@codewizard-dt/bootstrap 4.0.0 → 5.3.0

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 (53) hide show
  1. package/README.md +18 -60
  2. package/lib/prompts/README.md +0 -1
  3. package/lib/scripts/README.md +1 -2
  4. package/lib/scripts/migrate-project.sh +1 -1
  5. package/lib/scripts/setup-project.sh +0 -1
  6. package/lib/scripts/sync-wiki-scaffold.sh +3 -15
  7. package/lib/scripts/templates/CLAUDE-wiki.md +4 -4
  8. package/lib/scripts/templates/bootstrap-prefs-schema.json +1 -1
  9. package/lib/scripts/templates/wiki/conventions.md +4 -2
  10. package/lib/scripts/templates/wiki/dashboard.html +2 -2
  11. package/lib/scripts/templates/wiki/index.md +4 -4
  12. package/lib/scripts/templates/wiki/work/requirements/index.md +1 -1
  13. package/lib/scripts/templates/wiki/work/requirements/lifecycle.md +2 -2
  14. package/lib/scripts/templates/wiki/work/roadmaps/index.md +1 -1
  15. package/lib/scripts/templates/wiki/work/roadmaps/lifecycle.md +4 -4
  16. package/lib/scripts/templates/wiki/work/tasks/index.md +1 -1
  17. package/lib/scripts/templates/wiki/work/tasks/lifecycle.md +6 -6
  18. package/lib/scripts/templates/wiki/work/uat/index.md +1 -1
  19. package/lib/scripts/templates/wiki/work/uat/lifecycle.md +4 -4
  20. package/lib/scripts/wiki-dashboard-server.js +1 -1
  21. package/lib/skills/README.md +2 -1
  22. package/lib/skills/architecture-audit/SKILL.md +228 -0
  23. package/lib/skills/bug-close/SKILL.md +5 -2
  24. package/lib/skills/bug-file/SKILL.md +24 -6
  25. package/lib/skills/decision-create/SKILL.md +7 -2
  26. package/lib/skills/demo/SKILL.md +10 -10
  27. package/lib/skills/elevator-pitch/SKILL.md +1 -1
  28. package/lib/skills/extract-feature/SKILL.md +29 -87
  29. package/lib/skills/marp-slideshow/SKILL.md +2 -2
  30. package/lib/skills/port-feature/SKILL.md +28 -83
  31. package/lib/skills/power-mode/SKILL.md +10 -10
  32. package/lib/skills/primer/SKILL.md +1 -1
  33. package/lib/skills/req-compile/SKILL.md +2 -2
  34. package/lib/skills/req-create/SKILL.md +13 -9
  35. package/lib/skills/req-extract-decisions/SKILL.md +10 -10
  36. package/lib/skills/req-finalize/SKILL.md +3 -3
  37. package/lib/skills/req-retire/SKILL.md +10 -10
  38. package/lib/skills/req-update/SKILL.md +4 -4
  39. package/lib/skills/roadmap-assess/SKILL.md +7 -7
  40. package/lib/skills/roadmap-create/SKILL.md +26 -22
  41. package/lib/skills/roadmap-next/SKILL.md +10 -10
  42. package/lib/skills/security-audit/SKILL.md +3 -0
  43. package/lib/skills/tackle/SKILL.md +3 -3
  44. package/lib/skills/task-add/SKILL.md +41 -22
  45. package/lib/skills/task-audit/SKILL.md +2 -2
  46. package/lib/skills/task-trash/SKILL.md +4 -4
  47. package/lib/skills/uat-auto/SKILL.md +2 -1
  48. package/lib/skills/uat-generate/SKILL.md +22 -22
  49. package/lib/skills/uat-skip/SKILL.md +21 -21
  50. package/lib/skills/uat-walk/SKILL.md +1 -1
  51. package/lib/skills/uat-walk/UAT-CORE.md +6 -6
  52. package/lib/skills/wiki-lint/SKILL.md +28 -1
  53. package/package.json +1 -1
@@ -19,7 +19,7 @@ The hard boundary:
19
19
 
20
20
  > *A roadmap shows order. A task contains implementation steps. Never smuggle step-level detail into a roadmap item.*
21
21
 
22
- If a checkbox starts growing sub-bullets like "run `pnpm install`" or "edit `src/foo.ts`", that content belongs in a real task file — created via `/task-add` (or `/task-add --roadmap ROADMAP-NNN` to auto-link). Redirect the user when this happens.
22
+ If a checkbox starts growing sub-bullets like "run `pnpm install`" or "edit `src/foo.ts`", that content belongs in a real task file — created via `/task-add` (or `/task-add --roadmap ROADMAP-NNNN` to auto-link). Redirect the user when this happens.
23
23
 
24
24
  This skill drives a **short** Socratic Q&A session via `AskUserQuestion`. Roadmap creation is execution planning, not product strategy — keep questions focused and tight. Aim for one or two batched `AskUserQuestion` rounds plus per-phase follow-ups, not a full PRD-style interrogation.
25
25
 
@@ -51,17 +51,18 @@ If the topic is a single task with several steps, **stop and tell the user** —
51
51
  - `wiki/work/roadmaps/lifecycle.md` (frontmatter schema, status lifecycle — authoritative)
52
52
  - A sample of recent roadmaps in `wiki/work/roadmaps/` to learn local conventions
53
53
  - The active-task bullets in `wiki/work/tasks/index.md` so you know what task files already exist and can be linked
54
+ 4. **Prior-art scan (optional, cheap — skip silently if nothing plausible turns up):** read `wiki/index.md`'s `### Concepts` and `### Sources` sections for titles/summaries matching the topic, then run `mcp__serena__search_for_pattern` for the topic's key terms across `wiki/knowledge/concepts/` and `wiki/knowledge/sources/`. This is a scan-and-surface check, not a `/research` substitute — don't widen it into a full research pass. Any candidate hit gets confirmed with the user during Step 3's Q&A, never cited unconfirmed. If confirmed, its slug(s) populate the roadmap's `derived_from:` frontmatter field (array of `wiki/knowledge/{concepts,sources}` slugs — see ROADMAP-0013 for a precedent).
54
55
 
55
56
  ### Step 2: Locate the roadmap directory and assign a number
56
57
 
57
- Roadmaps live at `wiki/work/roadmaps/NNN-slug.md`. Numbers are 3-digit zero-padded.
58
+ Roadmaps live at `wiki/work/roadmaps/ROADMAP-NNNN-slug.md`. Numbers are 4-digit zero-padded.
58
59
 
