@rse/ase 0.9.19 → 0.9.21

package/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "http://github.com/rse/ase",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.9.19",
+    "version":                              "0.9.21",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

package/plugin/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.9.19",
+    "version":     "0.9.21",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.9.19",
+    "version":     "0.9.21",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/.github/plugin/plugin.json

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.9.19",
+    "version":     "0.9.21",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/meta/ase-format-arch.md

@@ -9,10 +9,11 @@ and the "how" of the Software Engineering project.
 
 Each **Artifact** of the **Artifact Set**
 **Architecture (ARCH)** is stored under
-`docs/arch/ARCH-<artifact-no/>-<artifact-id/>-<artifact-slug/>.md`,
-relative to the project root directory, with <artifact-no/> being the
-zero-padded, two-digit sequence number of the **Artifact** (starting at
-`01`) according to the order of the **Artifact** list below, and with
+`<basedir/>/ARCH-<artifact-no/>-<artifact-id/>-<artifact-slug/>.md`,
+relative to the project root directory, with <basedir/> being the
+`project.artifact.arch.basedir` config variable, <artifact-no/> being
+the zero-padded, two-digit sequence number of the **Artifact** (starting
+at `01`) according to the order of the **Artifact** list below, and with
 <artifact-slug/> being derived from <artifact-name/> (see below) by
 Pascal-casing each word (upper-casing its first letter) and using `-`
 characters instead of spaces (e.g. `Context-View`).
@@ -74,6 +75,12 @@ distinct **Artifact**s (listed under their <artifact-name/> and their
     The major decisions related to the architecture, each recording the
     forces at play, the chosen response, and the reasoning that justifies it.
 
+10. **Technology Stack (TS)**:
+    The concrete technology products the solution is built upon, organized
+    by tier and lifecycle phase, recording for each component its chosen
+    product, its purpose, and the alternatives that were considered but not
+    chosen.
+
 The **Artifact**s have the following cross-references:
 
 ```text
@@ -89,6 +96,8 @@ ARCH-08-QP Quality Perspectives ──(affects)─►    ARCH-02-FV Functionalit
 ARCH-08-QP Quality Perspectives ──(affects)─►    ARCH-06-DP Deployment View
 ARCH-09-DR Decision Record      ──(affects)─►    ARCH-02-FV Functionality View
 ARCH-09-DR Decision Record      ──(affects)─►    ARCH-06-DP Deployment View
+ARCH-10-TS Technology Stack     ──(realizes)─►   ARCH-02-FV Functionality View
+ARCH-10-TS Technology Stack     ──(realizes)─►   ARCH-06-DP Deployment View
 ```
 
