chief-clancy 0.4.0 → 0.5.1

package/src/roles/setup/workflows/init.md

@@ -4,6 +4,15 @@
 
 Full wizard for setting up Clancy in a project. Follow every step exactly. Do not skip steps or reorder them.
 
+### Input handling
+
+This workflow runs inside a Claude Code session, not a vanilla terminal. Accept natural language responses alongside numbered options and y/N prompts:
+- Affirmative: "y", "yes", "sure", "go ahead", "yep" → treat as yes
+- Negative: "n", "no", "nah", "skip", "not now" → treat as no
+- Board selection: "jira", "github", "linear" → treat as selecting that board
+- Direct values: if the user types a status name like "Selected for Development" instead of picking option [2], accept it directly
+- If a response is ambiguous, ask for clarification
+
 ---
 
 ## Step 1 — Detect project state
@@ -13,9 +22,9 @@ Before asking any questions, silently check:
 - Is this an existing project? Check for `package.json`, `.git`, `src/`, `app/`, `lib/`
 - Is a board already configured? Check `.clancy/.env` for `JIRA_BASE_URL`, `GITHUB_TOKEN`, `LINEAR_API_KEY`
 - Does `CLAUDE.md` already exist? Flag for merge — never overwrite
-- Does `.clancy/` already exist? Warn and offer re-init or abort
+- Does `.clancy/.env` already exist? This means init has been completed before — warn and offer re-init or abort. Note: `.clancy/` alone may exist from the installer (runtime scripts) without init having run.
 
-If `.clancy/` exists, output:
+If `.clancy/.env` exists, output:
 
 It looks like Clancy is already set up in this project.
 
@@ -60,9 +69,9 @@ Output:
 
 "Chief Wiggum reporting for duty."
 
-Clancy pulls tickets from your Kanban board, implements them, commits, and squash-merges — one ticket per run, fresh context every time.
+Clancy pulls tickets from your Kanban board, plans and implements them, commits, and squash-merges — one ticket per run, fresh context every time.
 
-Let's get you set up.
+Let's get you set up. This takes about 3 minutes (4 steps, then optional extras).
 ```
 
 ---
@@ -122,7 +131,10 @@ Add this label to any issue you want Clancy to work on.
 **Linear** — ask in this order:
 
 1. `Paste your Linear API key: (create one at linear.app/settings/api)`
-2. `What's your Linear team ID? (find it at linear.app/settings/teams — click your team, copy the ID from the URL)`
+2. After verifying the API key (Step Q2b), auto-detect teams by querying `{ teams { nodes { id name } } }`.
+   - If exactly 1 team: use it automatically. Show `Using team: {name} ({id})`.
+   - If 2+ teams: show a numbered list and let the user pick.
+   - If the query fails or returns no teams: fall back to asking manually: `What's your Linear team ID? (find it at linear.app/settings/teams — click your team, copy the ID from the URL)`
 3. `What label should Clancy filter by? Create a "clancy" label in your Linear team and apply it to issues you want Clancy to implement. [clancy]`
 
 If a label is entered: store as `CLANCY_LABEL` in `.clancy/.env`. Always wrap the value in double quotes (e.g. `CLANCY_LABEL="clancy"`).
@@ -147,9 +159,11 @@ On failure, show:
 Check your credentials in the values you just entered.
 
 [1] Re-enter credentials
+[2] Skip verification (configure later via /clancy:settings)
 ```
 
-If [1]: go back to Q2 and re-ask all Jira questions. If the user wants to abandon setup entirely, they can Ctrl+C.
+If [1]: go back to Q2 and re-ask all Jira questions.
+If [2]: save the unverified credentials and continue with setup. The user can fix them later.
 
 **GitHub Issues** — call `GET https://api.github.com/repos/{GITHUB_REPO}` with `Authorization: Bearer {GITHUB_TOKEN}` and `X-GitHub-Api-Version: 2022-11-28`.
 
@@ -164,9 +178,11 @@ On failure, show:
 Check your token has `repo` scope and the repo name is correct.
 