59
- 1. **Use `mcp__serena__list_dir` on `wiki/work/roadmaps/` and `wiki/work/roadmaps/archive/`** (skip either that doesn't exist) to scan existing files. Collect every `NNN-` prefix from **both** directories — completed roadmaps move to `archive/` but keep their original number forever.
60
+ 1. **Use `mcp__serena__list_dir` on `wiki/work/roadmaps/` and `wiki/work/roadmaps/archive/`** (skip either that doesn't exist) to scan existing files. Collect the numeric value from every `ROADMAP-<digits>-` prefix across **both** directories, regardless of digit count (existing files are 3-digit; new ones are 4-digit) — ignore leading zeros when comparing.
60
61
  2. **Use `mcp__serena__search_for_pattern`** against `wiki/work/roadmaps/index.md` for `ROADMAP-\d{3}` entries — these may reserve numbers not yet on disk.
61
- 3. Take `max + 1`, zero-pad to 3 digits. The first roadmap is `001`.
62
+ 3. Take `max + 1`, zero-pad the result to 4 digits. In a brand-new project the first roadmap is `ROADMAP-0001`; in this repo, continue from the current max (do not restart at 1).
62
63
  4. **Derive the file slug** — names the **initiative**. Lowercase, dash-separated, ≤ 60 chars:
63
- - "Ship the billing portal" → `001-ship-billing-portal.md`
64
- - "Migrate to Postgres 17" → `004-migrate-postgres-17.md`
64
+ - "Ship the billing portal" → `ROADMAP-0001-ship-billing-portal.md`
65
+ - "Migrate to Postgres 17" → `ROADMAP-0004-migrate-postgres-17.md`
65
66
 
66
67
  Confirm the chosen number and slug with the user via `AskUserQuestion` only if either is non-obvious.
67
68
 
@@ -82,22 +83,24 @@ Walk through the elicitations below. Batch related questions into a single `AskU
82
83
  |-------|-------------------|
83
84
  | 1 | Goal, Phases, Owner, Linked PRD/ADRs |
84
85
 
86
+ If Step 1's prior-art scan surfaced candidate concept/source pages, fold a confirmation question into this same batch (or a short follow-up if the batch is already full): name the candidate page(s) and ask whether they're relevant to this roadmap. Confirmed hits become the `derived_from:` frontmatter value written in Step 6; unconfirmed or rejected candidates are dropped silently — never cited without confirmation.
87
+
85
88
  Then **per-phase**, in a single follow-up `AskUserQuestion` round (one question per phase, up to 4 — split into multiple rounds only if there are 5 phases):
86
89
 
87
90
  | # | Elicitation | Quality bar |
88
91
  |---|-------------|-------------|
89
- | 5 | **Phase N items** | For each phase, the user names (a) any existing tasks (`TASK-NNN` or slug fragments) that belong in this phase, and (b) any inline placeholder items. Items may be empty if the user wants to fill in later by editing the roadmap file directly or via `/task-add --roadmap ROADMAP-NNN` — but **at least one phase must contain at least one item** (a roadmap with zero items is not a roadmap) |
92
+ | 5 | **Phase N items** | For each phase, the user names (a) any existing tasks (`TASK-NNNN` or slug fragments) that belong in this phase, and (b) any inline placeholder items. Items may be empty if the user wants to fill in later by editing the roadmap file directly or via `/task-add --roadmap ROADMAP-NNNN` — but **at least one phase must contain at least one item** (a roadmap with zero items is not a roadmap) |
90
93
 
91
94
  When the user supplies a task reference:
92
95
 
93
- - Look it up in `wiki/work/tasks/` via `mcp__serena__find_file` to confirm it exists. The link must read `[[TASK-NNN: <task title>]]`.
96
+ - Look it up in `wiki/work/tasks/` via `mcp__serena__find_file` to confirm it exists. The link must read `[[TASK-NNNN: <task title>]]`.
94
97
  - If the user supplies a task reference that does **not** exist, treat it as an inline placeholder (do not fabricate a link). Note in the per-phase clarification that a task file must be created before this item can be worked on — it will be created automatically when `/roadmap-next` is run.
95
98
 
96
99
  **Inline placeholders**: items without a corresponding task file are written as `- [ ] <description>`. They are valid at creation time because tasks may not exist yet. However, **inline items cannot be worked on** — `/roadmap-next` will automatically invoke `/task-add` to create a task file for each inline item before surfacing it. The roadmap item is then upgraded to a task-link in place.
97
100
 
98
101
  **Redirection rule**: if the user starts spelling out implementation detail under an item (file paths, function names, sub-steps), respond:
99
102
 
100
- > That sounds like task content, not a roadmap item. Roadmaps show *ordering*. The *how* belongs in a task file — file one with `/task-add --roadmap ROADMAP-NNN <description>` and the roadmap will auto-link to it.
103
+ > That sounds like task content, not a roadmap item. Roadmaps show *ordering*. The *how* belongs in a task file — file one with `/task-add --roadmap ROADMAP-NNNN <description>` and the roadmap will auto-link to it.
101
104
 
102
105
  Then re-ask for a single checkbox-sized item.
103
106
 
@@ -110,7 +113,7 @@ Before writing the file, present a **tabular preview** of the roadmap:
110
113
  | Header | Title, Status (`active`), Owner, Linked PRD, Linked ADRs, Tags |
111
114
  | Goal | Full text |
112
115
  | Phases | Table of `Phase N` → `Name` → `# items` (task-link + inline counts) |
113
- | Per-phase items | One sub-list per phase showing each item's rendered form (`[[TASK-NNN: title]]` or inline text) |
116
+ | Per-phase items | One sub-list per phase showing each item's rendered form (`[[TASK-NNNN: title]]` or inline text) |
114
117
 
115
118
  The user confirms via `AskUserQuestion` with options like *Approve and write*, *Edit specific phase*, *Cancel*. Do **not** write the file until the user explicitly approves.
116
119
 
@@ -122,21 +125,22 @@ The number determined in Step 2 may now be stale (other roadmaps created mid-ses
122
125
 
123
126
  - `mcp__serena__list_dir` on `wiki/work/roadmaps/` **and** `wiki/work/roadmaps/archive/` (skip either that doesn't exist)
124
127
  - `mcp__serena__search_for_pattern` against `wiki/work/roadmaps/index.md` for `ROADMAP-\d{3}` entries
125
- - Collect every `NNN-` prefix from both directories, take `max + 1`, zero-pad to 3 digits
128
+ - Collect the numeric value from every `ROADMAP-<digits>-` prefix across both directories, regardless of digit count (existing files are 3-digit; new ones are 4-digit) — ignore leading zeros when comparing. Take `max + 1`, zero-pad the result to 4 digits.
126
129
  - If the number you planned to use in Step 4 has been taken, silently bump to the new next-available number and use it. Do not re-prompt the user.
127
130
  - **Never call `Write` before completing this re-scan.**
128
131
 
