@codewizard-dt/bootstrap 3.2.0 → 5.1.0

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.
Files changed (59) hide show
  1. package/README.md +18 -60
  2. package/bin/cli.js +0 -5
  3. package/lib/hooks/README.md +14 -5
  4. package/lib/hooks/lib/command-parse.js +28 -0
  5. package/lib/hooks/package-install-consent.js +60 -2
  6. package/lib/prompts/README.md +0 -1
  7. package/lib/scripts/README.md +20 -13
  8. package/lib/scripts/bootstrap-prefs.js +20 -1
  9. package/lib/scripts/migrate-project.sh +1 -1
  10. package/lib/scripts/setup-project.sh +0 -1
  11. package/lib/scripts/sync-wiki-scaffold.sh +3 -15
  12. package/lib/scripts/templates/CLAUDE-wiki.md +4 -4
  13. package/lib/scripts/templates/bootstrap-prefs-schema.json +10 -1
  14. package/lib/scripts/templates/wiki/conventions.md +1 -1
  15. package/lib/scripts/templates/wiki/dashboard.html +2 -2
  16. package/lib/scripts/templates/wiki/index.md +4 -4
  17. package/lib/scripts/templates/wiki/work/requirements/index.md +1 -1
  18. package/lib/scripts/templates/wiki/work/requirements/lifecycle.md +2 -2
  19. package/lib/scripts/templates/wiki/work/roadmaps/index.md +1 -1
  20. package/lib/scripts/templates/wiki/work/roadmaps/lifecycle.md +4 -4
  21. package/lib/scripts/templates/wiki/work/tasks/index.md +1 -1
  22. package/lib/scripts/templates/wiki/work/tasks/lifecycle.md +6 -6
  23. package/lib/scripts/templates/wiki/work/uat/index.md +1 -1
  24. package/lib/scripts/templates/wiki/work/uat/lifecycle.md +4 -4
  25. package/lib/scripts/wiki-dashboard-server.js +1 -1
  26. package/lib/skills/README.md +3 -1
  27. package/lib/skills/architecture-audit/SKILL.md +207 -0
  28. package/lib/skills/bootstrap-config/SKILL.md +1 -1
  29. package/lib/skills/bug-assess/SKILL.md +137 -0
  30. package/lib/skills/bug-close/SKILL.md +2 -2
  31. package/lib/skills/bug-file/SKILL.md +9 -5
  32. package/lib/skills/decision-create/SKILL.md +5 -1
  33. package/lib/skills/power-mode/SKILL.md +10 -10
  34. package/lib/skills/primer/SKILL.md +1 -1
  35. package/lib/skills/req-compile/SKILL.md +2 -2
  36. package/lib/skills/req-create/SKILL.md +13 -9
  37. package/lib/skills/req-extract-decisions/SKILL.md +10 -10
  38. package/lib/skills/req-finalize/SKILL.md +3 -3
  39. package/lib/skills/req-retire/SKILL.md +10 -10
  40. package/lib/skills/req-update/SKILL.md +4 -4
  41. package/lib/skills/roadmap-assess/SKILL.md +58 -20
  42. package/lib/skills/roadmap-create/SKILL.md +22 -22
  43. package/lib/skills/roadmap-next/SKILL.md +10 -10
  44. package/lib/skills/security-audit/SKILL.md +3 -0
  45. package/lib/skills/tackle/SKILL.md +3 -3
  46. package/lib/skills/task-add/SKILL.md +22 -22
  47. package/lib/skills/task-audit/SKILL.md +2 -2
  48. package/lib/skills/task-trash/SKILL.md +4 -4
  49. package/lib/skills/uat-generate/SKILL.md +22 -22
  50. package/lib/skills/uat-skip/SKILL.md +21 -21
  51. package/lib/skills/uat-walk/UAT-CORE.md +6 -6
  52. package/lib/skills/wiki-lint/SKILL.md +1 -1
  53. package/package.json +2 -4
  54. package/.github/workflows/docker-harness.yml +0 -26
  55. package/.github/workflows/security.yml +0 -24
  56. package/.gitleaks.toml +0 -15
  57. package/lib/prompts/setup-deployment.md +0 -322
  58. package/lib/scripts/setup-deployment.sh +0 -113
  59. package/raw/guides/deployment-strategy.md +0 -448
@@ -75,9 +75,8 @@ done
75
75
  # missing => prompt in interactive mode (default no), skip silently
76
76
  # otherwise. Opt out by deleting the file/dir (costs one default-no
77
77
  # prompt per interactive update).
78
- # mcp-tools.md is assembled per-project by build-mcp-guide.sh, and
79
- # deployment-strategy.md is delivered only by setup-deployment.sh
80
- # (`bootstrap deploy`) — neither is synced here.
78
+ # mcp-tools.md is assembled per-project by build-mcp-guide.sh and is not
79
+ # synced here.
81
80
  GUIDES_SRC="$TEMPLATE_DIR/raw/guides"
82
81
  GUIDES_DST="$PROJECT_DIR/wiki/guides"
83
82
  LEGACY_GUIDES="$PROJECT_DIR/.docs/guides"
@@ -142,9 +141,7 @@ done
142
141
 
143
142
  # 4b. LEGACY MIGRATION: guides used to live in .docs/guides/. Every
144
143
  # template-owned guide found there is removed (fresh copies now land in
145
- # wiki/guides/ above); deployment-strategy.md is MOVED to wiki/guides/
146
- # when `bootstrap deploy` has run (its build.yml marker exists) and
147
- # deleted otherwise. User-authored files in .docs/guides/ are untouched.
144
+ # wiki/guides/ above). User-authored files in .docs/guides/ are untouched.
148
145
  # Also removes deprecated task-spec.md from either location (superseded by
149
146
  # wiki/work/tasks/lifecycle.md, which it actively contradicts).
150
147
  if [ -d "$LEGACY_GUIDES" ]; then
@@ -154,15 +151,6 @@ if [ -d "$LEGACY_GUIDES" ]; then
154
151
  echo " Migrated: removed .docs/guides/$legacy (guides now live in wiki/guides/)."
155
152
  fi
156
153
  done
157
- if [ -f "$LEGACY_GUIDES/deployment-strategy.md" ]; then
158
- if [ -f "$PROJECT_DIR/.github/workflows/build.yml" ]; then
159
- mv "$LEGACY_GUIDES/deployment-strategy.md" "$GUIDES_DST/deployment-strategy.md"
160
- echo " Migrated: moved deployment-strategy.md to wiki/guides/ (deploy artifacts present)."
161
- else
162
- rm -f "$LEGACY_GUIDES/deployment-strategy.md"
163
- echo " Removed deployment-strategy.md (deploy-only guide; delivered by 'npx @codewizard-dt/bootstrap deploy')."
164
- fi
165
- fi
166
154
  # Drop the legacy dirs when empty; scratch content (.docs/demo etc.) is kept.
167
155
  rmdir "$LEGACY_GUIDES" 2>/dev/null && echo " Removed empty .docs/guides/." || true
168
156
  rmdir "$PROJECT_DIR/.docs" 2>/dev/null || true
@@ -19,11 +19,11 @@ CLAUDE.md This schema section.
19
19
 
