@chris1807/claude-kit 2.3.1 → 2.3.3

package/README.md

@@ -27,7 +27,7 @@ Every session Claude learns from your feedback and gets better at helping you sp
 |-----------|-------|----------------|-------------|
 | **Global Agents** | 10 | `~/.claude/agents/` (your machine, all projects) | backend, frontend, legacy (Lucee/CFML), mockup, reviewer, test-runner, build-validator, lint-checker, azure-ops, security-auditor |
 | **Project Agents** | 2 | `.claude/agents/` (in the project) | deployer, db-admin |
-| **Hooks** | 9 | `.claude/hooks/` (in the project) | Secret blocker, sensitive data blocker (Bash + MCP + output), protected files, auto-format, test suggestions, UAT reminder, self-improve |
+| **Hooks** | 10 | `.claude/hooks/` (in the project) | Secret blocker, sensitive data blocker (Bash + MCP + output), protected files, auto-format, test suggestions, work item intent, UAT reminder, self-improve |
 | **Slash Commands** | 24 | `.claude/commands/` (in the project) | `/implement`, `/review`, `/deep-review`, `/resolve-feedback`, `/fix-review`, `/deploy`, `/create-release`, `/deploy-release`, `/add-to-release`, `/cherry-pick`, `/promote`, `/rollback`, `/track`, `/plan-backlog`, `/plan-sprint`, `/quote-backlog`, `/cleanup-branches`, `/close-orphan-tasks`, `/quote`, `/explain`, `/create-work-item`, `/edit-work-item` |
 | **MCP Servers** | Up to 6 | `.mcp.json` (in the project) | **Azure DevOps** (work items, repos, pipelines, wiki), Playwright, MongoDB/SQL/Postgres, Teams, Stripe, Azure CLI |
 | **Workflow Template** | 1 | Appended to `CLAUDE.md` | Documents the full development process |
@@ -105,7 +105,7 @@ npx @chris1807/claude-kit init --all
 This installs:
 - ✅ Global agents (backend, frontend, legacy, mockup, reviewer, test-runner, build-validator, lint-checker, azure-ops, security-auditor)
 - ✅ Project agents (deployer, db-admin)
-- ✅ All 9 hooks
+- ✅ All 10 hooks
 - ✅ All 13 slash commands
 - ✅ MCP servers: Playwright, Teams, Azure CLI (+ your DB choice)
 - ✅ Settings, CLAUDE.md workflow, .gitignore
@@ -201,6 +201,7 @@ your-project/                      ← Project-specific
 │   │   ├── protected-files.sh     # BLOCKS/warns on critical file edits
 │   │   ├── auto-format.sh         # Auto-runs formatters after edits
 │   │   ├── test-on-change.sh      # Suggests related tests after edits
+│   │   ├── work-item-intent.sh    # Routes "create a bug/story" prompts to /create-work-item
 │   │   ├── uat-reminder.sh        # Reminds to run UAT after features
 │   │   └── self-improve.sh        # Saves learnings after each session
 │   │
@@ -691,7 +692,7 @@ Claude reviews for:
 | `/quote-backlog` | `/quote-backlog [project]` | Sweep backlog for unpointed items ready to estimate — stories in `Design Approved`, bugs in `New` (bugs have no design states) → review completeness, check for duplicates, suggest rewrites, propose points + creator comments (10 at a time, approval-gated). Also audits the drop-out queue — tagged bugs and stories bounced to Design Review — for items whose creator answered but which nobody returned to the sweep |
 | `/quote` | `/quote AB#1234` | Estimate a work item in story points (senior-calibrated Fibonacci rubric) |
 | `/explain` | `/explain AB#1234` | Summarize and explain a work item in plain language |
-| `/create-work-item` | `/create-work-item [description]` | Interactively draft and create a Feature, Bug, User Story, or Hot Fix — proposes story points (user must agree), creates pointed items in Dev Ready; on a Feature, also drafts its child stories with `Custom.Order` waves |
+| `/create-work-item` | `/create-work-item [description]` | Interactively draft and create a Feature, Bug, User Story, or Hot Fix — proposes story points (user must agree), creates pointed items in Dev Ready; on a Feature, also drafts its child stories with `Custom.Order` waves. Runs automatically for any plain-language request to create a work item |
 | `/edit-work-item` | `/edit-work-item AB#1234 [what to change]` | Revise an existing work item field-by-field. On a Feature, cascades into its child stories — updates, adds, retires, and re-sequences `Custom.Order` waves — with a safety gate on anything already past Dev Ready |
 | `/cleanup-branches` | `/cleanup-branches` | Delete merged feature/work branches |
 | `/close-orphan-tasks` | `/close-orphan-tasks --dry-run` | Close open Tasks whose parent is Ready to Deploy / Deployed / Closed |
@@ -707,6 +708,7 @@ These run automatically — no action needed:
 | **Before** any Bash command | `sensitive-data-blocker.sh` | Blocks `mongosh` commands that reference sensitive PII fields (TIN, SSN, bank accounts). **Blocks the command.** |
 | **Before** any MCP database tool | `sensitive-data-mcp-blocker.sh` | Blocks MongoDB/MSSQL/Postgres MCP tool calls that reference PII fields. **Blocks the call.** |
 | **After** any Bash/MCP/Read/Grep | `sensitive-data-output-blocker.sh` | Scans output for PII field names in JSON, C#, YAML formats — catches broad queries, seed data, test fixtures, log files, and git diffs. **Blocks the output.** |
+| **When you send a prompt** | `work-item-intent.sh` | Spots plain-language requests to create a work item ("log a bug…", "make a story…") and tells Claude to run `/create-work-item` instead of creating it directly. Never blocks; slash-command prompts are skipped. |
 | **Before** any file write | `secret-blocker.sh` | Scans for hardcoded credentials (MongoDB URIs, AWS keys, Stripe keys, passwords). **Blocks the write.** |
 | **Before** any file edit | `protected-files.sh` | Blocks edits to production/staging configs. Warns on critical files (CLAUDE.md, pipelines, Program.cs). |
 | **After** any file edit | `auto-format.sh` | Runs `dotnet format` on .cs files, `eslint --fix` on .ts/.tsx files |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@chris1807/claude-kit",
-  "version": "2.3.1",
+  "version": "2.3.3",
   "description": "Claude Code starter kit for Azure DevOps teams — agents, hooks, MCP servers, slash commands, and end-to-end work item → PR → release → deploy workflow automation",
   "type": "module",
   "bin": {

