +1 -1
- package/kit/templates/web-saas/.env.example +11 -11
- package/kit/templates/web-saas/.github/dependabot.yml +3 -3
- package/kit/templates/web-saas/.github/workflows/ci.yml +20 -20
- package/kit/templates/web-saas/.github/workflows/claude-ci-fix.yml +19 -19
- package/kit/templates/web-saas/.github/workflows/claude-maintenance.yml +18 -18
- package/kit/templates/web-saas/.github/workflows/live-monitoring.yml +12 -12
- package/kit/templates/web-saas/docs/architecture/stack.md +116 -116
- package/kit/templates/web-saas/docs/architecture/structure.md +44 -44
- package/kit/templates/web-saas/docs/design/design-guide.md +38 -38
- package/kit/templates/web-saas/tests/live/smoke.spec.ts +4 -4
- package/kit/templates/web-saas/tests/security/rls.mjs +22 -22
- package/kit/tools/codex/.codex/hooks.json +1 -1
- package/package.json +2 -2
- package/README.en.md +0 -267
|
@@ -1,7 +1,7 @@
|
|
|
1
|
-
#
|
|
2
|
-
#
|
|
3
|
-
# burakdogrul / TillerHand / npm-publish.yml / environment: npm.
|
|
4
|
-
#
|
|
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
|
|
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:
|
|
27
|
-
run: git merge-base --is-ancestor "$GITHUB_SHA" origin/main || { echo "
|
|
28
|
-
- name:
|
|
26
|
+
- name: Does the tag point to a commit on main
|
|
27
|
+
run: git merge-base --is-ancestor "$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 "
|
|
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
|
-
#
|
|
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
|
|
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)" "$(npm --version)"
|
|
54
|
-
#
|
|
55
|
-
#
|
|
56
|
-
- name:
|
|
54
|
+
# The account owner does the first publish by hand (with 2FA); if this version is already published (by hand), it is not tried again.
|
|
55
|
+
# Only a 404 counts as "does not exist"; a network or server error stops the run.
|
|
56
|
+
- name: Should it be published
|
|
57
57
|
id: check
|
|
58
58
|
run: |
|
|
59
59
|
v=$(node -p "require('./package.json').version")
|
|
60
60
|
if out=$(npm view "tillerhand@$v" version 2>&1); then
|
|
61
|
-
echo "::notice::tillerhand@$v
|
|
61
|
+
echo "::notice::tillerhand@$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
|
|
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
|
-
> [
|
|
3
|
+
> [One sentence: who is this project for, and what problem does it solve?]
|
|
4
4
|
|
|
5
|
-
|
|
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
|
-
**
|
|
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
|
-
**
|
|
9
|
+
**Session start:** Read `docs/workflow/progress.md` (current state, next step). Claude Code loads it by itself.
|
|
10
10
|
|
|
11
|
-
##
|
|
11
|
+
## Core rules (always apply)
|
|
12
12
|
|
|
13
|
-
1. **
|
|
14
|
-
2. **
|
|
15
|
-
3. **
|
|
16
|
-
4. **
|
|
17
|
-
5. **
|
|
18
|
-
6.
|
|
19
|
-
7. **
|
|
20
|
-
8. **
|
|
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
|
-
──
|
|
24
|
-
|
|
25
|
-
|
|
26
|
-
|
|
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. **
|
|
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
|
|
32
|
+
## In Codex and Antigravity
|
|
33
33
|
|
|
34
|
-
|
|
34
|
+
The kit was written for Claude Code; these equivalents apply in these two tools:
|
|
35
35
|
|
|
36
|
-
- **
|
|
37
|
-
- **AskUserQuestion
|
|
38
|
-
- **
|
|
39
|
-
- **Model
|
|
40
|
-
- **
|
|
41
|
-
- Claude Code
|
|
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
|
-
##
|
|
44
|
+
## Read when needed
|
|
45
45
|
|
|
46
|
-
|
|
|
46
|
+
| File | When |
|
|
47
47
|
|---|---|
|
|
48
|
-
| `docs/architecture/stack.md` |
|
|
49
|
-
| `docs/product/prd.md` |
|
|
50
|
-
| `docs/architecture/overview.md`, `docs/product/glossary.md` |
|
|
51
|
-
| `docs/product/roadmap.md` |
|
|
52
|
-
| `docs/design/design-guide.md`, `DESIGN.md`, `PRODUCT.md` |
|
|
53
|
-
| `docs/quality/test-plan.md`, `docs/security/checklist.md` |
|
|
54
|
-
| `docs/workflow/models.md` |
|
|
55
|
-
| `docs/ai/guide.md` (
|
|
56
|
-
| `docs/operations/accounts.md`, `docs/product/unit-economics.md` |
|
|
57
|
-
| `docs/operations/feature-flags.md` |
|
|
58
|
-
| `docs/product/feedback.md`, `docs/quality/metrics.md` |
|
|
59
|
-
| `docs/findings/<
|
|
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
|
|
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
|
-
## "
|
|
73
|
+
## Definition of "done"
|
|
74
74
|
|
|
75
|
-
- [ ]
|
|
76
|
-
- [ ] Lint,
|
|
77
|
-
- [ ]
|
|
78
|
-
- [ ]
|
|
79
|
-
- [ ]
|
|
80
|
-
- [ ]
|
|
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
|
-
##
|
|
82
|
+
## Never
|
|
83
83
|
|
|
84
|
-
- `.env`
|
|
85
|
-
-
|
|
86
|
-
-
|
|
87
|
-
-
|
|
88
|
-
-
|
|
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
|
-
|
|
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`
|
|
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
|
-
#
|
|
1
|
+
# Changelog
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
Format: [Keep a Changelog](https://keepachangelog.com/en/1.1.0/). Versioning: `MAJOR.MINOR.PATCH`.
|
|
4
4
|
|
|
5
5
|
## [Yayınlanmamış]
|
|
6
6
|
|
|
7
|
-
###
|
|
7
|
+
### Added
|
|
8
8
|
-
|
|
9
9
|
|
|
10
|
-
###
|
|
10
|
+
### Changed
|
|
11
11
|
-
|
|
12
12
|
|
|
13
|
-
###
|
|
13
|
+
### Fixed
|
|
14
14
|
-
|
|
15
15
|
|
|
16
16
|
## [0.1.0] - YYYY-AA-GG
|
|
17
17
|
|
|
18
|
-
###
|
|
19
|
-
-
|
|
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
|
|
5
|
+
## Claude Code-specific rules
|
|
6
6
|
|
|
7
|
-
|
|
7
|
+
The shared rules are in `AGENTS.md` (imported above). These are additions to them:
|
|
8
8
|
|
|
9
|
-
- **
|
|
10
|
-
- **
|
|
11
|
-
- **
|
|
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.
|