20
20
  **`wiki/work/`** — stateful lifecycle artifacts, organized by status. Active files are **never moved** after creation; state lives in the `status:` frontmatter field. Each family has a `lifecycle.md` (schema + valid transitions), an `index.md` listing **only active items**, and an `archive/` subdirectory for terminal items. When an item leaves the active set, delete its line from the family index; terminal items may be moved to `archive/` by `/wiki-archive`.
21
21
 
22
- - `wiki/work/requirements/` — REQ-NNN
22
+ - `wiki/work/requirements/` — REQ-NNNN
23
23
  - `wiki/work/decisions/` — DEC-NNNN (per-decision `#DM`)
24
- - `wiki/work/roadmaps/` — ROADMAP-NNN
25
- - `wiki/work/tasks/` — TASK-NNN
26
- - `wiki/work/uat/` — UAT-NNN (own family, one per task)
24
+ - `wiki/work/roadmaps/` — ROADMAP-NNNN
25
+ - `wiki/work/tasks/` — TASK-NNNN
26
+ - `wiki/work/uat/` — UAT-NNNN (own family, one per task)
27
27
  - `wiki/work/bugs/` — BUG-NNNN
28
28
 
29
29
  **`wiki/guides/`** — template-owned reference guides delivered by the bootstrap tooling (MCP tool rules in `mcp-tools.md`, shell anti-patterns, opted-in frameworks like evals or type-checking templates). Read them and obey them; **never edit them** — they are refreshed by `npx @codewizard-dt/bootstrap update` and any local edit will be overwritten. They are infrastructure, not wiki content: no frontmatter, no index entries, exempt from the atomic-page rule.
@@ -66,7 +66,7 @@
66
66
  "scope": "project",
67
67
  "consumer": "installer",
68
68
  "summary": "Install a specific optional guide into wiki/guides/",
69
- "detail": "One key per entry in sync-wiki-scaffold.sh's OPTIONAL_GUIDES list (sync-wiki-scaffold.sh:88), keyed by the exact entry text including any extension — today that is guides.evals-framework.md and guides.type-checking-templates. true delivers the guide into wiki/guides/ on every run; false keeps it out and suppresses the per-run prompt. A guide already present in wiki/guides/ (or in the legacy .docs/guides/) is refreshed regardless of this key — existing opt-in wins, because the file on disk is the stronger signal than a stored answer. The required guide tier is never gated by these keys.",
69
+ "detail": "One key per entry in sync-wiki-scaffold.sh's OPTIONAL_GUIDES list (sync-wiki-scaffold.sh:87), keyed by the exact entry text including any extension — today that is guides.evals-framework.md and guides.type-checking-templates. true delivers the guide into wiki/guides/ on every run; false keeps it out and suppresses the per-run prompt. A guide already present in wiki/guides/ (or in the legacy .docs/guides/) is refreshed regardless of this key — existing opt-in wins, because the file on disk is the stronger signal than a stored answer. The required guide tier is never gated by these keys.",
70
70
  "values": "true | false",
71
71
  "default": null,
72
72
  "askedBy": "sync-wiki-scaffold.sh",
@@ -181,6 +181,15 @@
181
181
  "default": false,
182
182
  "askedBy": "install-global.sh"
183
183
  },
184
+ "packageInstall.consent": {
185
+ "scope": "project",
186
+ "consumer": "skill",
187
+ "summary": "Whether package-install-consent.js allows package-manager installs for this project",
188
+ "detail": "package-install-consent.js is a PreToolUse hook that today denies every package-manager install command (npm install, pip install, uvx --from, etc.) unconditionally. false (and unset, the default) keeps denying exactly as today — no behavior change for a project that has not opted in. 'ask' makes the hook emit permissionDecision: \"defer\", handing the decision back to Claude Code's own native permission prompt instead of denying outright — this is safe even under headless/bypass runs because Claude Code's own permission system is the one deciding, not this hook blocking. true makes the hook emit permissionDecision: \"allow\" outright, skipping any prompt at all.",
189
+ "values": "true | false | ask",
190
+ "default": false,
191
+ "askedBy": "/bootstrap-config"
192
+ },
184
193
  "research.persistToRaw": {
185
194
  "scope": "either",
186
195
  "consumer": "skill",
@@ -21,7 +21,7 @@ Why this is the one expensive-to-defer rule: typed links, Maps of Content, super
21
21
 
22
22
  Reference pages by a **stable identity**, not a raw file path — so links survive reorganization.
23
23
 
24
- - **Work families** carry an ID in frontmatter and filename: `REQ-NNN`, `DEC-NNNN` (per-decision `#DM`), `ROADMAP-NNN`, `TASK-NNN`, `UAT-NNN`, `BUG-NNNN`.
24
+ - **Work families** carry an ID in frontmatter and filename: `REQ-NNNN`, `DEC-NNNN` (per-decision `#DM`), `ROADMAP-NNNN`, `TASK-NNNN`, `UAT-NNNN`, `BUG-NNNN`.
25
25
  - **Knowledge pages** carry an `id` (kebab-case slug) plus an `aliases:` list of alternative names. Link by title/alias (`[[Karpathy]]`) rather than by path; the alias makes the reference durable even if the file moves.
26
26
 