package/templates/commands/create-work-item.md

@@ -1,12 +1,14 @@
-Create a new Azure DevOps work item interactively. Usage: `/create-work-item`
+Create a new Azure DevOps work item (Bug, User Story, Feature, or Hot Fix) interactively. Use this whenever the user asks to create, log, file, open, or raise a work item, ticket, bug, story, feature, or hot fix, whether or not they typed the command. Usage: `/create-work-item [description]`
 
 This command walks the user through creating a Feature, Bug, User Story, or Hot Fix, develops an acceptance-criteria-ready plan, optionally embeds a UI mockup in the description, and creates the item in the chosen Azure DevOps project. For a Feature it can also draft and create the child User Stories that make the Feature implementable.
 
 Treat `$ARGUMENTS` as an optional rough description that the user may have typed inline (e.g. `/create-work-item users should be able to export payments`). If provided, skip the initial "describe your requirements" prompt in Step 2 and use it as the starting requirements text — but still confirm with the user before proceeding.
 
+**This command is the only way Claude creates a Feature, Bug, User Story, or Hot Fix.** A plain-language request ("log a bug that the export button 500s", "make a story for bulk assign") runs this command even when the user didn't type it. Claude invokes it through the Skill tool with the request text as `$ARGUMENTS`, and the `work-item-intent.sh` hook adds a reminder whenever a prompt reads like one. Every step below applies the same way to an invoked run: prior art, duplicate check, draft approval, and proposed points. Never skip ahead to a direct `wit_work_item_write` create.
+
 ## Step 1: Choose Work Item Type
 