 [1] Re-enter credentials
+[2] Skip verification (configure later via /clancy:settings)
 ```
 
-If [1]: go back to Q2 and re-ask all GitHub questions. If the user wants to abandon setup entirely, they can Ctrl+C.
+If [1]: go back to Q2 and re-ask all GitHub questions.
+If [2]: save the unverified credentials and continue with setup.
 
 **Linear** — call `POST https://api.linear.app/graphql` with `Authorization: {LINEAR_API_KEY}` (no Bearer prefix) and body `{"query": "{ viewer { id name } }"}`.
 
@@ -181,11 +197,13 @@ On failure, show:
 Check your API key at linear.app/settings/api.
 
 [1] Re-enter credentials
+[2] Skip verification (configure later via /clancy:settings)
 ```
 
-If [1]: go back to Q2 and re-ask all Linear questions. If the user wants to abandon setup entirely, they can Ctrl+C.
+If [1]: go back to Q2 and re-ask all Linear questions.
+If [2]: save the unverified credentials and continue with setup.
 
-Never silently continue with unverified credentials — the user must fix their credentials or exit with Ctrl+C.
+Never silently continue with unverified credentials — the user must explicitly choose to re-enter, skip, or exit.
 
 ---
 
@@ -277,6 +295,33 @@ If no: skip the commit silently. The user can commit manually later.
 
 ---
 
+## Step 4c — Optional roles
+
+Clancy includes the Implementer, Reviewer, and Setup roles by default. Optional roles add extra capabilities.
+
+```
+Clancy includes the Implementer, Reviewer, and Setup roles by default.
+You can enable additional roles:
+
+  [1] Planner   — Refine vague tickets into structured implementation plans
+
+Enter roles to enable (e.g. 1 or "all") or press Enter to skip:
+```
+
+Accept numbers, role names (e.g. "planner"), "all", or Enter to skip.
+
+If any roles are selected:
+- Store as `CLANCY_ROLES="planner"` (comma-separated if multiple) in `.clancy/.env`
+- The selected roles' commands and workflows will be installed on the next `npx chief-clancy` run
+
+If skipped (Enter): no `CLANCY_ROLES` line is written — only core roles are installed.
+
+The installer reads `CLANCY_ROLES` from `.clancy/.env` to determine which optional role directories to copy. Core roles (implementer, reviewer, setup) are always copied regardless of this setting. After changing `CLANCY_ROLES`, re-run `npx chief-clancy@latest --local` (or `--global`) to apply.
+
+Note: as more roles are added in future versions, they appear as additional numbered options here. The flow scales naturally.
+
+---
+
 ## Step 5 — Optional enhancements
 
 Output:
@@ -284,13 +329,13 @@ Output:
 ```
 Clancy is set up. A few optional enhancements are available:
 
-  1. Figma MCP        — fetch design specs when tickets include a Figma URL
-  2. Playwright       — screenshot and verify UI after implementing tickets
-  3. Notifications    — post to Slack or Teams when a ticket completes or errors
-  4. Max iterations   — set how many tickets /clancy:run processes per session
+  1. Max iterations   — set how many tickets /clancy:run processes per session
+  2. Figma MCP        — fetch design specs when tickets include a Figma URL
+  3. Playwright       — screenshot and verify UI after implementing tickets
+  4. Notifications    — post to Slack or Teams when a ticket completes or errors
 
 Each takes about 2 minutes to configure, or skip any for now.
-You can always add them later by editing .clancy/.env.
+You can always add them later via /clancy:settings.
 
 Set up optional enhancements? [y/N]
 ```
@@ -299,11 +344,26 @@ If no: skip to Step 6.
 
 If yes, walk through each in order. After each enhancement (whether configured or skipped), ask before starting the next one: `Set up [enhancement name]? [y/N]`
 
-### Enhancement 1: Figma MCP
+### Enhancement 1: Max iterations
+
+Output:
+
+```
+How many tickets should /clancy:run process before stopping? [5]
+(You can override this per-session with /clancy:run 20)
+```
+
+Validate the input is a positive integer between 1 and 100. If invalid, re-prompt.
+
+Write `MAX_ITERATIONS=<value>` to `.clancy/.env`.
+
+---
+
+### Enhancement 2: Figma MCP
 
 Output: `Fetch design context from Figma when tickets include a Figma URL. Set up Figma MCP? [y/N]`
 
-If no: skip to Enhancement 2.
+If no: skip to Enhancement 3.
 
 If yes: `Paste your Figma API key: (create one at figma.com/settings → Personal access tokens)`
 
@@ -313,10 +373,7 @@ If a key is entered:
    ```
    ✅ Figma connected: {email}
 
-   Note: Figma's API does not expose plan information.
-   Clancy uses 3 MCP calls per ticket (metadata, design context, screenshot).
-   Check your plan at figma.com/settings to confirm you have enough MCP calls for your usage.
-   Pro plans: 200 calls/day (~66 tickets). Starter: 6 calls/month (not suitable for AFK use).
+   Note: Check your Figma plan limits at figma.com/settings — Clancy uses 3 API calls per ticket.
 