27
27
  ## 3. Typed links
@@ -850,12 +850,12 @@
850
850
  // Two supported source formats:
851
851
  //
852
852
  // 1. Active-index bullet lines (all sub-parts optional):
853
- // - [TASK-NNN — Title](TASK-NNN-slug.md) — summary · status
853
+ // - [TASK-NNNN — Title](TASK-NNNN-slug.md) — summary · status
854
854
  // Separators matched literally: em dash — (U+2014) between title and
855
855
  // summary; middle dot · (U+00B7) before status suffix(es).
856
856
  //
857
857
  // 2. Archive-index table rows:
858
- // | [[TASK-NNN]] | Title | Final Status | Archived |
858
+ // | [[TASK-NNNN]] | Title | Final Status | Archived |
859
859
  // A data row is identified by its first cell being a [[...]] wiki-link
860
860
  // (the header and |----| separator rows fail that gate). Escaped
861
861
  // pipes (\|) inside cells are handled. Archive rows have no markdown
@@ -38,11 +38,11 @@ _(none yet)_ — one page per entity, filed by sub-type:
38
38
 
39
39
  Each family's `index.md` lists its **active items only** (completed/terminal items drop off the list; files never move — status lives in frontmatter).
40
40
 
41
- - **Requirements** — REQ-NNN. [Active index](work/requirements/index.md) · [lifecycle](work/requirements/lifecycle.md)
41
+ - **Requirements** — REQ-NNNN. [Active index](work/requirements/index.md) · [lifecycle](work/requirements/lifecycle.md)
42
42
  - **Decisions** — DEC-NNNN (per-decision `#DM`). [Active index](work/decisions/index.md) · [lifecycle](work/decisions/lifecycle.md)
43
- - **Roadmaps** — ROADMAP-NNN. [Active index](work/roadmaps/index.md) · [lifecycle](work/roadmaps/lifecycle.md)
44
- - **Tasks** — TASK-NNN. [Active index](work/tasks/index.md) · [lifecycle](work/tasks/lifecycle.md)
45
- - **UAT** — UAT-NNN, one per task. [Active index](work/uat/index.md) · [lifecycle](work/uat/lifecycle.md)
43
+ - **Roadmaps** — ROADMAP-NNNN. [Active index](work/roadmaps/index.md) · [lifecycle](work/roadmaps/lifecycle.md)
44
+ - **Tasks** — TASK-NNNN. [Active index](work/tasks/index.md) · [lifecycle](work/tasks/lifecycle.md)
45
+ - **UAT** — UAT-NNNN, one per task. [Active index](work/uat/index.md) · [lifecycle](work/uat/lifecycle.md)
46
46
  - **Bugs** — BUG-NNNN. [Active index](work/bugs/index.md) · [lifecycle](work/bugs/lifecycle.md)
47
47
 
48
48
  ---
@@ -7,6 +7,6 @@ updated: 2026-06-11
7
7
 
8
8
  Lists **only active** requirements (`draft`, `approved`). When an item leaves the active set (`retired`), delete its line here — the file itself never moves; status lives in its frontmatter. See the [lifecycle](lifecycle.md).
9
9
 
10
- Entry format: `- [REQ-NNN — Title](REQ-NNN-slug.md) — one-line summary · status`
10
+ Entry format: `- [REQ-NNNN — Title](REQ-NNNN-slug.md) — one-line summary · status`
11
11
 
12
12
  _(none yet)_
@@ -5,7 +5,7 @@ updated: 2026-06-11
5
5
 
6
6
  # Requirements Lifecycle
7
7
 
8
- Requirements (PRDs) capture the problem, personas, user stories, success metrics, and non-goals for a body of work. ID scheme: **REQ-NNN** (3-digit, zero-padded, globally unique). Filename: `REQ-NNN-slug.md`.
8
+ Requirements (PRDs) capture the problem, personas, user stories, success metrics, and non-goals for a body of work. ID scheme: **REQ-NNNN** (4-digit, zero-padded, globally unique). Filename: `REQ-NNNN-slug.md`.
9
9
 
10
10
  Active files are **never moved** after creation; state lives in the `status:` frontmatter field. Terminal items (`retired`) may be moved to [`archive/`](archive/) by `/wiki-archive`. The active set is tracked in [`index.md`](index.md).
11
11
 
@@ -13,7 +13,7 @@ Active files are **never moved** after creation; state lives in the `status:` fr
13
13
 
14
14
  | Key | Required | Notes |
15
15
  |-----|----------|-------|
16
- | `id` | yes | `REQ-NNN` |
16
+ | `id` | yes | `REQ-NNNN` |
17
17
  | `title` | yes | short requirement name |
18
18
  | `status` | yes | `draft \| approved \| retired` |
19
19
  | `created` / `updated` | yes | `YYYY-MM-DD` |
@@ -7,6 +7,6 @@ updated: 2026-06-11
7
7
 
8
8
  Lists **only active** roadmaps (`active`). When a roadmap completes (`done`), delete its line here — the file itself never moves; status lives in its frontmatter. See the [lifecycle](lifecycle.md).
9
9
 
10
- Entry format: `- [ROADMAP-NNN — Title](ROADMAP-NNN-slug.md) — one-line summary · N/M items checked`
10
+ Entry format: `- [ROADMAP-NNNN — Title](ROADMAP-NNNN-slug.md) — one-line summary · N/M items checked`
11
11
 
12
12
  _(none yet)_
@@ -5,7 +5,7 @@ updated: 2026-06-11
5
5
 
6
6
  # Roadmaps Lifecycle
7
7
 
8
- Execution-plan roadmaps: a goal, phases, and a hybrid checklist where each item is either a **task link** (`[TASK-NNN](../tasks/TASK-NNN-slug.md)`) or an **inline** checkbox item. ID scheme: **ROADMAP-NNN** (3-digit, zero-padded). Filename: `ROADMAP-NNN-slug.md`.
8
+ Execution-plan roadmaps: a goal, phases, and a hybrid checklist where each item is either a **task link** (`[TASK-NNNN](../tasks/TASK-NNNN-slug.md)`) or an **inline** checkbox item. ID scheme: **ROADMAP-NNNN** (4-digit, zero-padded). Filename: `ROADMAP-NNNN-slug.md`.
9
9
 
10
10
  Active files are **never moved** after creation; state lives in the `status:` frontmatter field. Terminal items (`done`) may be moved to [`archive/`](archive/) by `/wiki-archive`. The active set is tracked in [`index.md`](index.md).
11
11
 
@@ -13,12 +13,12 @@ Active files are **never moved** after creation; state lives in the `status:` fr
13
13
 