129
132
  ### Step 6: Write the roadmap file
130
133
 
131
- Use `Write` to create `wiki/work/roadmaps/NNN-slug.md` following the field table below and the item-rendering rules **exactly**; the frontmatter must match the schema in `wiki/work/roadmaps/lifecycle.md`.
134
+ Use `Write` to create `wiki/work/roadmaps/ROADMAP-NNNN-slug.md` following the field table below and the item-rendering rules **exactly**; the frontmatter must match the schema in `wiki/work/roadmaps/lifecycle.md`.
132
135
 
133
136
  | Field | Value at creation time |
134
137
  |-------|------------------------|
135
138
  | `Status` | `active` |
136
- | `aliases` | `[ROADMAP-NNN]` — mirrors the file's own `id:` value |
139
+ | `aliases` | `[ROADMAP-NNNN]` — mirrors the file's own `id:` value |
137
140
  | `Created` | Today's date (derive at runtime — use the conversation environment's `currentDate`, otherwise `date +%Y-%m-%d`) |
138
141
  | `Last updated` | Same as `Created` |
139
142
  | `Owner` | From Step 3 #3 |
143
+ | `derived_from` | Array of `wiki/knowledge/{concepts,sources}` slugs confirmed during Step 3's prior-art check, or omit the field entirely if none were confirmed — never invent entries |
140
144
  | `Linked PRD` | From Step 3 #4, or `—` |
141
145
  | `Linked ADRs` | From Step 3 #4, or `—` |
142
146
  | `Tags` | 1-3 short area tags inferred from the topic (e.g. `auth`, `billing`, `infra`). If the user did not name any, propose tags during Step 4's confirmation rather than inventing them silently |
@@ -146,7 +150,7 @@ Use `Write` to create `wiki/work/roadmaps/NNN-slug.md` following the field table
146
150
 
147
151
  **Item rendering rules**:
148
152
 
149
- - Task-link item: `- [ ] [[TASK-NNN: <task title>]]`
153
+ - Task-link item: `- [ ] [[TASK-NNNN: <task title>]]`
150
154
  - Inline item: `- [ ] <free-form description>`
151
155
 
152
156
  **Refuse to write** if:
@@ -165,7 +169,7 @@ Edit `wiki/work/roadmaps/index.md` to add a new bullet line (active items only
165
169
  2. If the placeholder line (`_(none yet)_` or a "no roadmaps yet" note) exists, **replace** it with the new line. Otherwise **append** the new line in numerical order.
166
170
  3. Use the entry format documented at the top of `index.md`:
167
171
 
168
- `- [ROADMAP-NNN — <title>](NNN-slug.md) — <one-line summary> · 0/<total> items checked`
172
+ `- [ROADMAP-NNNN — <title>](ROADMAP-NNNN-slug.md) — <one-line summary> · 0/<total> items checked`
169
173
 
170
174
  where `<title>` is the roadmap's H1 sub-title (without any `Roadmap NNN:` prefix), `<one-line summary>` is a short description of the goal, and `<total>` is the count of `- [ ]` checkboxes you just wrote across all phases.
171
175
 
@@ -181,7 +185,7 @@ Print a tabular summary:
181
185
 
182
186
  | Field | Value |
183
187
  |-------|-------|
184
- | File path | `wiki/work/roadmaps/NNN-slug.md` |
188
+ | File path | `wiki/work/roadmaps/ROADMAP-NNNN-slug.md` |
185
189
  | Status | `active` |
186
190
  | Phases | N |
187
191
  | Total items | M (task-link: X, inline: Y) |
@@ -189,9 +193,9 @@ Print a tabular summary:
189
193
  | Linked PRD | PRD-NNN or `—` |
190
194
  | Linked ADRs | list or `—` |
191
195
  | Index updated | yes (1 row added) |
192
- | Suggested next steps | `/roadmap-next wiki/work/roadmaps/NNN-slug.md` — surfaces the first item and creates task files for any inline placeholders • `/task-add --roadmap ROADMAP-NNN <description>` — file a new task auto-linked to this roadmap |
196
+ | Suggested next steps | `/roadmap-next wiki/work/roadmaps/ROADMAP-NNNN-slug.md` — surfaces the first item and creates task files for any inline placeholders • `/task-add --roadmap ROADMAP-NNNN <description>` — file a new task auto-linked to this roadmap |
193
197
 
194
- If any phase was left empty by design (user plans to fill it in later by editing the roadmap file directly or via `/task-add --roadmap ROADMAP-NNN`), note it in a separate **Gaps** section so the user can address it before execution begins.
198
+ If any phase was left empty by design (user plans to fill it in later by editing the roadmap file directly or via `/task-add --roadmap ROADMAP-NNNN`), note it in a separate **Gaps** section so the user can address it before execution begins.
195
199
 
196
200
  If the roadmap contains any inline placeholder items (items without a task-link), include a **Placeholders** section listing them:
197
201
 
@@ -208,17 +212,17 @@ This is informational only — no action required now.
208
212
  1. **Tables, not bullets, for every preview and summary in the conversation.** The roadmap file itself uses checklists (that's its format), but every Q&A preview and Step 8 report uses tables.
209
213
  2. **Phase names are short and execution-flavored.** "Foundation", "API", "Tests", "Release" — not "Phase where we figure out the database stuff".
210
214
  3. **Items are single checkbox-sized.** No sub-bullets, no indented steps, no embedded code blocks. If an item needs detail, it's a task — file one. Items without a task file are written as inline placeholders (`- [ ] <description>`) and are valid at creation time, but will be converted to task-links automatically by `/roadmap-next` before they can be worked on.
211
- 4. **Task-link items must use `[[TASK-NNN: <title>]]` format.** The `TASK-NNN:` prefix is required so the auto-checkoff machinery can detect references. Path-based markdown links break when files move to `archive/`; wiki-style ID links never do.
215
+ 4. **Task-link items must use `[[TASK-NNNN: <title>]]` format.** The `TASK-NNNN:` prefix is required so the auto-checkoff machinery can detect references. Path-based markdown links break when files move to `archive/`; wiki-style ID links never do.
212
216
  5. **At least one phase must contain at least one item.** An empty roadmap is a hard fail — loop back to Step 3 #5.
213
- 6. **Never invent task references.** If the user says "TASK-42" and no `042-*.md` file exists, render it as an inline placeholder, not a `[[TASK-NNN: ...]]` wiki link.
217
+ 6. **Never invent task references.** If the user says "TASK-42" and no `042-*.md` file exists, render it as an inline placeholder, not a `[[TASK-NNNN: ...]]` wiki link.
214
218
 
