@jakkrichm/create-nexus-devflow 2.6.0 → 2.6.1

package/template/.claude/skills/audit/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: audit
-description: "[devflow][B] Read-only code audit for a Blueprint project, except for the findings ledger it maintains at devflow/context/findings.md. Reviews the active feature, changed files, a selected path, or the full project through all concerns or a focused quality, security, performance, or tests lens. Use when the user runs /audit, invokes $audit, asks for a code or quality audit, security review, performance review, test quality review, dead-code or duplication check, vibe-coded project cleanup, or standards review."
+description: "[devflow] Read-only code audit for a Blueprint project, except for the findings ledger it maintains at devflow/context/findings.md. Reviews the active feature, changed files, a selected path, or the full project through all concerns or a focused quality, security, performance, or tests lens. Use when the user runs /audit, invokes $audit, asks for a code or quality audit, security review, performance review, test quality review, dead-code or duplication check, vibe-coded project cleanup, or standards review."
 ---
 
 # audit - review code quality against the project standards

package/template/.claude/skills/autopilot/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: autopilot
-description: "[devflow][B] Optional explicit Blueprint mode for one bounded spec/build/check/audit pass. It can pick or resume the current feature, write the spec when needed, create or reuse the branch, implement small steps, run build/tests/checks, create checkpoint commits after passing steps, audit changed code, repair confirmed high-severity findings, and stop with a review packet. It never completes, merges, pushes, deploys, publishes, sends, or performs destructive actions without explicit approval. Use only when the user explicitly runs /autopilot, invokes $autopilot, or directly asks for Autopilot."
+description: "[devflow] Optional explicit Blueprint mode for one bounded spec/build/check/audit pass. It can pick or resume the current feature, write the spec when needed, create or reuse the branch, implement small steps, run build/tests/checks, create checkpoint commits after passing steps, audit changed code, repair confirmed high-severity findings, and stop with a review packet. It never completes, merges, pushes, deploys, publishes, sends, or performs destructive actions without explicit approval. Use only when the user explicitly runs /autopilot, invokes $autopilot, or directly asks for Autopilot."
 ---
 
 # autopilot - optional Blueprint loop

package/template/.claude/skills/brainstorm/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: brainstorm
-description: "[devflow][B] Companion skill for structured divergent and convergent ideation, generating 2-3 viable options with trade-off analysis before committing to delivery."
+description: "[devflow] Companion skill for structured divergent and convergent ideation, generating 2-3 viable options with trade-off analysis before committing to delivery."
 argument-hint: "{topic, feature, or discovery-id}"
 ---
 

package/template/.claude/skills/brief/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: brief
-description: "[devflow][B] Read-only briefing on an upcoming build-plan feature before you spec it. With no argument, briefs the next unchecked item; given a number or name, briefs that one. Reads build-plan.md and project-overview.md and explains what the feature is, what it depends on, what it will touch, how big it is, and whether it will split - without writing anything. Use when the user runs /brief, asks what the next feature involves, wants to understand or preview a feature before /feature, or is deciding what to build or reorder next."
+description: "[devflow] Read-only briefing on an upcoming build-plan feature before you spec it. With no argument, briefs the next unchecked item; given a number or name, briefs that one. Reads build-plan.md and project-overview.md and explains what the feature is, what it depends on, what it will touch, how big it is, and whether it will split - without writing anything. Use when the user runs /brief, asks what the next feature involves, wants to understand or preview a feature before /feature, or is deciding what to build or reorder next."
 ---
 
 # brief - understand a feature before you spec it

package/template/.claude/skills/check/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: check
-description: "[devflow][F] Prove the current work actually does what its spec says and adheres to architectural standards through a Dual-Axis Independent Review (Spec Fidelity + Standards & Architecture). Drives the app (browser, CLI, or server), captures empirical evidence (screenshots, output, console/network errors), checks against 12 Fowler smells and deep-module standards, and reports pass/fail. Does not edit source or commit - it observes; fixing stays /implement's job. Use when the user runs /check, asks to confirm a step or feature works, wants proof before /complete, or wants to check a change in the running app rather than just the build."
+description: "[devflow] Prove the current work actually does what its spec says and adheres to architectural standards through a Dual-Axis Independent Review. Supports Multi-Run: given an optional ID or name (/check 12), targets that spec and records proof to devflow/context/{xxx-slug}/findings.md. Drives the app, captures empirical evidence, checks Fowler smells, and reports pass/fail. Use when running /check, confirming work, or validating before /complete."
+argument-hint: "[{run-id, number, or name}]"
 ---
 
 # check - Dual-Axis Independent Verification Engine
@@ -20,13 +21,14 @@ It changes no source and commits nothing — it executes, inspects, and reports
 
 ## Input
 
-Optional: a specific target to check (a step, a flow, a URL). With no argument, verify the whole current feature against `devflow/context/current-feature.md` and `devflow/context/coding-standards.md`.
+- **Given an ID or name** (e.g. `/check 12`, `/check 012`) -> targets `devflow/context/{xxx-slug}/` and records audit ledger to `{xxx-slug}/findings.md`.
+- **With no argument** (`/check`) -> verifies the active run matching current git branch or single active spec.
 