14
14
  | Key | Required | Notes |
15
15
  |-----|----------|-------|
16
- | `id` | yes | `ROADMAP-NNN` |
16
+ | `id` | yes | `ROADMAP-NNNN` |
17
17
  | `title` | yes | roadmap goal |
18
18
  | `status` | yes | `active \| done` |
19
19
  | `created` / `updated` | yes | `YYYY-MM-DD` |
20
20
  | `owner` | no | accountable person/role |
21
- | `linked_requirements` | no | `REQ-NNN` back-links |
21
+ | `linked_requirements` | no | `REQ-NNNN` back-links |
22
22
  | `linked_decisions` | no | `DEC-NNNN` back-links |
23
23
  | `tags` | no | discovery only |
24
24
 
@@ -28,5 +28,5 @@ Active files are **never moved** after creation; state lives in the `status:` fr
28
28
  active ──▶ done
29
29
  ```
30
30
 
31
- - **active** — at least one unchecked item remains. Items are added by editing the roadmap file directly, at creation via `/roadmap-create`, or via `/task-add --roadmap ROADMAP-NNN` (auto-links a new task); task-linked items auto-check when their task completes.
31
+ - **active** — at least one unchecked item remains. Items are added by editing the roadmap file directly, at creation via `/roadmap-create`, or via `/task-add --roadmap ROADMAP-NNNN` (auto-links a new task); task-linked items auto-check when their task completes.
32
32
  - **done** — every checklist item is checked. Completion is implicit; flip `status` to `done` when the last box is ticked.
@@ -7,6 +7,6 @@ updated: 2026-06-11
7
7
 
8
8
  Lists **only active** tasks (`todo`, `in-progress`). When a task leaves the active set (`done`, `trashed`), delete its line here — the file itself never moves; status lives in its frontmatter. See the [lifecycle](lifecycle.md).
9
9
 
10
- Entry format: `- [TASK-NNN — Title](TASK-NNN-slug.md) — one-line summary · status`
10
+ Entry format: `- [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line summary · status`
11
11
 
12
12
  _(none yet)_
@@ -5,7 +5,7 @@ updated: 2026-06-11
5
5
 
6
6
  # Tasks Lifecycle
7
7
 
8
- Execution-ready task files with `## Steps` checklists. ID scheme: **TASK-NNN** (3-digit, zero-padded). Filename: `TASK-NNN-slug.md`. UAT test files mirror task naming (**UAT-NNN**) and live in the sibling [`../uat/`](../uat/) family.
8
+ Execution-ready task files with `## Steps` checklists. ID scheme: **TASK-NNNN** (4-digit, zero-padded). Filename: `TASK-NNNN-slug.md`. UAT test files mirror task naming (**UAT-NNNN**) and live in the sibling [`../uat/`](../uat/) family.
9
9
 
10
10
  Active files are **never moved** after creation; state lives in the `status:` frontmatter field. Terminal items (`done`, `trashed`) may be moved to [`archive/`](archive/) by `/wiki-archive`. The active set is tracked in [`index.md`](index.md).
11
11
 
@@ -13,14 +13,14 @@ Active files are **never moved** after creation; state lives in the `status:` fr
13
13
 
14
14
  | Key | Required | Notes |
15
15
  |-----|----------|-------|
16
- | `id` | yes | `TASK-NNN` |
16
+ | `id` | yes | `TASK-NNNN` |
17
17
  | `title` | yes | task title |
18
18
  | `status` | yes | `todo \| in-progress \| done \| trashed` |
19
19
  | `created` / `updated` | yes | `YYYY-MM-DD` |
20
- | `depends_on` | no | `TASK-NNN` IDs that must finish first |
21
- | `blocks` | no | `TASK-NNN` IDs this one gates |
22
- | `parallel_safe_with` | no | `TASK-NNN` IDs safe to run concurrently |
23
- | `uat` | no | link to the matching `../uat/UAT-NNN-slug.md` |
20
+ | `depends_on` | no | `TASK-NNNN` IDs that must finish first |
21
+ | `blocks` | no | `TASK-NNNN` IDs this one gates |
22
+ | `parallel_safe_with` | no | `TASK-NNNN` IDs safe to run concurrently |
23
+ | `uat` | no | link to the matching `../uat/UAT-NNNN-slug.md` |
24
24
  | `tags` | no | discovery only |
25
25
 
26
26
  ## Status transitions
@@ -7,6 +7,6 @@ updated: 2026-06-11
7
7
 
8
8
  Lists **only active** UAT files (`pending`, `in-progress`, `failed`). When a UAT leaves the active set (`passed`, `skipped`, `trashed`), delete its line here — the file itself never moves; status lives in its frontmatter. See the [lifecycle](lifecycle.md).
9
9
 
10
- Entry format: `- [UAT-NNN — Title](UAT-NNN-slug.md) — verifies TASK-NNN · status`
10
+ Entry format: `- [UAT-NNNN — Title](UAT-NNNN-slug.md) — verifies TASK-NNNN · status`
11
11
 
12
12
  _(none yet)_
@@ -5,7 +5,7 @@ updated: 2026-06-11
5
5
 
6
6
  # UAT Lifecycle
7
7
 
8
- User-acceptance test files, one per task. ID scheme: **UAT-NNN** (3-digit, zero-padded) — the number **mirrors the task it verifies** (`UAT-014` ↔ `TASK-014`). Filename: `UAT-NNN-slug.md`.
8
+ User-acceptance test files, one per task. ID scheme: **UAT-NNNN** (4-digit, zero-padded) — the number **mirrors the task it verifies** (`UAT-0014` ↔ `TASK-0014`). Filename: `UAT-NNNN-slug.md`.
9
9
 
10
10
  Active files are **never moved** after creation; state lives in the `status:` frontmatter field. Terminal items (`passed`, `skipped`, `trashed`) may be moved to [`archive/`](archive/) by `/wiki-archive`. The active set is tracked in [`index.md`](index.md).
11
11
 
@@ -13,14 +13,14 @@ Active files are **never moved** after creation; state lives in the `status:` fr
13
13
 
14
14
  | Key | Required | Notes |
15
15
  |-----|----------|-------|
16
- | `id` | yes | `UAT-NNN` |
16
+ | `id` | yes | `UAT-NNNN` |
17
17
  | `title` | yes | UAT title |
18
18
  | `status` | yes | `pending \| in-progress \| passed \| failed \| skipped \| trashed` |
19
- | `task` | yes | `TASK-NNN` back-link to the task under test |
19
+ | `task` | yes | `TASK-NNNN` back-link to the task under test |
20
20
  | `created` / `updated` | yes | `YYYY-MM-DD` |
21
21
  | `tags` | no | discovery only |
22
22
 
23
- The body carries an `implements::[[TASK-NNN]]` typed link; the task carries a `uat:` frontmatter link back (`../uat/UAT-NNN-slug.md`).
23
+ The body carries an `implements::[[TASK-NNNN]]` typed link; the task carries a `uat:` frontmatter link back (`../uat/UAT-NNNN-slug.md`).
24
24
 
25
25
  ## Per-test markers
26
26
 
@@ -138,7 +138,7 @@ function listen(port, attempt) {
138
138
  }
139
139
  });
140
140
 
141
- server.listen(port, () => {
141
+ server.listen(port, '127.0.0.1', () => {
142
142
  console.log(`Wiki dashboard server running at http://localhost:${port}`);
143
143
  });
144
144
  }
@@ -19,7 +19,7 @@ Most skills operate on the LLM Wiki (`wiki/`, `raw/`) described in the root `CLA
19
19
 
20
