tracerkit 1.0.1 → 1.1.0

package/README.md

@@ -58,24 +58,87 @@ npx tracerkit uninstall .
 
 ## Skills
 
-### `/tk:prd <idea>` — Write a PRD
+### Core skills
+
+The three-step workflow that takes a feature from idea to verified archive.
+
+#### `/tk:prd <idea>` — Write a PRD
 
 Interactive interview to define a feature. Explores the codebase, asks scoping questions one at a time, designs deep modules, and writes a structured PRD.
 
 **Output:** `prds/<slug>.md`
 
-### `/tk:plan <slug>` — Create an implementation plan
+#### `/tk:plan <slug>` — Create an implementation plan
 
 Reads a PRD and breaks it into phased **tracer-bullet vertical slices** — each phase is a thin but complete path through every layer (schema, service, API, UI, tests), demoable on its own.
 
 **Output:** `plans/<slug>.md`
 
-### `/tk:verify <slug>` — Verify and archive
+#### `/tk:verify <slug>` — Verify and archive
 
 Read-only review that compares the codebase against the plan's done-when conditions. Runs tests, checks user stories, and stamps a **PASS** or **NEEDS_WORK** verdict. On PASS, automatically archives the PRD and plan to `archive/<slug>/`.
 
 **Output:** Verdict block in `plans/<slug>.md` — on PASS: `archive/<slug>/prd.md` + `archive/<slug>/plan.md`
 
+### Helper skills
+
+Useful but optional — this category will grow over time.
+
+#### `/tk:status` — Workflow dashboard
+
+Scans `prds/` and prints a table of all features grouped by status (`in_progress`, `created`, `done`), with age, latest verdict, and blocker/suggestion counts. Read-only — no files are modified.
+
+## Metadata Lifecycle
+
+Each PRD carries YAML frontmatter that tracks its position in the workflow. The skills update it automatically — you never need to edit it by hand.
+
+**Fields:**
+
+- `created` — ISO 8601 UTC timestamp, set when the PRD is written
+- `status` — `created` | `in_progress` | `done`
+- `completed` — ISO 8601 UTC timestamp, set when verification passes
+
+**How it changes:**
+
+| Stage    | Skill               | Frontmatter                                          |
+| -------- | ------------------- | ---------------------------------------------------- |
+| Defined  | `/tk:prd`           | `created: 2025-06-15T14:30:00Z`<br>`status: created` |
+| Planning | `/tk:plan`          | `status: in_progress`                                |
+| Verified | `/tk:verify` (PASS) | `status: done`<br>`completed: 2025-06-20T09:00:00Z`  |
+
+<details>
+<summary>Example frontmatter at each stage</summary>
+
+After `/tk:prd`:
+
+```yaml
+---
+created: 2025-06-15T14:30:00Z
+status: created
+---
+```
+
+After `/tk:plan`:
+
+```yaml
+---
+created: 2025-06-15T14:30:00Z
+status: in_progress
+---
+```
+
+After `/tk:verify` (PASS):
+
+```yaml
+---
+created: 2025-06-15T14:30:00Z
+status: done
+completed: 2025-06-20T09:00:00Z
+---
+```
+
+</details>
+
 ## Why TracerKit?
 
 Most planning tools produce horizontal task lists — nothing works until everything is done. TracerKit uses **tracer-bullet vertical slices** instead: each phase cuts through every layer (schema → service → API → UI → tests), so every phase is demoable on its own. Integration problems surface early, context stays focused, and AI assistants get small well-scoped phases instead of sprawling layers.

package/dist/bin.js

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import { n as e, r as t, t as n } from "./uninstall-BWCq5Ivr.js";
+import { n as e, r as t, t as n } from "./uninstall-B9BzyN-s.js";
 import { resolve as r } from "node:path";
 import { homedir as i } from "node:os";
 //#region src/cli.ts

package/dist/index.js

@@ -1,2 +1,2 @@
-import { i as e, n as t, r as n, t as r } from "./uninstall-BWCq5Ivr.js";
+import { i as e, n as t, r as n, t as r } from "./uninstall-B9BzyN-s.js";
 export { e as SKILL_NAMES, n as init, r as uninstall, t as update };

package/dist/{uninstall-BWCq5Ivr.js → uninstall-B9BzyN-s.js}

@@ -6,7 +6,8 @@ import { fileURLToPath as l } from "node:url";
 var u = [
 	"tk:prd",
 	"tk:plan",
-	"tk:verify"
+	"tk:verify",
+	"tk:status"
 ], d = s(o(l(import.meta.url)), "..", "templates");
 function f(e, t = "") {
 	let n = r(e, { withFileTypes: !0 }), i = [];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tracerkit",
-  "version": "1.0.1",
+  "version": "1.1.0",
   "description": "Stack-agnostic spec-driven workflow for AI coding assistants",
   "license": "MIT",
   "author": {

package/templates/.claude/skills/tk:plan/SKILL.md

@@ -1,7 +1,6 @@
 ---
 description: Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved to plans/. Use after /tk:prd.
 argument-hint: '[slug]'
-disable-model-invocation: true
 ---
 
 # PRD to Plan
@@ -26,6 +25,12 @@ Read `prds/<slug>.md`. If it does not exist, list available PRDs and ask.
 
 If `plans/<slug>.md` already exists, tell the user and ask whether to overwrite or pick a new name.
 