-Ask the user:
+If `$ARGUMENTS` already names the type unambiguously (`bug`, `user story` / `story`, `feature`, `hot fix` / `hotfix`), use it and skip the question. Name the type in the Step 2 confirmation so the user can correct it. Otherwise, ask the user:
 
 ```
 What type of work item do you want to create?

package/templates/hooks/work-item-intent.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+# Work Item Intent Hook (UserPromptSubmit)
+# Routes plain-language requests to create a work item through /create-work-item,
+# so "log a bug for the export 500" gets the same prior-art check, title prefix,
+# AC field, proposed points, and draft approval as typing the command.
+#
+# Never blocks. On a match it prints a note that Claude Code adds to the
+# prompt's context; the note is conditional, so a false positive ("add a
+# feature flag") costs a few tokens and is ignored.
+
+# Read the hook input from stdin
+INPUT=$(cat)
+
+MATCH=$(echo "$INPUT" | python3 -c "
+import sys, json, re
+try:
+    prompt = json.load(sys.stdin).get('prompt', '').strip()
+except Exception:
+    sys.exit(0)
+
+# Slash commands run their own flow — /create-work-item is already running,
+# and work items other commands create (Tasks, child stories) follow theirs.
+if prompt.startswith('/'):
+    sys.exit(0)
+
+verb = r'\b(create|make|add|file|log|open|raise|write\s+up|submit|draft|put\s+in|enter)\b'
+noun = (r'\b(work\s*items?|tickets?|bugs?|user\s+stor(y|ies)|stor(y|ies)|'
+        r'features?(?!\s+(flags?|toggles?|branch(es)?))|hot\s*fix(es)?|backlog\s+items?|pbis?)\b')
+
+if re.search(verb + r'.{0,40}?' + noun, prompt, re.IGNORECASE | re.DOTALL):
+    print('match')
+" 2>/dev/null)
+
+if [ "$MATCH" = "match" ]; then
+    echo "Work item request check: if the user is asking to create an Azure DevOps work item (Bug, User Story, Feature, or Hot Fix), run /create-work-item now with the Skill tool, passing their request as the arguments. Do not create it with a direct wit_work_item_write call. If /create-work-item is already running in this conversation, or this prompt is not a request to create a work item, ignore this note."
+fi
+
+exit 0

package/templates/infrastructure/CLAUDE-WORKFLOW.md

@@ -68,6 +68,7 @@ These run automatically — no action needed:
 | **Before any Bash command** | Sensitive data blocker prevents database queries that reference TIN, SSN, or other PII fields |
 | **Before any MCP database tool** | Sensitive data MCP blocker prevents MCP database queries that reference PII fields |
 | **After any Bash/MCP/Read/Grep command** | Sensitive data output blocker scans results for PII field names and blocks exposure |
+| **When you send a prompt** | Work item intent check — a plain-language request to create a work item is routed to `/create-work-item` |
 | **Before any file write** | Secret blocker scans for hardcoded credentials and blocks them |
 | **Before any file edit** | Protected files guard warns/blocks edits to production configs |
 | **After any file edit** | Auto-formatter runs (dotnet format for .cs, eslint --fix for .ts) |
@@ -109,6 +110,14 @@ Claude maintains persistent memory across sessions in `~/.claude/projects/.../me
 
 **One worktree per ticket.** `/implement` and `/rework` never check out in the folder the session started in. Each ticket gets a sibling git worktree, `../{repo}-AB{id}` (e.g. `../CSIPay-AB5373`), where every build, test, and commit happens. It is removed once the branch is pushed, or kept with a note if anything is uncommitted or unpushed. That lets several sessions work different tickets in the same repo at once. Say **"work in place"** (or "no worktree") to opt a run out. Sessions sharing a repo still share **local ports and the Dev database** — two dev servers on one port, or two integration runs against Dev, will still collide.
 
+### Creating Work Items — Always Through `/create-work-item`
+