    Figma MCP enabled.
    ```
@@ -329,23 +386,23 @@ Double-check it at figma.com/settings → Personal access tokens.
 [1] Try a different key
 [2] Skip Figma for now
 ```
-Never silently continue with an unverified key. If the user picks [1], re-prompt for the key and repeat the verification. If [2], skip to Enhancement 2.
+Never silently continue with an unverified key. If the user picks [1], re-prompt for the key and repeat the verification. If [2], skip to Enhancement 3.
 
 Write `FIGMA_API_KEY` to `.clancy/.env`. Add usage note to CLAUDE.md Clancy section.
 
 ---
 
-### Enhancement 2: Playwright visual checks
+### Enhancement 3: Playwright visual checks
 
-If Figma was configured in Enhancement 1, output:
+If Figma was configured in Enhancement 2, output:
 `Screenshot and verify UI after implementing tickets — and compare against the Figma design when one was fetched. Set up Playwright visual checks? [y/N]`
 
 Otherwise output:
 `Screenshot and verify UI after implementing tickets. Set up Playwright visual checks? [y/N]`
 
-If no: skip to Enhancement 3.
+If no: skip to Enhancement 4.
 
-If yes, continue:
+If yes, continue. For Storybook users this is about 5 quick questions; without Storybook, 3 questions.
 
 **Step 1: Storybook detection**
 
@@ -431,11 +488,11 @@ Create `.clancy/docs/PLAYWRIGHT.md` — see PLAYWRIGHT.md template in scaffold.m
 
 ---
 
-### Enhancement 3: Slack / Teams notifications
+### Enhancement 4: Slack / Teams notifications
 
 Output: `Post to a channel when a ticket completes or Clancy hits an error. Set up notifications? [y/N]`
 
-If no: skip to Enhancement 4.
+If no: skip to Step 6.
 
 If yes: `Paste your Slack or Teams webhook URL:`
 
@@ -454,19 +511,6 @@ Write `CLANCY_NOTIFY_WEBHOOK=<url>` to `.clancy/.env`.
 
 ---
 
-### Enhancement 4: Max iterations
-
-Output:
-
-```
-How many tickets should /clancy:run process before stopping? [5]
-(You can override this per-session with /clancy:run 20)
-```
-
-Write `MAX_ITERATIONS=<value>` to `.clancy/.env`.
-
----
-
 ## Step 6 — Offer map-codebase
 
 Output:
@@ -494,5 +538,5 @@ Output:
 - Config: `.clancy/.env`
 - CLAUDE.md: updated
 
-"Clancy's on the beat." — Run /clancy:dry-run to preview, /clancy:once to pick up a ticket, or /clancy:run to process the queue.
+"Clancy's on the beat." — Run /clancy:plan to refine backlog tickets, /clancy:dry-run to preview, or /clancy:once to pick up a ticket.
 ```

package/src/roles/setup/workflows/map-codebase.md

@@ -46,7 +46,7 @@ Tell the user agents are running:
 🚨 Clancy — Map Codebase
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-"Sending in the task force..." — 5 agents deployed.
+"Sending in the task force..." — 5 agents deployed. Ctrl+C to cancel.
 
   🔍 tech     → STACK.md, INTEGRATIONS.md
   🔍 arch     → ARCHITECTURE.md

package/src/roles/setup/workflows/settings.md

@@ -4,6 +4,14 @@
 
 View and change Clancy configuration. Reads `.clancy/.env`, shows current values, and lets the user update any setting interactively. Loops until the user exits. Never modifies anything other than `.clancy/.env`.
 