215
219
  ---
216
220
 
217
221
  ## CRITICAL Rules
218
222
 
219
223
  1. **Refuse to write the file if any required field is empty or fails its quality bar** (Goal, Owner, ≥1 phase with ≥1 item). Loop back to Step 3 — do not silently fill gaps with invented content.
220
- 2. **Never invent task links.** Every `[[TASK-NNN: ...]]` wiki link must correspond to a real file under `wiki/work/tasks/`. Verify with `mcp__serena__find_file` before rendering.
224
+ 2. **Never invent task links.** Every `[[TASK-NNNN: ...]]` wiki link must correspond to a real file under `wiki/work/tasks/`. Verify with `mcp__serena__find_file` before rendering.
221
225
  3. **Never use `sed`, `awk`, `echo >>`, or shell redirection to edit markdown.** Always `Read` then `Edit`. See `wiki/guides/mcp-tools.md`.
222
- 4. **Never auto-create downstream artifacts.** This skill creates exactly one roadmap file (plus the index row edit). Do **not** create tasks, PRDs, or ADRs as a side effect — the user can file tasks afterward via `/task-add --roadmap ROADMAP-NNN`.
226
+ 4. **Never auto-create downstream artifacts.** This skill creates exactly one roadmap file (plus the index row edit). Do **not** create tasks, PRDs, or ADRs as a side effect — the user can file tasks afterward via `/task-add --roadmap ROADMAP-NNNN`.
223
227
  5. **Redirect step-level detail to task territory** — if the user starts specifying *how* under an item, restate the question as "what's the single checkable unit?" and re-elicit.
224
228
  6. **Status starts as `active` and stays there.** This skill never writes `done`. The flip from `active` → `done` is a manual decision the human makes when every box is `[x]`. After flipping, the file may be moved to `wiki/work/roadmaps/archive/` — `/roadmap-next` will suggest this step.
@@ -20,7 +20,7 @@ Surface unchecked items in a single roadmap, grouped into parallelizable waves,
20
20
 
21
21
  This skill operates on exactly one roadmap — it no longer scans across all roadmaps. If `$ARGUMENTS` is empty, **stop** and report:
22
22
 
23
- > `/roadmap-next` requires a roadmap (path, `NNN-slug`, or number). Run `/roadmap-assess` to see a prioritized status update across all active roadmaps, then re-run `/roadmap-next <ROADMAP-NNN>` on the one you want to work.
23
+ > `/roadmap-next` requires a roadmap (path, `NNN-slug`, or number). Run `/roadmap-assess` to see a prioritized status update across all active roadmaps, then re-run `/roadmap-next <ROADMAP-NNNN>` on the one you want to work.
24
24
 
25
25
  ## Step 1: Resolve the file (`find_file`/`list_dir`, never bash)
26
26
 
@@ -40,7 +40,7 @@ Run the three shared procedures below, in order, on the resolved file.
40
40
 
41
41
  ### Parse a roadmap
42
42
 
43
- `Read` the file (markdown). Extract: **phases** (`## Phase N: <name>` in order), **items** (`- [ ]` unchecked / `- [x]` checked), **status** (`- **Status**: active | done`), and the `roadmap_id` (`- **ID**: ROADMAP-NNN` front matter or filename prefix, e.g. `003-billing.md` → `ROADMAP-003`). Per item capture: `phase` (nearest preceding heading, or `(no phase)`), `checked`, `text`, `kind` (`task-link` if body starts `[[TASK-NNN`, else `inline`), `task_id` (from `[[TASK-NNN: title]]`), `task_path` (`find_file` `TASK-NNN-*` in `wiki/work/tasks/` — matches active or archived). Compute `total`, `done`. Collect unchecked items into `candidate_items`, **capped at 9 total**.
43
+ `Read` the file (markdown). Extract: **phases** (`## Phase N: <name>` in order), **items** (`- [ ]` unchecked / `- [x]` checked), **status** (`- **Status**: active | done`), and the `roadmap_id` (`- **ID**: ROADMAP-NNNN` front matter — always read this first — or, as a fallback, the filename prefix, e.g. `ROADMAP-0013-billing.md` → `ROADMAP-0013`, or a legacy 3-digit file `ROADMAP-012-billing.md` → `ROADMAP-012`). Per item capture: `phase` (nearest preceding heading, or `(no phase)`), `checked`, `text`, `kind` (`task-link` if body starts `[[TASK-NNNN`, else `inline`), `task_id` (from `[[TASK-NNNN: title]]`), `task_path` (`find_file` `TASK-NNNN-*` in `wiki/work/tasks/` — matches active or archived). Compute `total`, `done`. Collect unchecked items into `candidate_items`, **capped at 9 total**.
44
44
 
45
45
  For each `candidate_items` item that is already `kind == 'task-link'` (skip this for `inline` items until after they're upgraded below): `Read` `task_path`'s frontmatter and store `task_status` (`todo | in-progress | pending-uat | done | trashed`, per [tasks lifecycle](../tasks/lifecycle.md)). If `task_status == 'pending-uat'`, also resolve `uat_path` — read the task's `uat:` frontmatter field if present and `find_file` it; if empty or not found, leave `uat_path` unset (implementation finished but `/uat-generate` hasn't run yet).
46
46
 
@@ -49,27 +49,27 @@ For each `candidate_items` item that is already `kind == 'task-link'` (skip this
49
49
  **All roadmap items must eventually be task files** — inline items are placeholders. For each `candidate_items` item with `kind == 'inline'`:
50
50
 
51
51
  1. Announce: `Inline item found: "<text>"[ (in <roadmap_title>)] — checking for an existing task before creating one.`
52
- 2. **Check for an existing task:** `Read` `wiki/work/tasks/index.md`, scan its active-item bullets for one whose title/summary plausibly covers the intent; if likely, `Read` that task to confirm. Found → use its `TASK-NNN` + path, skip to step 5 (do **not** call `task-add`).
52
+ 2. **Check for an existing task:** `Read` `wiki/work/tasks/index.md`, scan its active-item bullets for one whose title/summary plausibly covers the intent; if likely, `Read` that task to confirm. Found → use its `TASK-NNNN` + path, skip to step 5 (do **not** call `task-add`).
53
53
  3. Else invoke `Skill` `task-add` with the item text as `args` (**no** `--roadmap` flag — the link is managed here to avoid a duplicate item).
54
- 4. Extract the new task path + ID from task-add's summary (`File path` row); if parsing fails, `list_dir` `wiki/work/tasks/` for the newest `.md` not present before, and `Read` it to confirm `TASK-NNN` + title (from `# NNN: <title>`).
55
- 5. `Edit` the roadmap: `- [ ] <item_text>` → `- [ ] [[TASK-NNN: <title>]]`.
54
+ 4. Extract the new task path + ID from task-add's summary (`File path` row); if parsing fails, `list_dir` `wiki/work/tasks/` for the newest `.md` not present before, and `Read` it to confirm `TASK-NNNN` + title (from `# NNN: <title>`).
55
+ 5. `Edit` the roadmap: `- [ ] <item_text>` → `- [ ] [[TASK-NNNN: <title>]]`.
56
56
  6. Update the record: `kind='task-link'`, `task_id`, `task_path` (from `find_file`). A freshly created task is always `status: todo` — set `task_status = 'todo'` directly, no need to re-read the file.
57
57
 