 ---
 
 ## Step 1 - Build the Dual-Axis Review Matrix
 
-Read `devflow/context/current-feature.md` and `devflow/context/coding-standards.md`. Prepare the inspection criteria across two independent axes:
+Read the target spec from `devflow/context/{xxx-slug}/spec.md` (or `devflow/context/current-feature.md`) and `devflow/context/coding-standards.md`. Prepare the inspection criteria across two independent axes:
 
 1. **Axis 1 (Standards & Architecture Criteria)**:
    - Coding conventions in `coding-standards.md`

package/template/.claude/skills/ci/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: ci
-description: "[devflow][B] Set up or normalize automatic GitHub checks for a Blueprint project around one documented Verify command. Detects the real stack, package manager, existing checks, default branch, and workflows; preserves existing CI; combines only configured typecheck, test, and build commands; runs the command locally; and stops before push or remote ruleset changes. Use when the user runs /ci, invokes $ci, asks to add CI, set up GitHub Actions, add pull-request checks, or create automatic GitHub checks."
+description: "[devflow] Set up or normalize automatic GitHub checks for a Blueprint project around one documented Verify command. Detects the real stack, package manager, existing checks, default branch, and workflows; preserves existing CI; combines only configured typecheck, test, and build commands; runs the command locally; and stops before push or remote ruleset changes. Use when the user runs /ci, invokes $ci, asks to add CI, set up GitHub Actions, add pull-request checks, or create automatic GitHub checks."
 ---
 
 # ci - set up automatic GitHub checks

package/template/.claude/skills/complete/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: complete
-description: "[devflow][F] Wrap up a finished feature, fix, or rollback. Runs a final safety pass, archives its spec to devflow/history/features/, devflow/history/fixes/, or devflow/history/rollbacks/, updates the build plan for features and rollbacks, resets devflow/context/current-feature.md to its stub, and makes the work commit. Enforces a mandatory user gate: asks whether to squash-merge to main/master OR pull latest main/master into the feature/dev branch and push to remote for Merge Request (MR / PR) creation. Never merges into main/master without explicit user instruction."
+description: "[devflow] Wrap up a finished feature, fix, or rollback. Supports Multi-Run: given an optional ID (/complete 12), archives that run from devflow/context/{xxx-slug}/ to devflow/history/, cleans up the run workspace, updates build-plan and HISTORY.md, and makes the work commit. Enforces mandatory user gate (Squash-merge vs MR/PR)."
+argument-hint: "[{run-id, number, or name}]"
 ---
 
 # complete - log the finished work, make the work commit, and deliver
@@ -12,13 +13,18 @@ Where this sits in the workflow:
 
 `/implement` built the feature, fix, or rollback on its branch, with optional per-step commit
 checkpoints. This skill closes it out: it logs the work, makes the single
-work-level commit, and guides the delivery through a **Mandatory User Delivery Gate**. Run it only when the work is done,
+work-level commit, archives from `devflow/context/{xxx-slug}/`, cleans up the active run workspace, and guides the delivery through a **Mandatory User Delivery Gate**. Run it only when the work is done,
 reviewed, and the documented `Verify` command, or the fallback build and tests,
 passes.
 
+## Multi-Run Target Resolution
+
+- **Given an ID or name** (e.g. `/complete 12`, `/complete 058`) -> targets `devflow/context/{xxx-slug}/` for archiving and cleanup.
+- **With no argument** (`/complete`) -> targets the run matching the active branch or single active spec.
+
 ## Before you start
 
-Confirm the work is actually finished: `devflow/context/current-feature.md`
+Confirm the target work is actually finished: `devflow/context/{xxx-slug}/spec.md` (or `current-feature.md`)
 holds a real spec, its steps are built on a branch, and `Verify`, or the fallback
 build and tests, passes. If any of the
 spec's done-whens are behavioral, `/check` should have proven them against the

package/template/.claude/skills/convert-any-to-md/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: convert-any-to-md
-description: "[devflow][B] Converts any document (.xlsx, .pdf, .docx, .txt, .csv, .log, .json, .yaml, etc.) or mixed folders into clean Markdown in devflow/reference. Use whenever documents need to be analyzed, summarized, searched, or extracted from."
+description: "[devflow] Converts any document (.xlsx, .pdf, .docx, .txt, .csv, .log, .json, .yaml, etc.) or mixed folders into clean Markdown in devflow/reference. Use whenever documents need to be analyzed, summarized, searched, or extracted from."
 ---
 