+### Input handling
+
+This workflow runs inside a Claude Code session. Accept natural language alongside option codes:
+- "G1", "max iterations", "change iterations" → all resolve to the max iterations setting
+- "enable planner", "R1", "planner" → all resolve to the Planner role toggle
+- "switch board", "S" → switch board flow
+- If a response is ambiguous, ask for clarification
+
 ---
 
 ## Step 1 — Preflight
@@ -31,55 +39,72 @@ Source `.clancy/.env` silently. Detect which board is configured:
 
 ## Step 3 — Display settings menu
 
-Show all current values. Board-specific settings only appear when that board is configured.
+Show all current values. Board-specific settings only appear when that board is configured. Use stable letter/number mnemonics so options don't shift when boards change.
 
 ```
 🚨 Clancy — Settings
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-"Welcome to headquarters." — .clancy/.env
+"Welcome to headquarters."
 
 General
-[1] Max iterations    {MAX_ITERATIONS:-5}          tickets per /clancy:run session
-[2] Claude model      {CLANCY_MODEL:-default}     model used for each ticket session
-[3] Base branch       {CLANCY_BASE_BRANCH:-main}
+  [G1] Max iterations    {MAX_ITERATIONS:-5}          tickets per /clancy:run session
+  [G2] Claude model      {CLANCY_MODEL:-default}     model used for each ticket session
+  [G3] Base branch       {CLANCY_BASE_BRANCH:-main}
 
 {If Jira:}
 Jira
-[4] Queue status      {CLANCY_JQL_STATUS:-To Do}
-[5] Sprint filter     {on if CLANCY_JQL_SPRINT set, else off}
-[6] Label filter      {CLANCY_LABEL if set, else off — only pick up tickets with this label}
-[7] Pickup status     {CLANCY_STATUS_IN_PROGRESS if set, else off — move ticket on pickup}
-[8] Done status       {CLANCY_STATUS_DONE if set, else off — move ticket on completion}
+  [B1] Queue status      {CLANCY_JQL_STATUS:-To Do}
+  [B2] Sprint filter     {on if CLANCY_JQL_SPRINT set, else off}
+  [B3] Label filter      {CLANCY_LABEL if set, else off}
+  [B4] Pickup status     {CLANCY_STATUS_IN_PROGRESS if set, else off}
+  [B5] Done status       {CLANCY_STATUS_DONE if set, else off}
+
+{If GitHub:}
+GitHub
+  (No board-specific settings — labels are managed in GitHub directly)
 
 {If Linear:}
 Linear
-[4] Label filter      {CLANCY_LABEL if set, else off — only pick up issues with this label}
-[5] Pickup status     {CLANCY_STATUS_IN_PROGRESS if set, else off — move issue on pickup}
-[6] Done status       {CLANCY_STATUS_DONE if set, else off — move issue on completion}
+  [B1] Label filter      {CLANCY_LABEL if set, else off}
+  [B2] Pickup status     {CLANCY_STATUS_IN_PROGRESS if set, else off}
+  [B3] Done status       {CLANCY_STATUS_DONE if set, else off}
+
+Roles
+  [R1] Planner           {✅ enabled / ─ disabled}
+
+{If Planner enabled:}
+Planner
+{If Jira:}
+  [P1] Plan queue status  {CLANCY_PLAN_STATUS:-Backlog}
+{If GitHub:}
+  [P1] Plan label         {CLANCY_PLAN_LABEL:-needs-refinement}
+{If Linear:}
+  [P1] Plan state type    {CLANCY_PLAN_STATE_TYPE:-backlog}
 
-Optional enhancements
-[{N}] Figma MCP       {enabled if FIGMA_API_KEY set, else not set}
-[{N}] Playwright      {enabled if PLAYWRIGHT_ENABLED=true, else off}
-[{N}] Notifications   {configured if CLANCY_NOTIFY_WEBHOOK set, else not set}
+Integrations
+  [I1] Figma MCP         {enabled if FIGMA_API_KEY set, else not set}
+  [I2] Playwright        {enabled if PLAYWRIGHT_ENABLED=true, else off}
+  [I3] Notifications     {configured if CLANCY_NOTIFY_WEBHOOK set, else not set}
 
-[{N}] Switch board    currently: {Jira / GitHub Issues / Linear}
-[{N}] Exit
+  [S]  Switch board      currently: {Jira / GitHub Issues / Linear}
+  [D]  Save as defaults  save current settings for all future projects
+  [X]  Exit
 
 Which setting would you like to change?
 ```
 
-Number each option sequentially. Show only the board-specific section that matches the configured board. If Jira: show [4] queue status, [5] sprint, [6] label, [7] pickup status, [8] done status. If Linear: show [4] label, [5] pickup status, [6] done status. If GitHub: no board-specific options.
+Accept the user's response as a code (e.g. "G1", "R1"), a setting name (e.g. "max iterations", "model"), or a natural language description (e.g. "change the model", "enable planner"). If ambiguous, clarify. Show only the board-specific section that matches the configured board. The Planner section only appears when the Planner role is enabled.
 