+Every Feature, User Story, Bug, or Hot Fix Claude creates goes through `/create-work-item`, whether or not the user typed the command. "Log a bug that the export 500s", "make a story for bulk assign", "open a ticket for this" all mean: invoke `create-work-item` with the Skill tool, passing the request text as the arguments. Never create one with a direct `wit_work_item_write` call. That skips the prior-art and duplicate checks, the title prefix, the AC field, the proposed points, and the user's approval of the draft. The `work-item-intent.sh` hook adds a reminder to any prompt that reads like a creation request.
+
+This includes items Claude decides to raise itself, such as a defect found mid-task or out-of-scope work. Propose it, and if the user agrees, run `/create-work-item` with what you found.
+
+Work items a command creates as one of its own steps keep that command's flow: child Tasks from `/implement`, `/rework`, `/plan-backlog`, and `/plan-sprint`, and child stories from `/create-work-item` and `/edit-work-item`. A new Bug or Story requested in the middle of one of those commands still goes through `/create-work-item`.
+
 ### Story Points & Dev Ready Policy
 
 These rules apply to **every** command or flow that creates or estimates work items:
@@ -365,7 +374,7 @@ All deployment and release operations are available as slash commands:
 | `/plan-sprint` | `/plan-sprint [project]` | Sweep the current sprint for stories/bugs with no child tasks → propose one child task with hours per item |
 | `/quote-backlog` | `/quote-backlog [project]` | Sweep backlog for unpointed items ready to estimate — stories in `Design Approved`, **bugs in `New`** (bugs have no design states) → review completeness, check for duplicates, suggest rewrites, propose points + creator comments (10 at a time, approval-gated). Pointed items move to Dev Ready; stories that can't be quoted move back to **Design Review**, bugs that can't be quoted get a **`needs-info`** tag, so the next sweep skips them. Every run also audits the drop-out queue (tagged bugs **and** stories bounced to Design Review) and reports any whose creator answered but which nobody returned to the sweep — neither mechanism expires, so those are otherwise invisible forever |
 | `/quote` | `/quote AB#1234` | Estimate story points for one work item; on approval, sets the points and moves the item to Dev Ready. If it can't be estimated, offers to send a story back to **Design Review** or tag a bug **`needs-info`** |
-| `/create-work-item` | `/create-work-item [description]` | Interactively draft and create a Feature, Bug, User Story, or Hot Fix — proposes story points (user must agree) and creates pointed items in Dev Ready; on a Feature, also drafts its child stories with `Custom.Order` waves |
+| `/create-work-item` | `/create-work-item [description]` | Interactively draft and create a Feature, Bug, User Story, or Hot Fix — proposes story points (user must agree) and creates pointed items in Dev Ready; on a Feature, also drafts its child stories with `Custom.Order` waves. Runs automatically for any plain-language request to create a work item |
 | `/edit-work-item` | `/edit-work-item AB#1234 [what to change]` | Revise an existing work item field-by-field. On a Feature, cascades the change into its child stories — updates, adds, retires, and re-sequences `Custom.Order` waves — with a safety gate on anything already past Dev Ready |
 | `/cleanup-branches` | `/cleanup-branches` | Delete merged branches |
 | `/close-orphan-tasks` | `/close-orphan-tasks [scope] [--dry-run]` | Close open Tasks whose parent is Ready to Deploy / Deployed / Closed |

package/templates/infrastructure/settings.json

@@ -108,6 +108,16 @@
           }
         ]
       }
+    ],
+    "UserPromptSubmit": [
+      {
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash .claude/hooks/work-item-intent.sh"
+          }
+        ]
+      }
     ]
   }
 }