 # Convert Any Document to Markdown

package/template/.claude/skills/debug/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: debug
-description: "[devflow][B] Diagnose a failing test, broken build, crash, error, regression, or unexpected behavior without editing source or DevFlow state. Follows a strict 6-Phase Scientific Debugging Loop: builds a red-capable tight feedback loop, reproduces & minimises, tests 3-5 falsifiable hypotheses, localizes the failure to a root cause, and reports a repair handoff to /fix or /implement. Use when the user runs /debug, invokes $debug, asks why something is failing or broken, wants a root-cause investigation, or asks to diagnose before fixing."
+description: "[devflow] Diagnose a failing test, broken build, crash, error, regression, or unexpected behavior without editing source or DevFlow state. Follows a strict 6-Phase Scientific Debugging Loop: builds a red-capable tight feedback loop, reproduces & minimises, tests 3-5 falsifiable hypotheses, localizes the failure to a root cause, and reports a repair handoff to /fix or /implement. Use when the user runs /debug, invokes $debug, asks why something is failing or broken, wants a root-cause investigation, or asks to diagnose before fixing."
 ---
 
 # debug - 6-Phase Scientific Debugging Protocol

package/template/.claude/skills/devflow/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: devflow
-description: "[devflow][B] Flagship interactive guide, state inspector, and intent router for DevFlow workflows."
+description: "[devflow] Flagship interactive guide, state inspector, and intent router for DevFlow workflows."
 ---
 
 # devflow - Interactive Workflow Guide & Intent Router for Nexus-DevFlow

package/template/.claude/skills/discovery/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: discovery
-description: "[devflow][D] Unified discovery and exploration stage in DevFlow 2.5.0 - conducts project-level roadmap discovery (project-plan.md/build-plan.md) or feature-level pre-delivery exploration before the Single Living Spec lifecycle."
+description: "[devflow] Unified discovery and exploration stage in DevFlow 2.5.0 - conducts project-level roadmap discovery (project-plan.md/build-plan.md) or feature-level pre-delivery exploration before the Single Living Spec lifecycle."
 argument-hint: "[{title, request, IDEA-xxx, or discovery-id}]"
 ---
 

package/template/.claude/skills/doctor/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: doctor
-description: "[devflow][B] Run a read-only Blueprint health check for setup, onboarding, required files, tool adapters, commands, optional verification and CI, Blueprint visibility, ignore rules, planning readiness, overview freshness, and workflow drift. Use when the user runs /doctor, asks whether the Blueprint is installed correctly, wants a health check, setup check, doctor pass, or says something feels off before starting or resuming work."
+description: "[devflow] Run a read-only Blueprint health check for setup, onboarding, required files, tool adapters, commands, optional verification and CI, Blueprint visibility, ignore rules, planning readiness, overview freshness, and workflow drift. Use when the user runs /doctor, asks whether the Blueprint is installed correctly, wants a health check, setup check, doctor pass, or says something feels off before starting or resuming work."
 ---
 
 # doctor - Blueprint health check

package/template/.claude/skills/feature/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: feature
-description: "[devflow][F] Turn a feature from build-plan.md into a buildable spec. With no argument, specs the next unchecked item in the build plan; given a number or name, specs that one. If a clearly new feature does not match the plan, proposes a reviewed plan addition, refreshes the overview after approval, then specs it. Sizes the feature and splits anything too big into smaller sub-features (4a, 4b, ...), writes small, reviewable build steps to devflow/context/current-feature.md, then red-teams its own draft for gaps, oversized steps, and scope creep before stopping at a review gate. Use when the user runs /feature, names or numbers a feature, asks to add and start a new feature, or asks to spec out, break down, or start the next feature."
+description: "[devflow] Turn a feature from build-plan.md into a buildable living spec. Supports Multi-Run Spec Queue: drafts dedicated context in devflow/context/{xxx-slug}/ without blocking additional specs. With no argument, specs the next unchecked item; given a number or name, specs that one. Sizes and splits large items (4a, 4b), generates TDD checklist steps, red-teams the draft, and stops at review gate. Use when running /feature, naming a feature, or drafting the next living spec."
+argument-hint: "[{number, name, DISC-id, or IDEA-id}]"
 ---
 