 ---
 
 ## Step 4 — Handle each selection
 
-After the user picks a number, handle it as below. After saving, print `✅ Saved.` and loop back to Step 3 to show the updated menu.
+After the user picks an option (by code, name, or description), handle it as below. After saving, print `✅ Saved.` and loop back to Step 3 to show the updated menu.
 
 ---
 
-### [1] Max iterations
+### [G1] Max iterations
 
 ```
 Max iterations — current: {value}
@@ -89,11 +114,13 @@ How many tickets should /clancy:run process per session?
 [2] Enter a different number
 ```
 
+Validate the input is a positive integer between 1 and 100. If invalid, re-prompt.
+
 Write `MAX_ITERATIONS=<value>` to `.clancy/.env`.
 
 ---
 
-### [2] Claude model
+### [G2] Claude model
 
 ```
 Claude model — current: {value or "default"}
@@ -111,7 +138,7 @@ Otherwise: write `CLANCY_MODEL=<value>` to `.clancy/.env`.
 
 ---
 
-### [3] Base branch
+### [G3] Base branch
 
 ```
 Base branch — current: {value}
@@ -124,7 +151,7 @@ Write `CLANCY_BASE_BRANCH=<value>` to `.clancy/.env`.
 
 ---
 
-### [4] Jira status filter (Jira only)
+### [B1] Jira status filter (Jira only)
 
 ```
 Jira status filter — current: {value}
@@ -139,7 +166,7 @@ Write `CLANCY_JQL_STATUS=<value>` to `.clancy/.env`.
 
 ---
 
-### [5] Jira sprint filter (Jira only)
+### [B2] Jira sprint filter (Jira only)
 
 ```
 Jira sprint filter — current: {on / off}
@@ -154,7 +181,7 @@ If off: remove `CLANCY_JQL_SPRINT` from `.clancy/.env` (or comment it out).
 
 ---
 
-### [6] Jira label filter (Jira only)
+### [B3] Jira label filter (Jira only)
 
 ```
 Jira label filter — current: {label name or "off"}
@@ -171,7 +198,7 @@ If [2]: remove `CLANCY_LABEL` from `.clancy/.env`.
 
 ---
 
-### [7] Jira In Progress status (Jira only)
+### [B4] Jira In Progress status (Jira only)
 
 ```
 Jira In Progress status — current: {value or "off"}
@@ -188,7 +215,7 @@ If [2]: remove `CLANCY_STATUS_IN_PROGRESS` from `.clancy/.env`.
 
 ---
 
-### [8] Jira Done status (Jira only)
+### [B5] Jira Done status (Jira only)
 
 ```
 Jira Done status — current: {value or "off"}
@@ -205,7 +232,7 @@ If [2]: remove `CLANCY_STATUS_DONE` from `.clancy/.env`.
 
 ---
 
-### [4] Linear label filter (Linear only)
+### [B1] Linear label filter (Linear only)
 
 ```
 Linear label filter — current: {label name or "off"}
@@ -222,7 +249,7 @@ If [2]: remove `CLANCY_LABEL` from `.clancy/.env`.
 
 ---
 
-### [5] Linear In Progress status (Linear only)
+### [B2] Linear In Progress status (Linear only)
 
 ```
 Linear In Progress status — current: {value or "off"}
@@ -239,7 +266,7 @@ If [2]: remove `CLANCY_STATUS_IN_PROGRESS` from `.clancy/.env`.
 
 ---
 
-### [6] Linear Done status (Linear only)
+### [B3] Linear Done status (Linear only)
 
 ```
 Linear Done status — current: {value or "off"}
@@ -256,7 +283,79 @@ If [2]: remove `CLANCY_STATUS_DONE` from `.clancy/.env`.
 