58
58
  If `task-add` fails/cancels, **stop and report**: `Task creation cancelled for: "<text>"[ (in <roadmap_title>)]. Inline items cannot be worked on without a task file. Re-run /roadmap-next after /task-add <description>.`
59
59
 
60
60
  ### Parallelism analysis → waves
61
61
 
62
- After upgrades, for each item: `Read` its `task_path`, find `## Dependencies` / `## Blocked by`, extract `TASK-NNN` refs; an **active blocker** is a dep whose `TASK-NNN` also appears in `candidate_items`. Store as `blockers`. Topological sort: **Wave 1** = empty `blockers`; **Wave 2** = blockers all in Wave 1; **Wave 3** = blockers all in Wave 1∪2. Omit Wave 4+. **Cap each wave at 3 items** (document order); note overflow count. Store as `waves`.
62
+ After upgrades, for each item: `Read` its `task_path`, find `## Dependencies` / `## Blocked by`, extract `TASK-NNNN` refs; an **active blocker** is a dep whose `TASK-NNNN` also appears in `candidate_items`. Store as `blockers`. Topological sort: **Wave 1** = empty `blockers`; **Wave 2** = blockers all in Wave 1; **Wave 3** = blockers all in Wave 1∪2. Omit Wave 4+. **Cap each wave at 3 items** (document order); note overflow count. Store as `waves`.
63
63
 
64
64
  ### Archive a fully-complete roadmap (`total > 0` and `done == total`) — run automatically, no prompt
65
65
 
66
66
  1. If `status: active`, `Edit` → `status: done`.
67
67
  2. Remove its row from `wiki/work/roadmaps/index.md` (active-only index).
68
68
  3. `git mv <roadmap_path> wiki/work/roadmaps/archive/<filename>` (Bash — `git mv` only).
69
- 4. Append to `wiki/work/roadmaps/archive/index.md`: `| [[ROADMAP-NNN]] | <title> | done | YYYY-MM-DD |`.
69
+ 4. Append to `wiki/work/roadmaps/archive/index.md`: `| [[ROADMAP-NNNN]] | <title> | done | YYYY-MM-DD |`.
70
70
  5. Append to `wiki/log.md`:
71
71
  ```
72
- ## [YYYY-MM-DD] archive | <ROADMAP-NNN> — completed, moved to archive
72
+ ## [YYYY-MM-DD] archive | <ROADMAP-NNNN> — completed, moved to archive
73
73
  All items checked. Moved to wiki/work/roadmaps/archive/<filename>.
74
74
  ```
75
75
 
@@ -86,7 +86,7 @@ After upgrades, for each item: `Read` its `task_path`, find `## Dependencies` /
86
86
  **Wave 1** — ready now (run these in parallel):
87
87
  | # | Phase | Item | Action |
88
88
  |---|-------|------|--------|
89
- | 1 | Phase N: name | TASK-NNN: item title | `/tackle <task_path>` |
89
+ | 1 | Phase N: name | TASK-NNNN: item title | `/tackle <task_path>` |
90
90
 
91
91
  **Wave 2** — start after Wave 1 completes: …
92
92
  **Wave 3** — start after Wave 2 completes: …
@@ -100,7 +100,7 @@ After upgrades, for each item: `Read` its `task_path`, find `## Dependencies` /
100
100
  - `pending-uat` with no `uat_path` → `` `/uat-generate <task_path>` `` — annotate the Item cell with a trailing `⏳ awaiting UAT (no tests yet)`
101
101
  - `task_path` not found → `` `/tackle <task_path>` `` with ` (file not found)` appended, regardless of status (can't read a status that isn't there)
102
102
 
103
- - **Zero items** → `Roadmap has no checklist items yet. Edit the roadmap file directly to add items, or link a new task to it with /task-add --roadmap <ROADMAP-NNN> <description>.`
103
+ - **Zero items** → `Roadmap has no checklist items yet. Edit the roadmap file directly to add items, or link a new task to it with /task-add --roadmap <ROADMAP-NNNN> <description>.`
104
104
 
105
105
  ---
106
106
 
@@ -211,6 +211,8 @@ Huge inputs (malicious or not) exhaust token budgets, spike rate limits, and inf
211
211
 
212
212
  ## Reporting
213
213
 
214
+ **Output**: after compiling findings, write the full report to `wiki/reports/security-audit/<YYYY-MM-DD>.md` using the **Write** tool (create the directory if it doesn't exist). If a report for today already exists, write `<YYYY-MM-DD>-2.md` (then `-3`, …) rather than overwriting — a persisted history is what makes check B4 ("benchmark results tracked over time") true instead of aspirational. Print the same report in the conversation as well; the file is a durable copy, not a replacement for the reply.
215
+
214
216
  **Per-check status:** ✅ PASS (control exists & effective) · ⚠️ WARN (partial / has gaps) · ❌ FAIL (no evidence; vulnerable) · ℹ️ N/A (not applicable) · 🔍 NEEDS-REVIEW (can't determine from code — flag for manual review).
215
217
 
216
218
  **Report structure:**
@@ -244,3 +246,4 @@ Categories audited: [list]
244
246
  5. **Do not fix** — audit and report only; hand off fixes to the user or `/task-add`.
245
247
  6. **Scope to the repo** — don't speculate about external infra unless config files are present.
246
248
  7. **One category at a time** — complete each fully before the next; don't interleave findings.
249
+ 8. **Persist the report** — write it to `wiki/reports/security-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.
@@ -47,14 +47,14 @@ Zero-click: find the first actionable roadmap item and tackle it, **no prompts**
47
47
  ### Task survey (empty OR unresolved)
48
48
 