 # feature - turn a build-plan feature into a buildable spec
@@ -8,18 +9,22 @@ description: "[devflow][F] Turn a feature from build-plan.md into a buildable sp
 Where this sits in the workflow:
 
     project-overview.md  +  build-plan.md  ->  [this skill]  ->  build
-    (source of truth,        (which feature       (the spec for      (code,
-     from /overview)          to build)            one feature)        reviewed)
+    (source of truth,        (which feature       (the spec in       (code,
+     from /overview)          to build)            contexts/xxx/)      reviewed)
 
 `build-plan.md` is intentionally high-level - one line per feature, no detail,
 no ordering ceremony. All of that is this skill's job: take one listed feature,
 read the full context from `project-overview.md`, and turn it into something
-buildable.
+buildable in `devflow/context/{xxx-slug}/spec.md`.
+
+## Multi-Run Spec-Ahead Support
+
+`/feature` supports drafting multiple specs ahead of time. Creating a spec creates a dedicated workspace directory at `devflow/context/{xxx-slug}/` and does **not block** drafting subsequent features.
 
 ## Input
 
 A feature from `build-plan.md`, by number or name - e.g. `/feature 3` or
-`/feature "typing engine"`.
+`/feature "typing engine"` or `/feature DISC-20260826-001`.
 
 The request may also describe a genuinely new feature that is not in the build
 plan yet. That goes through the new-feature intake in Step 1. Never silently add

package/template/.claude/skills/fix/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: fix
-description: "[devflow][F] Document an ad-hoc bug fix or small change (one not in the build plan) into devflow/context/current-feature.md so it runs through the same build loop. Writes a short fix spec and stops; then /implement builds it and /complete logs it to devflow/history/fixes/ and merges. Use when the user runs /fix, reports a bug, or asks to fix or change something that isn't a planned build-plan feature."
+description: "[devflow] Document an ad-hoc bug fix or small change (one not in the build plan) into devflow/context/{xxx-slug}/spec.md so it runs through the same build loop. Supports Multi-Run: drafts dedicated fix context and allows selective /implement [id]. Writes a short fix spec and stops; then /implement builds it and /complete logs it to devflow/history/fixes/ and merges. Use when running /fix, reporting a bug, or fixing an ad-hoc issue."
+argument-hint: "[{title or issue-description}]"
 ---
 
 # fix - document an ad-hoc fix, then build it like anything else
@@ -13,7 +14,7 @@ Where this sits in the workflow:
 
 A fix is a bug or small change that isn't a planned build-plan feature. It runs
 through the same loop as a feature (build with review gates, iterate, then merge);
-it just starts here instead of `/feature`, and is logged separately.
+it creates a dedicated run folder at `devflow/context/{xxx-slug}/` (e.g. `059-fix-login-error`).
 
 ## Input
 
@@ -21,16 +22,13 @@ A description of the bug or change, for example `/fix "password reset email neve
 sends"`. If the user just reported the problem in chat, use that.
 
 The input may also be a finding ID from `devflow/context/findings.md`, alone
-or with a description, for example `/fix F-03`. Pull the problem statement from
-that ledger entry. Use this form only between work items, when
-`current-feature.md` is the reset stub: this skill overwrites that file, so
-while a spec is active, repair its findings through `/implement` instead.
+or with a description, for example `/fix F-03`.
 
 ## Step 1 - write the fix spec
 
 Pull context from `devflow/context/project-overview.md` and `devflow/context/coding-standards.md`,
-then write a short spec to `devflow/context/current-feature.md` (this file holds whatever
-is being built now, feature or fix). Keep it lighter than a feature spec:
+calculate the next sequential running ID (e.g. `059-fix-slug`),
+then write a short spec to `devflow/context/{xxx-slug}/spec.md` (and update `devflow/context/current-feature.md`). Keep it lighter than a feature spec:
 
 - **Title** - the bug or change in a few words.
 - **Type:** Fix  (so `/complete` logs it to `devflow/history/fixes/`, not `devflow/history/features/`).