 ---
 
-### Figma MCP
+### [R1] Planner role
+
+```
+Planner role — currently: {enabled / disabled}
+The Planner refines vague backlog tickets into structured implementation plans.
+Commands: /clancy:plan, /clancy:approve
+
+[1] Enable
+[2] Disable
+[3] Cancel
+```
+
+If enabling:
+- Add `planner` to `CLANCY_ROLES` in `.clancy/.env` (create the key if it doesn't exist, append if other roles are listed)
+- Show `✅ Planner role enabled. Re-run the installer to apply: npx chief-clancy@latest --local (or --global)`
+
+If disabling:
+- Remove `planner` from `CLANCY_ROLES` in `.clancy/.env` (if empty after removal, remove the line entirely)
+- Keep planner-specific settings (CLANCY_PLAN_STATUS, etc.) in `.clancy/.env` so re-enabling is frictionless
+- Show `✅ Planner role disabled. Re-run the installer to apply: npx chief-clancy@latest --local (or --global)`
+
+---
+
+### [P1] Plan queue status (Jira only)
+
+```
+Plan queue status — current: {value or "Backlog"}
+Which Jira status should /clancy:plan fetch backlog tickets from?
+Common values: Backlog, To Refine, Unrefined
+
+[1] Backlog (default)
+[2] Enter a different value
+```
+
+If [1]: remove `CLANCY_PLAN_STATUS` from `.clancy/.env` (uses default).
+If [2]: prompt `What status name should /clancy:plan fetch from?` then write `CLANCY_PLAN_STATUS=<value>` to `.clancy/.env`.
+
+---
+
+### [P1] Plan label (GitHub only)
+
+```
+Plan label — current: {value or "needs-refinement"}
+Which label marks issues for /clancy:plan to refine?
+Create this label in GitHub first if it doesn't exist.
+
+[1] needs-refinement (default)
+[2] Enter a different label name
+```
+
+If [1]: remove `CLANCY_PLAN_LABEL` from `.clancy/.env` (uses default).
+If [2]: prompt `What label should /clancy:plan filter by?` then write `CLANCY_PLAN_LABEL=<value>` to `.clancy/.env`.
+
+---
+
+### [P1] Plan state type (Linear only)
+
+```
+Plan state type — current: {value or "backlog"}
+Which Linear state type should /clancy:plan fetch issues from?
+
+[1] backlog (default)
+[2] triage
+[3] Enter a different value
+```
+
+If [1]: remove `CLANCY_PLAN_STATE_TYPE` from `.clancy/.env` (uses default).
+If [2]: write `CLANCY_PLAN_STATE_TYPE=triage` to `.clancy/.env`.
+If [3]: prompt `What state type should /clancy:plan fetch from?` then write `CLANCY_PLAN_STATE_TYPE=<value>` to `.clancy/.env`.
+
+---
+
+### [I1] Figma MCP
 
 ```
 Figma MCP — current: {enabled / not set}
@@ -271,7 +370,7 @@ If [2]: remove `FIGMA_API_KEY` from `.clancy/.env`.
 
 ---
 
-### Playwright
+### [I2] Playwright
 
 ```
 Playwright visual checks — current: {enabled / off}
@@ -288,7 +387,7 @@ If [2] Disable: set `PLAYWRIGHT_ENABLED=false` in `.clancy/.env`.
 
 ---
 
-### Notifications
+### [I3] Notifications
 
 ```
 Notifications — current: {configured / not set}
@@ -303,7 +402,7 @@ If [2]: remove `CLANCY_NOTIFY_WEBHOOK` from `.clancy/.env`.
 
 ---
 
-### Switch board
+### [S] Switch board
 
 Show which board is currently active, then offer the other two:
 
@@ -394,7 +493,7 @@ Then loop back to the main settings menu.
 
 ---
 
-### Exit
+### [X] Exit
 
 Print nothing extra. Stop.
 
@@ -411,13 +510,7 @@ When updating a value:
 
 ---
 
-### Save as global defaults
-
-At the bottom of the settings menu (before Exit), show:
-
-```
-[{N}] Save as defaults   save current settings for all future projects
-```
+### [D] Save as global defaults
 
 When selected:
 

package/src/roles/setup/workflows/update-docs.md

@@ -50,6 +50,9 @@ If `PLAYWRIGHT_ENABLED=true` and the tech agent is re-running: verify `PLAYWRIGH
 ## Step 3 — Confirm before running
 
 ```
+🚨 Clancy — Update Docs
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
 Based on your changes, I'll re-run:
   - {agent list}
 
@@ -81,9 +84,9 @@ git commit -m "docs(clancy): update-docs — refresh .clancy/docs/"
 ## Step 6 — Final message
 
 ```
-Docs updated.
+✅ Docs updated — {N} files refreshed.
 
 Updated: {file list}
 
-Run /clancy:once or /clancy:run when ready.
+"Case files updated." — Run /clancy:once or /clancy:run when ready.
 ```