 Context View (CV)
@@ -897,3 +906,262 @@ forces at play, the chosen response, and the reasoning that justifies it.
     -   **Rejected alternatives when the rejection is non-obvious.** If
         you considered GraphQL and picked REST for subtle reasons, record it -
         otherwise someone will suggest GraphQL again in six months.
+
+Technology Stack (TS)
+---------------------
+
+The concrete technology products the solution is built upon, organized by
+tier and lifecycle phase, recording for each component its chosen product,
+its purpose, and the alternatives that were considered but not chosen.
+
+-   Format:
+
+    <format>
+
+    #   ARCHITECTURE: TECHNOLOGY STACK (ARCH-TS)
+
+    ✳   Created:  **<timestamp-created/>**
+    ✎   Modified: **<timestamp-modified/>**
+
+    <arch-ts-component/>
+    <arch-ts-component/>
+    [...]
+
+    </format>
+
+-   <arch-ts-component/> format:
+
+    <format>
+
+    ##  COMPONENT: <arch-ts-component-name/> <a id="ARCH-TS-<arch-ts-component-id/>"></a>
+
+    -   When:         <arch-ts-component-when/>
+    -   Tier:         <arch-ts-component-tier/>
+    -   Coverage:     <arch-ts-component-coverage/>
+    -   Product:      <arch-ts-component-product/>
+    -   Realizes:     <arch-ts-component-element/>[, ...]
+    -   Alternatives: <arch-ts-component-alternative/>[, ...]
+
+    <arch-ts-component-description/>,
+    **BECAUSE** <arch-ts-component-rationale/>.
+
+    </format>
+
+-   <arch-ts-component/> details:
+
+    -   <arch-ts-component-id/>: per-artifact unique "slug" of always 1-3
+        lower-cased words (concatenated with "-" characters and
+        in total not longer than 30 characters), derived from
+        <arch-ts-component-name/>.
+
+    -   <arch-ts-component-name/> is a short (2-5 word) summary of the
+        technology component (e.g. `UI Framework`, `Web Server`, `Relational
+        Database`).
+
+    -   <arch-ts-component-when/> is the lifecycle phase in which the
+        component is relevant, one of:
+
+        -   `Build-Time`: Used during development, compilation, or packaging.
+        -   `Run-Time`:   Used while the solution executes in production.
+
+    -   <arch-ts-component-tier/> is the architectural tier the component
+        belongs to, one of:
+
+        -   `Client`: Runs on the client side (e.g. browser, desktop, mobile).
+        -   `Server`: Runs on the server side (e.g. backend, application, API).
+
+    -   <arch-ts-component-coverage/> is either one or more of the
+        *Client Aspects* or one or more of the *Server Aspects* defined
+        below. The general goal is to achieve a maximum coverage of all
+        aspects per <arch-ts-component-tier/> with the minimum total
+        number of <arch-ts-component-product/>.
+
+    -   <arch-ts-component-product/> is the concrete product, library, or
+        framework chosen for this component (e.g. `VueJS`, `Node.js`,
+        `PostgreSQL`).
+
+    -   <arch-ts-component-element/> is an `ARCH-FV-<arch-fv-component-id/>`
+        or `ARCH-DP-<arch-dp-node-id/>` reference to the functional element
+        or deployment node this product realizes.
+
+    -   <arch-ts-component-alternative/> is a product that would also fit
+        this component but was not chosen (e.g. `React`, `Svelte`).
+
+    -   <arch-ts-component-description/> is a concise paragraph (1-3
+        sentences) of prose describing how the product is used within the
+        solution and how it fits into the overall technology stack.
+
+    -   <arch-ts-component-rationale/> is the 1-sentence rationale ("why")
+        for choosing this product over the alternatives.
+
+    -   In case the element reference is not present, the
+        entire `-   Realizes:` bullet point is omitted.
+
+    -   In case no alternatives were considered, the
+        entire `-   Alternatives:` bullet point is omitted.
+
+    -   In case the rationale is not present, the
+        entire `, **BECAUSE** [...]` clause is omitted.
+
+-   The known *Client Aspects* which usually have to covered (at least for
+    clients in a Rich-Client architecture):
+
+    -   **Interface Theme**:
+        Style Reset, Shape, Color, Gradient, Shadow, Font, Icon.
+
+    -   **Interface Widgets**:
+        Icon, Label, Text Paragraph, Image, Form, Text-Field, Text-Area,
+        Date Picker, Toggle, Radio Button, Checkbox, Select List, Slider,
+        Progress Bar, Hyperlink, Popup Menu, Dropdown Menu, Toolbar, Tooltip,
+        Tab, Pill, Breadcrumb, Pagination, Badge, Alert, Panel, Modal, Table,
+        Scrollbar, Carousel.
+
+    -   **Interface Layouting**:
+        Responsive Design, Media Query, Frame, Grid, Padding, Border,
+        Margin, Alignment, Force, Magnetism.
+
+    -   **Interface Effects**:
+        Transition, Transformation, Keyframes, Easing Function, Sound
+        Effect, Physics.
+
+    -   **Interface Interactions**:
+        Mouse, Keyboard, Touchscreen, Gesture, Clipboard, Drag & Drop.
+
+    -   **Interface States**:
+        Rendered, Enabled, Visible, Focused, Warning, Error, Floating.
+
+    -   **Interface Mask**:
+        Markup Loading, Markup Generation, Virtual DOM, Text, Bitmaps,
+        Vectors, 2D/3D Canvas, Accessibility.
+
+    -   **Interface Internationalization**:
+        Text Internationalization (I18N).
+
+    -   **Data Conversion**:
+        Value Formatting, Value Parsing, Localization (L10N).
+
+    -   **Data Binding**:
+        Reactive, Observer, Unidirectional, Bidirectional, Incremental.
+
+    -   **Presentation Model**:
+        Parameter Value, Command Value, State Value, Data Value, Event
+        Value, Value Validation, Presentation Logic.
+
+    -   **Dialog Navigation**:
+        Deep Linking, Routing, Dialog Flow.
+
+    -   **Dialog Automation**:
+        Dialog Macros, Click-Through, Smoke Testing.
+
+    -   **Dialog Communication**:
+        Service, Event, Model, Socket, Hooks.
+
+    -   **Dialog Life-Cycle**:
+        Component States, Component State Transitions.
+
+    -   **Dialog Structure**:
+        Component, Model/View/Controller Roles, Hierarchical Composition.
+
+    -   **State Persistence**:
+        Local Storage, Cookies, Caching.
+
+    -   **Business Model**:
+        Entity, Field, Relationship, Universally Unique Identifiers (UUID).
+
+    -   **Use-Case Authorization**:
+        User Experience, Dialog Restriction, User, Group, Role, Use-Case,
+        Data, Access.
+
+    -   **Client Networking**:
+        Request/Response, Synchronization, Push, Pull, Pulled-Push,
+        REST, GraphQL, Authentication, Session.
+
+    -   **Environment Detection**:
+        Runtime Detection, Feature Detection.
+
+-   The known *Server Aspects* which usually have to covered (at least for
+    servers, sometimes called Thin-Servers, in a Rich-Client architecture):
+
+    -   **Environment Detection**:
+        Detect the run-time environment, like underlying operating
+        system, execution platform, network topology, feature toggles, etc.
+
+    -   **Argument Parsing**:
+        Parse options and arguments of the Command-Line Interface (CLI)
+        to bootstrap application parameters.
+
+    -   **Configuration Parsing**:
+        Load and parse directives from configuration file to bootstrap
+        application parameters.
+
+    -   **Process Daemonizing**:
+        Detach from the startup terminal and host process in order to run
+        fully independently.
+
+    -   **Process Management**:
+        (Pre-)fork child processes and/or threads of execution and monitor
+        and control them during the life-cycle of the application.
+
+    -   **Component Management**:
+        Structure the code into components, instantiate them under run-time
+        and manage them in a stateful component life-cycle.
+
+    -   **Component Communication**:
+        Provide inter-component communication mechanisms like events, hooks,
+        registry, etc.
+
+    -   **Server Networking**:
+        Listen to network sockets, accept connections and manage
+        request/response and message communication.
+
+    -   **Peer Information**:
+        Determine unique identification and add-on information about the
+        client peer.
+
+    -   **Session Handling**:
+        Manage secured per-connection sessions to keep state between
+        communication requests and/or client sessions.
+
+    -   **User Authentication**:
+        Determine and validate the unique identity of the user communicating
+        over the current network connection.
+
+    -   **Request Validation**:
+        Validate the syntactical and semantical compliance of the requests
+        and sanitize the requests.
+
+    -   **Request Processing**:
+        Process the request by dispatching execution according to the
+        provided request and determined context information.
+
+    -   **Role Authorization**:
+        Determine whether the role of the current user is allowed to execute
+        the current request.
+
+    -   **Client Networking**:
+        Provide mechanisms to connect to peers over the network and perform
+        request/response and/or publish/subscribe communication.
+
+    -   **Task Scheduling**:
+        Schedule and execute recurring tasks independent of regular I/O
+        operations.
+
+    -   **Execution Tracing**:
+        Provide mechanisms for tracing the execution by logging event and
+        measurement information at certain points of interest.
+
+    -   **Database Access**:
+        Map in-memory domain entities onto data store dependent persistent
+        data structure.
+
+    -   **Database Connectivity**:
+        Locally or remotely connect the database access layer to the
+        underlying data store.
+
+    -   **Database Schema**:
+        Create, update or downgrade the data schema inside the underlying
+        data store.
+
+    -   **Database Bootstrapping**:
+        Create, update or downgrade both mandatory bootstrapping and optional
+        domain-specific data inside the underlying data store.