package/template/.claude/skills/grill/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: grill
-description: "[devflow][B] Interactive Socratic alignment & domain modeling - stress-test plans, extract domain glossary, and record architecture decision records (ADRs) before delivery."
+description: "[devflow] Interactive Socratic alignment & domain modeling - stress-test plans, extract domain glossary, and record architecture decision records (ADRs) before delivery."
 argument-hint: "{topic, plan, or question}"
 ---
 

package/template/.claude/skills/idea/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: idea
-description: "[devflow][B] Quick idea capture and AI enrichment - analyze feasibility, value, key points, and record into devflow/ideas.md inbox."
+description: "[devflow] Quick idea capture and AI enrichment - analyze feasibility, value, key points, and record into devflow/ideas.md inbox."
 argument-hint: "\"<idea text or description>\""
 ---
 

package/template/.claude/skills/implement/SKILL.md

@@ -1,9 +1,10 @@
 ---
 name: implement
-description: "[devflow][F] Build the feature, fix, or rollback spec'd in devflow/context/current-feature.md, one small reviewable step at a time. Creates the matching branch, implements each step, shows the diff and explains it in plain English, tests, and iterates until it works. Type: Rollback specs use a guarded reverse patch that preserves Blueprint history. After each approved step it offers an optional commit checkpoint on the branch; the work-level commit, merge, and logging are /complete's job. Use when the user runs /implement, or asks to build, implement, or start the current feature, fix, or rollback once its spec is ready."
+description: "[devflow] Build the feature, fix, or rollback spec, one small reviewable step at a time with Strict TDD. Supports Multi-Run: given an optional ID or name (/implement 12, /implement 012), targets that spec from devflow/context/{xxx-slug}/. Checks out matching branch, runs pre-flight drift revalidation, executes TDD steps with diffs, and offers commit checkpoints. Use when running /implement, or starting work on a spec."
+argument-hint: "[{run-id, number, or name}]"
 ---
 
-# implement - build the current spec, one reviewed step at a time
+# implement - build the target spec, one reviewed step at a time
 
 Where this sits in the workflow:
 
@@ -12,7 +13,7 @@ Where this sits in the workflow:
                                         reviewed)        merge + log)
 
 `/feature`, `/fix`, or `/rollback` wrote the spec to
-`devflow/context/current-feature.md` and stopped.
+`devflow/context/{xxx-slug}/spec.md` (or `devflow/context/current-feature.md`) and stopped.
 This skill turns that spec into code, following the build loop in
 `devflow/context/ai-interaction.md`, without vibe coding: small steps, a visible diff plus
 a plain-English explanation for each, testing, and iteration until it works, all
@@ -20,9 +21,14 @@ behind your approval. It builds on a branch and offers an optional commit
 checkpoint after each step; the work-level commit, merging, and logging are
 `/complete`'s job.
 
+## Multi-Run Target Resolution
+
+- **Given an ID or name** (e.g. `/implement 12`, `/implement 012`, `/implement kanban`) -> locates the matching run folder `devflow/context/{xxx-slug}/`, checks out `feature/{xxx-slug}`, and loads only that run's `spec.md`.
+- **With no argument** (`/implement`) -> checks current git branch, or auto-picks if only 1 spec is active, or prompts the user if multiple specs are queued.
+
 ## Before you start
 
-Read `devflow/context/current-feature.md`. If it has no real spec (still the stub, or its
+Read the target spec from `devflow/context/{xxx-slug}/spec.md` (or `devflow/context/current-feature.md`). If it has no real spec (still the stub, or its
 status is already complete), stop and tell the user to run `/feature` (for a
 planned feature), `/fix` (for an ad-hoc bug or change), or `/rollback` (for a
 completed feature reversal) first. Pull the

package/template/.claude/skills/onboard/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: onboard
-description: "[devflow][B] Set up the Blueprint after overlaying it onto a freshly scaffolded or early project. Detects the stack, tunes project files and adapters, documents real commands and existing checks, points to the optional standalone CI setup, and tells the user what to fill in before /overview or $overview. Use when the user runs /onboard, invokes $onboard, just copied the Blueprint into a new project, or asks what to do after overlaying the Blueprint. For an existing app with meaningful shipped features, use adopt instead."
+description: "[devflow] Set up the Blueprint after overlaying it onto a freshly scaffolded or early project. Detects the stack, tunes project files and adapters, documents real commands and existing checks, points to the optional standalone CI setup, and tells the user what to fill in before /overview or $overview. Use when the user runs /onboard, invokes $onboard, just copied the Blueprint into a new project, or asks what to do after overlaying the Blueprint. For an existing app with meaningful shipped features, use adopt instead."
 ---
 
 # onboard - finish the Blueprint overlay setup

package/template/.claude/skills/overview/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: overview
-description: "[devflow][B] Distill user-owned planning docs into `devflow/context/project-overview.md` using a deterministic compiler. The overview is the living source of truth that agents read every session."
+description: "[devflow] Distill user-owned planning docs into `devflow/context/project-overview.md` using a deterministic compiler. The overview is the living source of truth that agents read every session."
 ---
 