20
  | Skill | Purpose |
21
21
  |-------|---------|
22
- | `req-create` | Draft a new requirement (REQ-NNN) via Socratic Q&A — problem, personas, user stories, success metrics, non-goals |
22
+ | `req-create` | Draft a new requirement (REQ-NNNN) via Socratic Q&A — problem, personas, user stories, success metrics, non-goals |
23
23
  | `req-finalize` | Run a completeness audit on a draft requirement, resolve gaps via Q&A, flip `status: draft → approved` |
24
24
  | `req-extract-decisions` | Extract Architecturally Significant Requirements from an approved requirement and propose Decision Group candidates |
25
25
  | `req-update` | Amend an approved requirement with a tracked, append-only Amendment block; direct edits for drafts |
@@ -67,6 +67,7 @@ Most skills operate on the LLM Wiki (`wiki/`, `raw/`) described in the root `CLA
67
67
  | Skill | Purpose |
68
68
  |-------|---------|
69
69
  | `bug-file` | File a new bug report with required-on-report fields; append it to the bug index |
70
+ | `bug-assess` | Survey all active bugs together — batch-triage any still-open reports first, then rank the active set by priority, severity, and impact into a single prioritized fix order with a status update for each bug |
70
71
  | `bug-triage` | Set priority/assignee/tags/impact, then advance to `in-progress`, keep `triaged`, or reject (wontfix/duplicate/cannot-reproduce) and archive |
71
72
  | `bug-close` | Close an in-progress bug — record root cause and resolution, require a regression test, move to `archive/` |
72
73
 
@@ -103,6 +104,7 @@ Most skills operate on the LLM Wiki (`wiki/`, `raw/`) described in the root `CLA
103
104
  | Skill | Purpose |
104
105
  |-------|---------|
105
106
  | `security-audit` | Audit an LLM/AI application across 11 categories — internal posture (observability, rate limiting, access controls, HITL policy, benchmarking) and external threats (prompt injection, data leakage, output XSS, excessive agency, supply chain, token DoS) |
107
+ | `architecture-audit` | Audit an AI agent/application's architecture across 9 categories — design fit (single- vs. multi-agent justification, orchestration topology, delegation hygiene, framework/SDK fit, compounding-error containment) and operational readiness (observability, cost/resource controls, context/state management, cross-agent safety composition) |
106
108
 
107
109
  ## Porting & extraction
108
110
 
@@ -0,0 +1,207 @@
1
+ ---
2
+ name: architecture-audit
3
+ description: Audit an AI agent/application's architecture across 9 categories — design fit (single- vs. multi-agent justification, orchestration topology, delegation hygiene, framework/SDK fit, compounding-error containment) and operational readiness (observability, cost/resource controls, context/state management, cross-agent safety composition). Run a full audit or a single named category.
4
+ category: researching
5
+ model: claude-opus-5
6
+ argument-hint: "[category-name | full]"
7
+ disable-model-invocation: false
8
+ user-invocable: true
9
+ ---
10
+
11
+ # AI Architecture Audit
12
+
13
+ Structured architecture audit of this project's agentic/LLM system design. **Audits and reports only — does not fix.**
14
+
15
+ **Invocation** `$ARGUMENTS`: empty/`full` → all 9 categories · named category (e.g. `orchestration-topology`) → that one · `design` → the 5 design-fit categories · `operations` → the 4 operational-readiness categories.
16
+
17
+ ## Setup (before any category)
18
+
19
+ 1. **Read project context** — `mcp__serena__list_dir` on root + key dirs (src, app, api, lib, server, agents, orchestrator, workflows, tools, skills).
20
+ 2. **Find the agentic surface** — orchestrator/lead-agent entry points, subagent or worker definitions, tool/function registries, agent framework imports (`langgraph`, `crewai`, `autogen`, `@anthropic-ai/claude-agent-sdk`, `openai-agents`, `google-adk`, `@mastra/*`, `ai` (Vercel AI SDK)), any workflow/pipeline DSL.
21
+ 3. **Establish the shape** — single agent, code-defined workflow, or multi-agent (and if multi-agent: how many roles, what topology connects them). This shape gates which checks below even apply.
22
+ 4. **Note deployment context** — is this repo the LLM application itself, or (as with `bootstrap-claude`) tooling that configures agent behavior for other projects/sessions. Adjust "codebase" checks accordingly — e.g. for a Claude Code skill/subagent system, the orchestrator is a skill file, not application code.
23
+
24
+ Use Serena `find_symbol` / `search_for_pattern` to locate code — never shell `grep`/`find`.
25
+
26
+ ## Category reference
27
+
28
+ | ID | Category | Group |
29
+ |----|----------|-------|
30
+ | `architecture-fit` | Single- vs. Multi-Agent Fit | Design |
31
+ | `orchestration-topology` | Orchestration Topology | Design |
32
+ | `delegation-hygiene` | Delegation & Prompt Hygiene | Design |
33
+ | `framework-fit` | Framework / SDK Fit | Design |
34
+ | `error-containment` | Compounding-Error Containment | Design |
35
+ | `observability` | Agent Observability & Tracing | Operations |
36
+ | `cost-resource-controls` | Cost & Resource Controls | Operations |
37
+ | `context-state-management` | Context & State Management | Operations |
38
+ | `safety-composition` | Cross-Agent Safety Composition | Operations |
39
+
40
+ ---
41
+
42
+ ## Design-fit categories
43
+
44
+ ### `architecture-fit` — Single- vs. Multi-Agent Fit
45
+ Multi-agent systems cost roughly 4-15x a single-chat interaction in tokens; the gain only shows up on genuinely breadth-first, parallelizable work. Teams that skip this check routinely build elaborate multi-agent systems that a better-prompted single agent would have matched.
46
+
47
+ | # | Check | How to verify |
48
+ |---|-------|---------------|
49
+ | AF1 | The task class this system targets is actually breadth-first/parallelizable (independent facets, independent files/records) rather than a single linear reasoning chain | Read the orchestrator's task-decomposition logic or prompt; does it fan out over genuinely independent units? |
50
+ | AF2 | A single-agent or code-defined-workflow baseline was tried/considered before multi-agent was adopted, or there's a documented reason it wasn't | Check ADRs/decision docs, comments, or commit history for the design rationale |
51