49
49
  Recommend from the index; **do not auto-pick**.
50
- - **Read only `wiki/work/tasks/index.md`** (canonical active list: bullet lines `- [TASK-NNN — Title](TASK-NNN-slug.md) — one-line summary · status`). Do NOT read individual task files, `grep`, `bash`, or aggregate across `wiki/work/tasks/` — the index exists to prevent exactly that. The only per-file read is the chosen task in Step 1.
50
+ - **Read only `wiki/work/tasks/index.md`** (canonical active list: bullet lines `- [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line summary · status`). Do NOT read individual task files, `grep`, `bash`, or aggregate across `wiki/work/tasks/` — the index exists to prevent exactly that. The only per-file read is the chosen task in Step 1.
51
51
  - Missing `index.md` / no active-item bullets → STOP: `Task index at wiki/work/tasks/index.md is empty or missing. Add tasks with /task-add, or invoke /tackle <path-or-slug> directly.` Do not scan every file.
52
52
  - `index.md` carries no progress columns — it lists title + one-line summary + `status` only, and `status` now directly distinguishes `todo` / `in-progress` / `pending-uat` (see [lifecycle](../tasks/lifecycle.md)) — no need to infer UAT-awaiting state from file existence. If a bullet points at a task file that no longer exists (moved/archived), note the drift in one sentence and skip it — don't pre-emptively fix the index.
53
53
  - Empty active list → STOP: "No active tasks to tackle".
54
- - Present the active items as a compact table (`TASK-NNN` · title · status). Below it, a **Recommendation** ranking top 1–3 by priority, using `status` alone:
54
+ - Present the active items as a compact table (`TASK-NNNN` · title · status). Below it, a **Recommendation** ranking top 1–3 by priority, using `status` alone:
55
55
  1. `status: in-progress` — finish what's started.
56
56
  2. `status: todo`, lowest-numbered first.
57
- - Tasks at `status: pending-uat` are excluded from recommendations and listed under `**Awaiting UAT**:` — `mcp__serena__list_dir` on `wiki/work/uat/` for the matching `UAT-NNN-*` file; if found, suggest `/uat-walk wiki/work/uat/UAT-NNN-<slug>.md`; if none found (implementation finished but `/uat-generate` never ran), suggest `/uat-generate wiki/work/tasks/TASK-NNN-<slug>.md` instead.
57
+ - Tasks at `status: pending-uat` are excluded from recommendations and listed under `**Awaiting UAT**:` — `mcp__serena__list_dir` on `wiki/work/uat/` for the matching `UAT-NNNN-*` file; if found, suggest `/uat-walk wiki/work/uat/UAT-NNNN-<slug>.md`; if none found (implementation finished but `/uat-generate` never ran), suggest `/uat-generate wiki/work/tasks/TASK-NNNN-<slug>.md` instead.
58
58
  - Progress counts, `[BLOCKED]`/`[FAILED]` flags, and per-step state are **not** in `index.md` by design — they live in the task files. This no-args survey deliberately ranks on `status` + UAT presence alone rather than re-reading every task file; use `/task-audit` when the full progress/blocker picture is needed. (Design note: the survey was simplified to `index.md`'s real bullet schema rather than expanding `index.md` with Progress/UAT/Flags columns, which would violate the "active items only, flat list" convention in `wiki/conventions.md`.)
59
59
  - Use `AskUserQuestion` (top rec first, labelled `(Recommended)`; up to 2 more; `header` = number-slug). If input was unresolved, prefix one line noting it. Do NOT proceed to Step 1 until the user chooses.
60
60
 
@@ -3,7 +3,7 @@ name: task-add
3
3
  description: Create a structured, execution-ready task file in wiki/work/tasks/
4
4
  category: planning
5
5
  model: claude-sonnet-5
6
- argument-hint: <task description> [--decision DEC-NNNN#DM] [--roadmap ROADMAP-NNN]
6
+ argument-hint: <task description> [--decision DEC-NNNN#DM] [--roadmap ROADMAP-NNNN] [--knowledge <slug>]
7
7
  disable-model-invocation: false
8
8
  user-invocable: true
9
9
  ---
@@ -42,8 +42,8 @@ If no decision reference: skip this step entirely.
42
42
  ### Step 3: Parse and validate roadmap reference (only if `$ARGUMENTS` contains `--roadmap` or a `ROADMAP-` token)
43
43
 
44
44
  Detect:
45
- - `ROADMAP-NNN` — bare token
46
- - `--roadmap ROADMAP-NNN` or `--roadmap NNN` — flag form
45
+ - `ROADMAP-NNNN` — bare token
46
+ - `--roadmap ROADMAP-NNNN` or `--roadmap NNN` — flag form
47
47
 
48
48
  Strip the roadmap token from `$ARGUMENTS`.
49
49
 
@@ -55,11 +55,27 @@ Store `(roadmap_file_path, roadmap_number)` for Step 9.
55
55
 
56
56
  If no roadmap reference: skip this step entirely.
57
57
 
58
+ ### Step 2b: Parse and validate knowledge reference (only if `$ARGUMENTS` contains `--knowledge` or a recognizable concept/source slug)
59
+
60
+ Detect:
61
+ - `--knowledge <slug>` — flag form (e.g. `--knowledge wiki-skill-boilerplate-duplication`)
62
+ - a bare slug matching an existing page filename (without extension) in `wiki/knowledge/concepts/` or `wiki/knowledge/sources/`
63
+
64
+ Strip the knowledge token and any `--knowledge` flag from `$ARGUMENTS` to get the clean task description.
65
+
66
+ Locate the page: use `mcp__serena__find_file` to search for `<slug>.md` (try the slug as given, and with `.md` appended if not already present) in `wiki/knowledge/concepts/` and `wiki/knowledge/sources/`.
67
+
68
+ **If found**: store `(knowledge_file_path, knowledge_slug)` for Step 8.
69
+
70
+ **If not found**: warn the user (e.g. "Knowledge page '<slug>' not found in wiki/knowledge/concepts/ or wiki/knowledge/sources/ — continuing without a knowledge link.") and continue — never block task creation on a missing knowledge page.
71
+
72
+ If no knowledge reference: skip this step entirely.
73
+
58
74
  ### Step 4: Determine the next task number
59
75
 
60
76
  Scan **all** task locations to find the next available number:
61
77
  - `mcp__serena__list_dir` on `wiki/work/tasks/` and `wiki/work/tasks/archive/` (skip either that doesn't exist).
62
- - Collect every `TASK-NNN` prefix from filenames across **both** directories. Take `max + 1`, zero-pad to 3 digits. The first task is `TASK-001`.
78
+ - Collect every `TASK-<digits>` prefix from filenames across **both** directories. Take `max + 1`, zero-pad the result to 4 digits. In a brand-new project the first task is `TASK-0001`; in this repo, continue from the current max (do not restart at 1). Collect the numeric value from every `TASK-<digits>-` prefix regardless of digit count — existing tasks are 3-digit, new ones are 4-digit — ignoring leading zeros when comparing.
63
79
  - Also scan `wiki/work/tasks/index.md` for any reserved IDs not yet on disk.
64
80
  - Never re-use a number — IDs are immutable references, and archived tasks keep their original number forever (terminal tasks move to `archive/`; they don't stay in `wiki/work/tasks/`).
65
81
 