 # overview - dynamic project overview compiler

package/template/.claude/skills/prototype/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: prototype
-description: "[devflow][B] Interactively prototype the look of a project. Asks about the desired look and feel and which pages to draft, proposes a plan, and only then writes throwaway static HTML/CSS mockups to prototypes/ that share one theme (a set of CSS theme variables). A plan-first, pre-build helper that sits outside the spec-driven feature loop, like scaffolding. Use when the user runs /prototype, names screens to mock up, or asks to prototype the layout, theme, or look and feel."
+description: "[devflow] Interactively prototype the look of a project. Asks about the desired look and feel and which pages to draft, proposes a plan, and only then writes throwaway static HTML/CSS mockups to prototypes/ that share one theme (a set of CSS theme variables). A plan-first, pre-build helper that sits outside the spec-driven feature loop, like scaffolding. Use when the user runs /prototype, names screens to mock up, or asks to prototype the layout, theme, or look and feel."
 ---
 
 # prototype - lock the look before you build

package/template/.claude/skills/release/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: release
-description: "[devflow][B] Prepare a Blueprint project for deployment to Render or Vercel. Reads the plans, project commands, app config, and current repo state; verifies build, start, output, env, health checks, and provider config; can create or update render.yaml or vercel.json when requested; and stops before any external deploy, service creation, remote env change, push, publish, or destructive action unless the user explicitly approves. Use when the user runs /release, invokes $release, asks for Render setup, Vercel setup, deploy readiness, deployment config, render.yaml, or vercel.json."
+description: "[devflow] Prepare a Blueprint project for deployment to Render or Vercel. Reads the plans, project commands, app config, and current repo state; verifies build, start, output, env, health checks, and provider config; can create or update render.yaml or vercel.json when requested; and stops before any external deploy, service creation, remote env change, push, publish, or destructive action unless the user explicitly approves. Use when the user runs /release, invokes $release, asks for Render setup, Vercel setup, deploy readiness, deployment config, render.yaml, or vercel.json."
 ---
 
 # release - deployment readiness for Render and Vercel

package/template/.claude/skills/report-html/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: report-html
-description: "[devflow][B] Standalone HTML Report Generator - render an interactive standalone HTML dashboard from current-feature.md or 60-report.md on demand."
+description: "[devflow] Standalone HTML Report Generator - render an interactive standalone HTML dashboard from current-feature.md or 60-report.md on demand."
 argument-hint: "{running-id or workspace path}"
 ---
 

package/template/.claude/skills/rollback/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: rollback
-description: "[devflow][B] Plan a safe reversal of a completed Blueprint feature using its archived spec and squashed git commit. Finds the exact feature commit, reviews later commits for dependency risk, writes a Type: Rollback spec to devflow/context/current-feature.md, and stops for review before /implement applies any code change. Use when the user runs /rollback, asks to remove or undo a completed feature, or wants to return the app to its pre-feature behavior without erasing Blueprint history."
+description: "[devflow] Plan a safe reversal of a completed Blueprint feature using its archived spec and squashed git commit. Finds the exact feature commit, reviews later commits for dependency risk, writes a Type: Rollback spec to devflow/context/current-feature.md, and stops for review before /implement applies any code change. Use when the user runs /rollback, asks to remove or undo a completed feature, or wants to return the app to its pre-feature behavior without erasing Blueprint history."
 ---
 
 # rollback - safely reverse a completed feature

package/template/.claude/skills/status/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: status
-description: "[devflow][B] Show where the project stands: build-plan progress, the current feature's checked and unchecked steps, git state, drift warnings, and the exact next action. Read-only. Use when the user runs /status, asks where things stand, what's next, what's in progress, or is picking work back up after a break or a context clear."
+description: "[devflow] Show where the project stands: build-plan progress, the current feature's checked and unchecked steps, git state, drift warnings, and the exact next action. Read-only. Use when the user runs /status, asks where things stand, what's next, what's in progress, or is picking work back up after a break or a context clear."
 ---
 
 # status - where the project stands right now

package/template/.claude/skills/test/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: test
-description: "[devflow][B] Test execution, missing test generation, and coverage analysis across unit, integration, and smoke test suites."
+description: "[devflow] Test execution, missing test generation, and coverage analysis across unit, integration, and smoke test suites."
 ---
 