+### 1b. Update PRD status
+
+Update the YAML frontmatter in `prds/<slug>.md` to `status: in_progress`. Change only the `status` field — do not touch any other frontmatter fields or the markdown content below the closing `---`.
+
+If the PRD has no frontmatter, skip this step silently.
+
 ### 2. Explore the codebase
 
 Understand current architecture, existing patterns, and integration points.

package/templates/.claude/skills/tk:prd/SKILL.md

@@ -1,7 +1,6 @@
 ---
 description: Create a PRD through user interview, codebase exploration, and module design, saved to prds/. Use when starting a new feature or change.
 argument-hint: <idea>
-disable-model-invocation: true
 ---
 
 # PRD Writing
@@ -55,6 +54,11 @@ Present modules to user. Confirm which need tests.
 Save to `prds/<slug>.md` (create `prds/` if missing).
 
 ```markdown
+---
+created: <current UTC timestamp, ISO 8601, e.g. 2025-06-15T14:30:00Z>
+status: created
+---
+
 # Feature Name
 
 ## Problem Statement

package/templates/.claude/skills/tk:status/SKILL.md

@@ -0,0 +1,64 @@
+---
+description: Show a dashboard of all features and their workflow status. Use any time to check progress.
+---
+
+# Workflow Dashboard
+
+Scan all PRDs and display a status overview of every feature in the workflow.
+
+## Workflow
+
+### 1. Scan PRDs
+
+List all `.md` files in `prds/`. If the directory is missing or empty, print "No features found — run `/tk:prd` to start one." and stop.
+
+### 2. Parse each PRD
+
+For each file `prds/<slug>.md`:
+
+1. Read YAML frontmatter (between opening and closing `---` delimiters)
+2. Extract fields: `created`, `status`, `completed`
+3. If no frontmatter exists, treat as `status: unknown` with no age
+
+### 3. Read verdict data
+
+For each slug, check if `plans/<slug>.md` exists. If it does, find the last `## Verdict` block and extract:
+
+- **Result**: PASS or NEEDS_WORK
+- **BLOCKERS**: count
+- **SUGGESTIONS**: count
+
+If no plan or no verdict block exists, leave verdict columns blank.
+
+### 4. Print the table
+
+Group features by status in this order: `in_progress`, `created`, `done`, `unknown`.
+
+Within each group, sort by `created` date (oldest first). Features without a `created` date sort last.
+
+Print a markdown table:
+
+```
+## Workflow Dashboard
+
+| Feature | Status | Age | Verdict | Blockers | Suggestions |
+|---------|--------|-----|---------|----------|-------------|
+| <slug>  | ...    | ... | ...     | ...      | ...         |
+```
+
+Column definitions:
+
+- **Feature**: the slug (filename without `.md`)
+- **Status**: `created`, `in_progress`, `done`, or `unknown`
+- **Age**: human-readable duration since `created` (e.g. "3d", "2w", "1mo") — blank if no `created`
+- **Verdict**: latest verdict result or blank
+- **Blockers**: blocker count from latest verdict or blank
+- **Suggestions**: suggestion count from latest verdict or blank
+
+After the table, print a one-line summary: `N features: X in progress, Y created, Z done`.
+
+## Rules
+
+- Read-only — this skill must not create, edit, or delete any files
+- Graceful degradation for missing frontmatter, missing plans, or missing verdicts
+- No arguments accepted — always scans all PRDs

package/templates/.claude/skills/tk:verify/SKILL.md

@@ -1,7 +1,6 @@
 ---
 description: Compare implementation against plan, emit BLOCKERS/SUGGESTIONS and a PASS or NEEDS_WORK verdict. Auto-archives on PASS. Use after implementing a plan.
 argument-hint: '[slug]'
-disable-model-invocation: true
 ---
 
 # Verify Implementation
@@ -80,9 +79,18 @@ Append a verdict block at the bottom of `plans/<slug>.md`:
 
 If a previous verdict block exists, replace it with the new one.
 
-### 7. On PASS — archive
+### 7. On PASS — update PRD status and archive
 
-If the verdict is **PASS**, automatically archive:
+If the verdict is **PASS**:
+
+**First**, update the YAML frontmatter in `prds/<slug>.md`:
+
+- Set `status: done`
+- Add `completed: <current UTC timestamp, ISO 8601, e.g. 2025-06-15T14:30:00Z>`
+- Do not touch any other frontmatter fields or the markdown content below the closing `---`
+- If the PRD has no frontmatter, skip frontmatter update silently
+
+**Then**, automatically archive:
 
 1. Create `archive/<slug>/` directory (and `archive/` if missing)
 2. Move `prds/<slug>.md` → `archive/<slug>/prd.md`