@@ -89,17 +105,17 @@ Confirm with the user via `AskUserQuestion`.
89
105
 
90
106
  ### Step 7a: Re-verify next task number — IMMEDIATELY before writing
91
107
 
92
- Re-run the scan from Step 4. If the number planned in Step 7 is now taken, silently bump to the new next-available number. **Never call `Write` before completing this re-scan.**
108
+ Re-run the scan from Step 4, collecting the numeric value from every `TASK-<digits>-` prefix regardless of digit count and zero-padding the result to 4 digits. If the number planned in Step 7 is now taken, silently bump to the new next-available number. **Never call `Write` before completing this re-scan.**
93
109
 
94
110
  ### Step 8: Create the task file
95
111
 
96
- Create `wiki/work/tasks/TASK-NNN-slug.md` using the `Write` tool.
112
+ Create `wiki/work/tasks/TASK-NNNN-slug.md` using the `Write` tool.
97
113
 
98
114
  **Frontmatter** (required):
99
115
  ```yaml
100
116
  ---
101
- id: TASK-NNN
102
- aliases: [TASK-NNN]
117
+ id: TASK-NNNN
118
+ aliases: [TASK-NNNN]
103
119
  title: "<task title>"
104
120
  status: todo
105
121
  created: YYYY-MM-DD
@@ -112,16 +128,17 @@ tags: []
112
128
  ---
113
129
  ```
114
130
 
115
- Populate `depends_on`, `blocks`, and `parallel_safe_with` from Step 5 as lists of `TASK-NNN` IDs (empty list if none).
131
+ Populate `depends_on`, `blocks`, and `parallel_safe_with` from Step 5 as lists of `TASK-NNNN` IDs (empty list if none).
116
132
 
117
133
  **Body structure**:
118
134
 
119
135
  ```markdown
120
- # TASK-NNN — Task Title
136
+ # TASK-NNNN — Task Title
121
137
 
122
138
  implements::[[DEC-NNNN#DM]] ← only when a decision reference was provided
123
- depends_on::[[TASK-NNN]] ← one line per dependency from Step 5; omit entirely if none
124
- blocks::[[TASK-NNN]] ← one line per blocked task from Step 5; omit entirely if none
139
+ relates_to::[[<slug>]] ← only when Step 2b resolved a knowledge reference
140
+ depends_on::[[TASK-NNNN]] ← one line per dependency from Step 5; omit entirely if none
141
+ blocks::[[TASK-NNNN]] ← one line per blocked task from Step 5; omit entirely if none
125
142
 
126
143
  ## Objective
127
144
 
@@ -149,14 +166,16 @@ Agent type annotations: valid types are `general-purpose`, `Explore`, `Plan`.
149
166
 
150
167
  **Decision link** (only when Step 2 found an accepted decision reference): Insert `implements::[[DEC-NNNN#DM]]` as a typed link on the line immediately after the H1, before `## Objective`.
151
168
 
152
- **Dependency links** (from the Step 5 data, no re-derivation needed): insert one `depends_on::[[TASK-NNN]]` line per dependency and one `blocks::[[TASK-NNN]]` line per blocked task, in the same position — immediately after `implements::` when it's present, or immediately after the H1 when it isn't. *Aside: these typed-link lines are additive to the existing `> **Depends on**:`/`> **Blocks**:` blockquote format, not a replacement, and creating them here does not backfill any pre-existing task file.*
169
+ **Knowledge link** (only when Step 2b resolved a knowledge reference): Insert `relates_to::[[<slug>]]` as a typed link in the same position — immediately after `implements::` when it's present, or immediately after the H1 when it isn't.
170
+
171
+ **Dependency links** (from the Step 5 data, no re-derivation needed): insert one `depends_on::[[TASK-NNNN]]` line per dependency and one `blocks::[[TASK-NNNN]]` line per blocked task, in the same position — immediately after `implements::` when it's present, or immediately after the H1 when it isn't. *Aside: these typed-link lines are additive to the existing `> **Depends on**:`/`> **Blocks**:` blockquote format, not a replacement, and creating them here does not backfill any pre-existing task file.*
153
172
 
154
173
  ### Step 9: Update the family index
155
174
 
156
175
  Append to `wiki/work/tasks/index.md`:
157
176
 
158
177
  ```
159
- - [TASK-NNN — Title](TASK-NNN-slug.md) — one-line objective · todo
178
+ - [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line objective · todo
160
179
  ```
161
180
 
162
181
  If the file does not exist, create it with a `# Tasks` heading and the list entry. Insert in numeric order.
@@ -166,7 +185,7 @@ If the file does not exist, create it with a `# Tasks` heading and the list entr
166
185
  In the decision's `### Links` section, add or append a `Source task(s):` line:
167
186
 
168
187
  ```
169
- - Source task(s): [[TASK-NNN]] — **WIP** (added YYYY-MM-DD)
188
+ - Source task(s): [[TASK-NNNN]] — **WIP** (added YYYY-MM-DD)
170
189
  ```
171
190
 
172
191
  If no `### Links` section exists, create one before the closing `---` separator of that decision block. Use `Read` then `Edit` — never shell redirection.
@@ -176,7 +195,7 @@ If no `### Links` section exists, create one before the closing `---` separator
176
195
  Read the roadmap file. Identify the last `## Phase N:` section (or any checklist section). Append a new `- [ ]` line:
177
196
 
178
197
  ```
179
- - [ ] [[TASK-NNN: <task title>]]
198
+ - [ ] [[TASK-NNNN: <task title>]]
180
199
  ```
181
200
 
182
201
  Update the roadmap's `updated:` frontmatter field to today's date. Use `Read` then `Edit`.
@@ -186,8 +205,8 @@ Update the roadmap's `updated:` frontmatter field to today's date. Use `Read` th
186
205
  Append:
187
206
 
188
207
  ```
189
- ## [YYYY-MM-DD] task | TASK-NNN <task title>
190
- Created task TASK-NNN: <one sentence summarising the objective>.
208
+ ## [YYYY-MM-DD] task | TASK-NNNN <task title>
209
+ Created task TASK-NNNN: <one sentence summarising the objective>.
191
210
  ```
192
211
 
193
212
  ### Step 13: Refresh the hot cache
@@ -197,14 +216,14 @@ The new task is durable, cross-session-relevant wiki state. Run the **Hot Cache
197
216
  ### Step 14: Confirm completion
198
217
 
199
218
  Report:
200
- - Created file: `wiki/work/tasks/TASK-NNN-slug.md`
201
- - Task ID: `TASK-NNN`
219
+ - Created file: `wiki/work/tasks/TASK-NNNN-slug.md`
220
+ - Task ID: `TASK-NNNN`
202
221
  - Status: `todo`
203
222
  - Next steps:
204
223
 
205
224
  ```
206
- To implement: /tackle wiki/work/tasks/TASK-NNN-slug.md
207
- To generate tests: /uat-generate TASK-NNN
225
+ To implement: /tackle wiki/work/tasks/TASK-NNNN-slug.md
226
+ To generate tests: /uat-generate TASK-NNNN
208
227
  ```
209
228
 
210
229
  If linked to a roadmap, mention which roadmap was updated and suggest:
@@ -25,7 +25,7 @@ Analyse all active tasks: verify implementation completeness, auto-check unannot
25
25
 
26
26
  Read `wiki/work/tasks/index.md` using the `Read` tool.
27
27
 
28
- - Parse every active-item bullet line — format `- [TASK-NNN — Title](TASK-NNN-slug.md) — one-line summary · status`. Extract the `TASK-NNN` ID and the linked file path (e.g. `wiki/work/tasks/TASK-001-project-registry-push.md`) for each.
28
+ - Parse every active-item bullet line — format `- [TASK-NNNN — Title](TASK-NNNN-slug.md) — one-line summary · status`. Extract the `TASK-NNNN` ID and the linked file path (e.g. `wiki/work/tasks/TASK-001-project-registry-push.md`) for each.
29
29
  - `index.md` lists active items only and carries no progress or flags columns — those are computed from each task file in Step 2.
30
30
  - If the list is empty, report "No active tasks — nothing to audit." and STOP.
31
31
 
@@ -84,7 +84,7 @@ In the same file read, locate the dependency blockquote appearing **immediately
84
84
  - Links follow the pattern `[NNN-slug](NNN-slug.md)` — extract the NNN-slug identifier from each link.
85
85
  - A task with no dependency block at all is treated as having `Depends on: none`, `Blocks: none`, `Parallel-safe with: none`.
86
86
 
87
- Going forward, task files should also carry one `depends_on::[[TASK-NNN]]` line per dependency and one `blocks::[[TASK-NNN]]` line per blocked task, directly below the blockquote — these are additive typed links for Obsidian/Breadcrumbs graph visualization. `/task-audit`'s own parser continues to read only the blockquote above, unchanged.
87
+ Going forward, task files should also carry one `depends_on::[[TASK-NNNN]]` line per dependency and one `blocks::[[TASK-NNNN]]` line per blocked task, directly below the blockquote — these are additive typed links for Obsidian/Breadcrumbs graph visualization. `/task-audit`'s own parser continues to read only the blockquote above, unchanged.
88
88
 
89
89
  ### 2f. Build the Node Record
90
90
 
@@ -70,7 +70,7 @@ If the user says **No**, STOP.
70
70
  ```
71
71
  Then append to `wiki/work/tasks/archive/index.md`:
72
72
  ```
73
- | [[TASK-NNN]] | <Title> | trashed | YYYY-MM-DD |
73
+ | [[TASK-NNNN]] | <Title> | trashed | YYYY-MM-DD |
74
74
  ```
75
75
 