 # Test-Driven Development, Generation & Execution

package/template/.claude/skills/tests/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: tests
-description: "[devflow][B] Add or normalize unit testing for a Blueprint project. Detects the stack, reuses an existing test runner when present, or installs the stack-native unit test runner when missing, then adds one small example test, updates AGENTS.md commands, runs build and tests, and reports the diff. Use when the user runs /tests, invokes $tests, asks to add unit tests, set up unit testing, configure tests, or make tests part of the Blueprint workflow."
+description: "[devflow] Add or normalize unit testing for a Blueprint project. Detects the stack, reuses an existing test runner when present, or installs the stack-native unit test runner when missing, then adds one small example test, updates AGENTS.md commands, runs build and tests, and reports the diff. Use when the user runs /tests, invokes $tests, asks to add unit tests, set up unit testing, configure tests, or make tests part of the Blueprint workflow."
 ---
 
 # tests - add unit testing to the project

package/template/.claude/skills/try/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: try
-description: "[devflow][B] Generate a human manual try guide for the current or most recently completed Blueprint feature, fix, or rollback. Reads the spec, project commands, and available app context, then tells the user exactly what to start, where to go, what to click or run, what to expect, and what would count as wrong. Read-only. Use when the user runs /try, invokes $try, asks how to test manually, asks where to click, asks how to see the change, or wants a manual review path after /implement, /autopilot, /check, or /complete."
+description: "[devflow] Generate a human manual try guide for the current or most recently completed Blueprint feature, fix, or rollback. Reads the spec, project commands, and available app context, then tells the user exactly what to start, where to go, what to click or run, what to expect, and what would count as wrong. Read-only. Use when the user runs /try, invokes $try, asks how to test manually, asks where to click, asks how to see the change, or wants a manual review path after /implement, /autopilot, /check, or /complete."
 ---
 
 # try - manual review guide

package/template/AGENTS.md

@@ -1,4 +1,4 @@
-# Nexus-DevFlow 2.6.0 (The 3-Pillars & Single Living Spec Model)
+# Nexus-DevFlow 2.6.1 (The 3-Pillars & Single Living Spec Model)
 
 Instructions for AI coding agents working in this project. This is the cross-tool entry point: Codex, Google Antigravity, Cursor, GitHub Copilot, Gemini CLI, Aider, Zed, Windsurf, and others read `AGENTS.md`. Claude Code reads `CLAUDE.md`, which imports this file (`@AGENTS.md`), so there is a single source of truth.
 

package/template/devflow/build-plan.md

@@ -84,6 +84,16 @@
   - *Dependencies*: ADR-001
   - *Scope*: รวมความสามารถเชิงสถาปัตยกรรมระดับลึกของ Deep-Track เข้าสู่ 4 ขั้นตอนหลักของ Fast-Track บนเอกสาร Single Living Spec (`current-feature.md`) จัดเก็บประวัติแบบ Single Archive (`.md`), ปลดระวาง stage skills 10-70 ที่ซ้ำซ้อน, และปรับปรุงเอกสาร & Schemas ทั้งหมด
 
+---
+
+## 🚀 Phase 11: Multi-Run Context Architecture & Spec Queue Engine
+
+- [x] **11. Multi-Run Context Architecture & Spec Queue Engine (`IDEA-026`, `DISC-20260826-001`)** `[Size: M]`
+  - *Dependencies*: Feature 10, Feature 3
+  - *Scope*: แยกจัดเก็บ Task-Specific Context เป็นโฟลเดอร์ย่อยใน `devflow/context/{xxx-slug}/`, พัฒนา Context Resolver สำหรับสลับและเรียกใช้งาน `/implement <id>`, `/check <id>`, `/complete <id>` แบบระบุ Running ID หรือ Fuzzy Match, และอัปเกรด CLI/Dashboard/Skills ให้รองรับ Spec Queue หลายรันพร้อมกัน
+
+
+
 
 
 

package/template/devflow/reference/running-id-contract.md

@@ -1,4 +1,4 @@
-# DevFlow 2.5.0 Running ID & 3-Pillars Workspace Contract
+# DevFlow 2.6.0 Running ID & 3-Pillars Multi-Run Context Contract
 