+ | AF3 | Subagent/team count scales with query complexity rather than being a fixed high number for every request | Find team-size logic — is there a simple/complex branch, or is it always N agents? |
52
+ | AF4 | The system doesn't spawn a new agent for tasks a single tool call or direct response could handle | Sample a few entry points — trace what triggers agent spawning vs. direct execution |
53
+ | AF5 | Token/cost multiplier of the multi-agent path vs. a single-agent equivalent has been measured or estimated, not assumed | Look for benchmarking, eval comparisons, or cost analysis docs |
54
+
55
+ **Severity if missing**: HIGH for AF1–AF2 (wrong default costs compound on every request), MEDIUM for AF3–AF5.
56
+
57
+ ### `orchestration-topology` — Orchestration Topology
58
+ The pattern that survives production is hierarchical orchestrator + isolated subagents; peer-to-peer "group chat" topologies have a documented failure mode where a single false premise cascades to 100% of agents.
59
+
60
+ | # | Check | How to verify |
61
+ |---|-------|---------------|
62
+ | OT1 | A single orchestrator/lead agent assigns work and owns final synthesis — subagents don't coordinate directly with each other | Trace message/control flow between agents |
63
+ | OT2 | Subagents are stateless or locally-scoped, not sharing a mutable global state that any agent can write | Check subagent context construction — do they receive isolated inputs? |
64
+ | OT3 | No peer-to-peer "group chat" / mesh topology where agents debate or negotiate directly without orchestrator mediation | Look for direct agent-to-agent message passing outside the orchestrator |
65
+ | OT4 | If a router/supervisor pattern is used instead of full orchestration, routing decisions are logged and deterministic where possible (not silently LLM-guessed) | Find the routing/classification step and its output handling |
66
+ | OT5 | Subagent results return to the orchestrator for verification/synthesis rather than being trusted and passed straight downstream | Trace what happens to a subagent's raw output after it returns |
67
+
68
+ **Severity if missing**: CRITICAL for OT3 (documented production failure mode), HIGH for OT1–OT2, MEDIUM for OT4–OT5.
69
+
70
+ ### `delegation-hygiene` — Delegation & Prompt Hygiene
71
+ Every subagent needs an explicit objective, output format, tool/source guidance, and task boundary; subagents should return distilled summaries, not full transcripts, back to the lead — raw transcripts pollute the lead's context and burn tokens at the multi-agent cost multiplier.
72
+
73
+ | # | Check | How to verify |
74
+ |---|-------|---------------|
75
+ | DH1 | Each subagent invocation carries an explicit objective and expected output format, not just a raw forwarded user request | Read subagent prompt-construction code/skill text |
76
+ | DH2 | Subagents are given explicit tool/source guidance and a task boundary (what's in scope, what's out) | Same — check for scope-limiting language |
77
+ | DH3 | Subagents return a distilled summary/result to the lead agent, not their full tool-call transcript | Check what's captured from a subagent call and passed back up |
78
+ | DH4 | Effort-scaling rules exist so a simple query can't accidentally spawn a large team | Find team-size/effort selection logic and its default |
79
+ | DH5 | Fresh (non-forked) subagents receive full necessary context in the prompt itself — the delegator doesn't assume shared memory the subagent doesn't have | Read a sample delegation prompt for self-containment |
80
+
81
+ **Severity if missing**: HIGH for DH1–DH3 (directly drives cost and quality), MEDIUM for DH4–DH5.
82
+
83
+ ### `framework-fit` — Framework / SDK Fit
84
+ Vendor-native SDKs win when committed to one provider; LangGraph earns its complexity only when graph/checkpointing durability is actually needed; CrewAI trades production maturity for prototyping speed; AutoGen is maintenance-only and shouldn't anchor new work.
85
+
86
+ | # | Check | How to verify |
87
+ |---|-------|---------------|
88
+ | FF1 | The chosen framework/SDK matches actual needs (durable checkpointing → LangGraph; single-provider → vendor-native SDK; fast prototyping → CrewAI; TS product backend → Mastra; TS UI+streaming → Vercel AI SDK) rather than being inherited by default | Check framework imports against what the system actually does with them |
89
+ | FF2 | The system is not built on AutoGen for new/active development | Check dependency manifests for `autogen`/`pyautogen` |
90
+ | FF3 | If a provider-neutral framework was chosen while only ever calling one model provider, there's a specific reason (multi-provider roadmap, need for the framework's graph/state machinery) | Check model client config vs. framework choice |
91
+ | FF4 | Framework version is pinned, and any framework-specific abstraction (state graph, crew config) is not duplicating functionality the vendor SDK already provides for free | Check lockfile/manifest pinning; look for redundant home-grown orchestration next to an already-capable framework |
92
+ | FF5 | If using the Claude Agent SDK, it's clearly distinguished in code/docs from the Messages API Tool Runner (`client.beta.messages.tool_runner`) — the former ships the full Claude Code harness (filesystem/bash tools included), the latter only loops over developer-defined tools | Check which package is imported and whether docs/comments describe its actual scope correctly |
93
+
94
+ **Severity if missing**: HIGH for FF2 (built on a retired framework), MEDIUM for FF1, FF3–FF5.
95
+
96
+ ### `error-containment` — Compounding-Error Containment
97
+ At 85% per-step accuracy, a 10-step chain succeeds only ~20% of the time; a wrong output at step N poisons every downstream agent's context, and summarization adds its own lossy error on top. The fix is architectural: decompose into small, independently verifiable units rather than one monolithic chain.
98
+
99
+ | # | Check | How to verify |
100
+ |---|-------|---------------|
101
+ | EC1 | Multi-step/multi-agent workflows are decomposed into atomic subtasks whose outputs can be independently verified before entering downstream context | Trace a workflow's step boundaries — is there a check between steps, or a blind pass-through? |
102