76
76
  3. **For each related UAT file** (if any):
@@ -81,7 +81,7 @@ If the user says **No**, STOP.
81
81
  ```
82
82
  - Append to `wiki/work/uat/archive/index.md`:
83
83
  ```
84
- | [[UAT-NNN]] | <Title> | trashed | YYYY-MM-DD |
84
+ | [[UAT-NNNN]] | <Title> | trashed | YYYY-MM-DD |
85
85
  ```
86
86
 
87
87
  ### Step 5: Update Active Indexes
@@ -90,14 +90,14 @@ Remove the task's row from `wiki/work/tasks/index.md`. If there is a matching UA
90
90
 
91
91
  Use `Read` then `Edit` — never `echo >>` or `sed`. If a row is already absent, note it and continue.
92
92
 
93
- **Do NOT remove references from roadmaps, decisions, or other files** — `[[TASK-NNN]]` and `[[UAT-NNN]]` IDs remain valid regardless of file location.
93
+ **Do NOT remove references from roadmaps, decisions, or other files** — `[[TASK-NNNN]]` and `[[UAT-NNNN]]` IDs remain valid regardless of file location.
94
94
 
95
95
  ### Step 6: Append to wiki/log.md
96
96
 
97
97
  Append one entry to `wiki/log.md`:
98
98
 
99
99
  ```
100
- ## [YYYY-MM-DD] task-trashed | TASK-NNN <title> — archived to wiki/work/tasks/archive/
100
+ ## [YYYY-MM-DD] task-trashed | TASK-NNNN <title> — archived to wiki/work/tasks/archive/
101
101
  ```
102
102
 
103
103
  Use `Read` then `Edit` — never `echo >>`.
@@ -55,6 +55,7 @@ Unit-backed:
55
55
  • UAT-EDGE-002: Rate Limit Window — `node --test test/rate-limit.test.js` (7 tests, 0 fail)
56
56
  Failed:
57
57
  • UAT-API-003: Delete Position — "auto-judge: HTTP 500 expected 204"
58
+ → /bug-file "UAT-API-003: HTTP 500 received, expected 204"
58
59
  • UAT-EDGE-001: Empty Positions — "auto-judge: manual test requires human verification"
59
60
  Next action: /uat-walk wiki/work/uat/UAT-005-positions.md
60
61
  ```
@@ -65,7 +66,7 @@ On all-pass, replace `Next action` with the task/UAT IDs and their new `done`/`p
65
66
 
66
67
  ## Rules
67
68
 
68
- - **No user interaction, ever** — no `AskUserQuestion`, no inline prompts, no clarifying questions. Ambiguity → record fail / exit with a diagnostic summary.
69
+ - **No user interaction, ever** — no `AskUserQuestion`, no inline prompts, no clarifying questions. Ambiguity → record fail / exit with a diagnostic summary. Bug-file suggestions in the summary are informational text only — never call `/bug-file` itself.
69
70
  - **Verdict discipline** — `[x] Pass` only on concrete machine-verified evidence: a matching live command, or a unit-backed run meeting all 7 criteria. `[FAIL: auto-judge: <reason>]` for everything else (uncertainty, missing command with no unit test, non-verifiable Expected, UI, bare manual); **never** `[SKIP]`.
70
71
  - **A green exit code is not a pass** — for unit-backed tests, always confirm the run actually executed tests from the recorded file (UAT-CORE Step 4 criterion 3). Exit 0 with 0 tests collected is the one failure mode that looks exactly like success.
71
72
  - **No browser automation** — UI tests always fail-closed to human verification, unit test or not.