 ## The 3-Pillars Workspace Architecture
 
@@ -7,15 +7,23 @@ All DevFlow framework assets are organized into three clean pillars representing
 ```text
 devflow/
 ├── 🔮 ideas.md                 # [1. Future / Backlog] Centralized Idea Inbox with AI scoring
+├── 🗺️ project-plan.md          # [1. Future] Master product roadmap and system vision
+├── 📋 build-plan.md            # [1. Future] User-owned feature queue and sizing
 │
-├── ⚡ context/                  # [2. Present / Active] Living Source of Truth & Active Work
+├── ⚡ context/                  # [2. Present / Active] Living Source of Truth & Multi-Run Contexts
 │   ├── project-overview.md     # Primary source of truth for project architecture and tech stack
 │   ├── coding-standards.md     # Engineering, code quality, TDD, and testing standards
 │   ├── ai-interaction.md       # AI agent interaction rules, unified living spec flow, and Thai defaults
-│   ├── findings.md             # Open and resolved audit findings ledger (P0-P3)
 │   ├── glossary.md             # Domain glossary and architecture vocabulary
+│   ├── current-feature.md      # Active Living Spec pointer / legacy fallback
 │   ├── current-stage.md        # Active state pointer and run tracker
-│   └── current-feature.md      # Single Living Spec (Active work / stub when idle)
+│   ├── findings.md             # Shared/default audit findings ledger (P0-P3)
+│   │
+│   ├── {xxx-slug}/             # Active Run Workspace & Spec Queue (Multi-Run Active Task)
+│   │   ├── spec.md             # Living Spec + Checklist for this run
+│   │   ├── stage.md            # Runtime stage, track, and branch pointer
+│   │   └── findings.md         # Dedicated audit findings ledger for this run
+│   └── ...
 │
 ├── 📦 history/                  # [3. Past / Completed] Permanent Delivery & Release Archives
 │   ├── features/               # Completed features, architecture migrations, tooling (xxx-slug.md)
@@ -32,9 +40,9 @@ devflow/
 ## Running ID Naming Convention
 
 ### 1. Standard Running IDs
-- **Format**: `xxx-slug` (e.g. `001-setup-auth`, `053-unify-deep-and-fast-track-model`)
+- **Format**: `xxx-slug` (e.g. `001-setup-auth`, `058-multi-run-context-architecture`)
 - **Prefix Removal**: The legacy `RUN-` prefix is discontinued in favor of clean 3-digit sequential numbering.
-- **Git Branch Standard**: `feature/{xxx-slug}` or `fix/{xxx-slug}` (or specific release branches such as `2.5.0`).
+- **Git Branch Standard**: `feature/{xxx-slug}` or `fix/{xxx-slug}` (or specific release branches such as `2.6.0`).
 
 ### 2. Sub-Feature Running IDs (`xxx[a-z]-slug`)
 - **Format**: `xxx[a-z]-slug` (e.g. `038a-backend-schema-and-api`, `038b-frontend-ui-and-state`)
@@ -44,19 +52,15 @@ devflow/
 
 ---
 
-## Multi-Factor Sizing Heuristic & Splitting Engine
+## Multi-Run Spec Queue & Selective Execution Rule
 
-A feature is considered **Oversized (`L` or `XL`)** and recommended for sub-feature splitting when any of the following conditions are met:
-1. **Files Touched**: Predicted to modify or create $\ge 6$ files.
-2. **Architectural Layers**: Crosses $\ge 3$ distinct layers (e.g. Database Migrations + Backend APIs + Frontend UI + State Store).
-3. **Task Complexity**: Contains $\ge 6$ checklist tasks or involves heavy multi-service integrations.
+1. **Spec-Ahead & Non-blocking Drafting**:
+   - `/feature [id / title]` and `/fix [title]` create dedicated run folders at `devflow/context/{xxx-slug}/`.
+   - Creating a spec does **not block** drafting additional specs. Multiple specs can reside in `devflow/context/` simultaneously.
+2. **Selective Execution (`/implement [id]`)**:
+   - Spec execution can be invoked targeting a specific ID (e.g. `/implement 12`, `/implement 012`, or `/implement kanban`).
+   - The AI checks out the matching git branch `feature/{xxx-slug}`, loads only that run's `spec.md` and global context, and executes tasks with Strict TDD.
+3. **Dedicated Quality Ledger & Safe Archival (`/complete [id]`)**:
+   - Each run maintains its own `findings.md` within `devflow/context/{xxx-slug}/`.
+   - `/complete` compiles the living spec, archives it to `devflow/history/{features|fixes|rollbacks}/{xxx-slug}.md`, removes `devflow/context/{xxx-slug}/`, updates `HISTORY.md` and `build-plan.md`, and prompts for squash-merge/PR.
 
-When detected during `/feature` or `/brief`, the AI triggers the **Interactive Split Gate**, proposing a clean `4a`, `4b` sub-feature breakdown before opening the first spec.
-
----
-
-## Single Active Run Rule (One Thing at a Time)
-
-1. Only **one active run** is permitted at any given time in `current-feature.md`.
-2. Before opening a new run (`/feature` or `/fix`), the AI checks `current-stage.md` and `current-feature.md`.
-3. If an active run is in progress, the AI **blocks** starting a new task and requires closing the active run via `/complete` (or explicitly cancelling/rolling back).