+ | EC2 | Long agent chains have an explicit accuracy/success expectation, not an assumption that each step is reliable | Look for retry logic, validation steps, or documented error budgets |
103
+ | EC3 | A verification or review step exists before a subagent's output is treated as ground truth by later steps (mirrors the code-review "verify" pattern already used elsewhere in this repo's own skills) | Check for a distinct verify/critique phase vs. single-pass execution |
104
+ | EC4 | Summarization steps (context compression, subagent-result distillation) are checked for information loss on critical facts, not applied uniformly with no spot-check | Find summarization logic and any safeguards around it |
105
+ | EC5 | Failure in one subtask degrades gracefully (partial result, flagged gap) rather than silently propagating a wrong answer through the rest of the pipeline | Trace error-handling paths from a subagent/tool failure |
106
+
107
+ **Severity if missing**: HIGH for EC1, EC3 (structural risk compounds silently), MEDIUM for EC2, EC4–EC5.
108
+
109
+ ---
110
+
111
+ ## Operational-readiness categories
112
+
113
+ ### `observability` — Agent Observability & Tracing
114
+ Without tracing of routing decisions, tool-call timing, and token/cost by agent, incidents in a multi-step system are nearly impossible to diagnose after the fact — and for a Claude Code–based system specifically, this may already be available for free via the harness's built-in OpenTelemetry export.
115
+
116
+ | # | Check | How to verify |
117
+ |---|-------|---------------|
118
+ | OB1 | Agent/tool-call spans are instrumented (ideally OTel GenAI semantic conventions: `gen_ai.*`, `invoke_agent`/`execute_tool` spans) so a request's full delegation chain is reconstructable | Search for tracing SDK usage, span creation around LLM/tool calls |
119
+ | OB2 | Token usage and cost are attributable per agent/subagent/skill, not just aggregated globally | Check metrics emission — is there a per-agent or per-role dimension? |
120
+ | OB3 | Tool-call timing and latency are captured, not just success/failure | Look for duration measurement around tool execution |
121
+ | OB4 | Routing/orchestration decisions (which subagent was chosen, why) are logged, not just their outcomes | Check orchestrator logging around the dispatch/routing step |
122
+ | OB5 | If this is a Claude Code–based system, `CLAUDE_CODE_ENABLE_TELEMETRY`/`OTEL_*` (built-in metrics, log events, beta distributed traces with nested subagent spans) has been evaluated and a decision made, not left unexamined | Check for any documentation, env config, or explicit decision record about Claude Code's native OTel export |
123
+ | OB6 | Telemetry defaults to structural data only (durations, model names, token counts) — prompt/tool-argument content logging is an explicit, reviewed opt-in, not a default | Check `OTEL_LOG_USER_PROMPTS`/`OTEL_LOG_TOOL_DETAILS`-equivalent flags and their default state |
124
+
125
+ **Severity if missing**: HIGH for OB1–OB4 (no incident-investigation capability), MEDIUM for OB5–OB6.
126
+
127
+ ### `cost-resource-controls` — Cost & Resource Controls
128
+ Recursive or looping agent calls and unscaled team sizes turn a benign request into a runaway cost; controls need to exist at the orchestration layer, not just the API layer.
129
+
130
+ | # | Check | How to verify |
131
+ |---|-------|---------------|
132
+ | CR1 | Agent recursion depth or iteration count is capped (circuit breaker on runaway delegation loops) | Search for max_iterations/max_depth guards in orchestration code |
133
+ | CR2 | Per-request or per-session token/cost budgets are enforced, with multi-agent fan-out counted against the same budget | Check budget/limit logic — does it account for subagent token spend, not just the top-level call? |
134
+ | CR3 | Concurrent subagent count is bounded (matches this repo's own convention of hard-coded team-size caps, e.g. min/max concurrency per orchestrator) | Check concurrency limits in the orchestrator |
135
+ | CR4 | A cost-anomaly alert exists for spend spikes attributable to agent/tool misbehavior | Check billing/cost monitoring config |
136
+ | CR5 | Timeouts exist on individual agent/tool calls so one hung step doesn't block or inflate the whole pipeline | Check timeout params on model/tool clients |
137
+
138
+ **Severity if missing**: HIGH for CR1–CR3 (direct runaway-cost risk), MEDIUM for CR4–CR5.
139
+
140
+ ### `context-state-management` — Context & State Management
141
+ Context window growth in multi-turn or multi-agent workflows must be bounded; unmanaged growth degrades quality and inflates cost, and naive summarization can silently drop critical facts.
142
+
143
+ | # | Check | How to verify |
144
+ |---|-------|---------------|
145
+ | CS1 | Conversation/session history is pruned, summarized, or windowed rather than growing unbounded across turns | Look for history management/truncation logic |
146
+ | CS2 | Subagent context is constructed explicitly per-call (fresh subagents get what they need in the prompt) rather than relying on implicit shared state | Check subagent invocation — is context assembled deliberately or inherited by default assumption? |
147
+ | CS3 | State that must persist across steps (task state, roadmap/task status, workflow progress) lives in a durable, inspectable store, not only in an LLM's working context | Check where cross-step state is actually written (files, DB, wiki) vs. held only in-context |
148
+ | CS4 | Any automatic context-compression feature (memory summarization, observational memory) has visibility into when it fires and what it costs, rather than running as an invisible background process | Check for logging/telemetry around compression events |
149
+ | CS5 | Long-running or resumable workflows checkpoint state so a crash or interruption doesn't require replaying the entire chain | Check for checkpoint/resume support in the workflow engine |
150
+
151
+ **Severity if missing**: HIGH for CS1, CS3 (direct cost/quality and correctness risk), MEDIUM for CS2, CS4–CS5.
152
+
153
+ ### `safety-composition` — Cross-Agent Safety Composition
154
+ Individually-benign behavior in each agent can compound into an unwanted *global* outcome across a multi-agent system — per-agent safety does not automatically compose into system-level safety.
155
+
156
+ | # | Check | How to verify |
157
+ |---|-------|---------------|
158
+ | SC1 | System-level behavior (not just each agent's individual output) is reviewed or tested — e.g. does the combination of subagent outputs ever produce an outcome no single agent would have produced alone? | Check for integration-level tests/evals beyond per-agent unit checks |
159
+ | SC2 | Destructive or irreversible actions require the same HITL gating regardless of which agent in the chain initiates them (a subagent can't bypass a gate the orchestrator enforces) | Trace a destructive action's authorization path when triggered by a subagent vs. the lead agent |
160
+ | SC3 | Shared resources/tools used by multiple agents have consistent permission scoping — one agent's tool grant isn't inherited by another via shared context | Check tool/permission assignment per agent role |
161
+ | SC4 | A quirk or drift in one agent's behavior (e.g. a subagent that over-triggers a tool) is monitored at the aggregate/system level, not just per-agent | Check for system-level monitoring/alerting distinct from per-agent logs |
162
+ | SC5 | Agent role boundaries are enforced structurally (scoped tools/prompts), not only by instruction — an agent shouldn't be able to talk itself into another agent's authority | Check whether role/tool restriction is code-level or prompt-level only |
163
+
164
+ **Severity if missing**: CRITICAL for SC2 (bypassable HITL gate), HIGH for SC1, SC3, MEDIUM for SC4–SC5.
165
+
166
+ ---
167
+
168
+ ## Reporting
169
+
170
+ **Output**: after compiling findings, write the full report to `.docs/architecture-audit/report-<YYYY-MM-DD>.md` using the **Write** tool (create the directory if it doesn't exist). If a report for today already exists, write `report-<YYYY-MM-DD>-2.md` (then `-3`, …) rather than overwriting, so architecture posture is trackable over time rather than a one-off snapshot. Print the same report in the conversation as well; the file is a durable copy, not a replacement for the reply.
171
+
172
+ **Per-check status:** ✅ PASS (control exists & effective) · ⚠️ WARN (partial / has gaps) · ❌ FAIL (no evidence; at risk) · ℹ️ N/A (not applicable to this architecture) · 🔍 NEEDS-REVIEW (can't determine from code — flag for manual review).
173
+
174
+ **Report structure:**
175
+ ```
176
+ ## AI Architecture Audit — [project] — [date]
177
+ Architecture shape: [single agent / code-defined workflow / multi-agent — N roles, topology]
178
+ Categories audited: [list]
179
+
180
+ ### [Category Name]
181
+ | Check | Status | Notes |
182
+ |-------|--------|-------|
183
+ | AF1 | ✅ | Task decomposition is genuinely breadth-first — see lib/skills/power-mode/SKILL.md:L… |
184
+ | OT3 | ❌ | Subagents pass results directly to each other outside orchestrator control |
185
+ **Category verdict**: FAIL (1+ CRITICAL failures)
186
+ **Priority mitigations**: [specific action + file reference] …
187
+
188
+ ### Summary
189
+ | Category | Verdict | Critical | High | Medium |
190
+ |----------|---------|----------|------|--------|
191
+ **Overall architecture posture**: [CRITICAL / HIGH / MEDIUM / LOW]
192
+ **Top 3 actions to take now**: 1. … 2. … 3. …
193
+ ```
194
+
195
+ **Verdict rules:** CRITICAL posture = any CRITICAL finding fails · HIGH = all CRITICAL pass but 2+ HIGH fail · MEDIUM = all CRITICAL & HIGH pass or WARN · LOW = only MEDIUM and below.
196
+
197
+ ## CRITICAL rules
198
+
199
+ 1. **Read code, don't run it** — verify architecture claims by reading implementation/skill definitions, never by attempting live load tests or real multi-agent runs.
200
+ 2. **Cite specific files and line numbers** for every PASS or FAIL — say where you looked; "no evidence found" alone is insufficient.
201
+ 3. **Serena for all code navigation** (`find_symbol`, `search_for_pattern`, `get_symbols_overview`) — no shell grep.
202
+ 4. **Flag NEEDS-REVIEW honestly** — controls needing runtime observation (e.g. actual token-cost multiplier, live cascade behavior) get flagged with what to verify manually.
203
+ 5. **Do not fix** — audit and report only; hand off fixes to the user or `/task-add`.
204
+ 6. **Scope to the repo** — don't speculate about external infra unless config files are present.
205
+ 7. **One category at a time** — complete each fully before the next; don't interleave findings.
206
+ 8. **Judge fit, not fashion** — a single agent that passes evaluation is not a finding against it; only flag multi-agent complexity, topology, or framework choice as a gap when it's mismatched to the actual task shape, not merely "not the newest pattern."
207
+ 9. **Persist the report** — write it to `.docs/architecture-audit/` (see Reporting) in addition to printing it; a report that only lives in the chat leaves no trail for the next audit to compare against.
@@ -112,7 +112,7 @@ Skip this question entirely when a mode word was supplied as an argument — but
112
112
  5. When the chosen key has `consumer: skill`, print this heavier banner:
113
113
  > This is a **skill preference**. Changing it changes what a slash command actually does the next time it runs — not merely whether the installer asks you a question.
114
114
 
115
- Name the affected command from the entry's `askedBy` / `summary` — e.g. `gitCommit.versionBump` changes what `/git-commit` does on every commit. The `consumer: skill` population is `gitCommit.versionBump`, `gitCommit.autoPush`, `gitCommit.lint`, `research.persistToRaw`, `research.autoIngest`, `uatGenerate.promoteTests`, and `gitignore.offerSectionUpdates`. Every other key is `consumer: installer` and gets the lighter framing: it only affects whether a setup/update script prompts you.
115
+ Name the affected command from the entry's `askedBy` / `summary` — e.g. `gitCommit.versionBump` changes what `/git-commit` does on every commit. The `consumer: skill` population is `gitCommit.versionBump`, `gitCommit.autoPush`, `gitCommit.lint`, `packageInstall.consent`, `research.persistToRaw`, `research.autoIngest`, `uatGenerate.promoteTests`, and `gitignore.offerSectionUpdates`. Every other key is `consumer: installer` and gets the lighter framing: it only affects whether a setup/update script prompts you.
116
116
 
117
117
  ## Step E — Choose the value and the layer (edit mode)
118
118