package/plugin/meta/ase-format-spec.md

@@ -9,10 +9,11 @@ and the "what" of the Software Engineering project.
 
 Each **Artifact** of the **Artifact Set**
 **Specification (SPEC)** is stored under
-`docs/spec/SPEC-<artifact-no/>-<artifact-id/>-<artifact-slug/>.md`,
-relative to the project root directory, with <artifact-no/> being the
-zero-padded, two-digit sequence number of the **Artifact** (starting at
-`01`) according to the order of the **Artifact** list below, and with
+`<basedir/>/SPEC-<artifact-no/>-<artifact-id/>-<artifact-slug/>.md`,
+relative to the project root directory, with <basedir/> being the
+`project.artifact.spec.basedir` config variable, <artifact-no/> being
+the zero-padded, two-digit sequence number of the **Artifact** (starting
+at `01`) according to the order of the **Artifact** list below, and with
 <artifact-slug/> being derived from <artifact-name/> (see below) by
 Pascal-casing each word (upper-casing its first letter) and using `-`
 characters instead of spaces (e.g. `Customer-Journey`).

package/plugin/meta/ase-skill.md

@@ -139,8 +139,14 @@ Skill Sequential Processing
 -   *IMPORTANT*: For each <step/> you *MUST* use the `TaskUpdate` tool
     for updating its status *during* processing, once a <step/> finished.
 
--   *IMPORTANT*: You *MUST* sequentially execute every <step/> in
-    a <flow/> *EXACTLY* as the instructions specify.
+-   *IMPORTANT*: You *MUST* *strictly sequentially* execute every <step/> in
+    a <flow/>. You *MUST* not implicitly skip any <step/> during
+    processing, except you were explicitly requested to do this or the
+    step is a configured to be a conditional step!
+
+-   *IMPORTANT*: You *MUST* *strictly sequentially* execute every numbered
+    items in a <step/>. You *MUST* not implicitly skip any numbered item during
+    processing, except you were explicitly requested to do this!
 
 -   *IMPORTANT*: For any <step/> that specifies an *agent* in its
     `agent="[...]"` XML attribute, you *MUST* use the specified

package/plugin/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "http://github.com/rse/ase",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "http://github.com/rse/ase/issues" },
-    "version":                              "0.9.19",
+    "version":                              "0.9.21",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

package/plugin/skills/ase-code-craft/SKILL.md

@@ -43,12 +43,6 @@ From scratch *craft* the following feature:
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
 filesystem-modifying tool during this entire skill. The *only*
 permitted way to persist artifacts is via `ase_task_save(...)`.

package/plugin/skills/ase-code-refactor/SKILL.md

@@ -43,12 +43,6 @@ to `true`, <getopt-option-dry/> to `true`, and <getopt-option-next/> to
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
 filesystem-modifying tool during this entire skill. The *only*
 permitted way to persist artifacts is via `ase_task_save(...)`.

package/plugin/skills/ase-code-resolve/SKILL.md

@@ -43,12 +43,6 @@ to `true`, <getopt-option-dry/> to `true`, and <getopt-option-next/> to
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 You *MUST* *NOT* call `Edit`, `Write`, `NotebookEdit`, or any
 filesystem-modifying tool during this entire skill. The *only*
 permitted way to persist artifacts is via `ase_task_save(...)`.

package/plugin/skills/ase-docs-distill/SKILL.md

@@ -37,12 +37,6 @@ effort: high
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 <flow>
 
 1.  <step id="STEP 1: Resolve Input">

package/plugin/skills/ase-meta-diff/SKILL.md

@@ -44,12 +44,6 @@ render a *blast-radius map*.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 <flow>
 
 1.  <step id="STEP 1: Determine Change Set">

package/plugin/skills/ase-meta-review/SKILL.md

@@ -43,12 +43,6 @@ scan: it complements `ase-code-lint` (mechanical quality), `ase-code-analyze`
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 <flow>
 
 1.  <step id="STEP 1: Determine Change Set">

package/plugin/skills/ase-sync-import/SKILL.md

@@ -0,0 +1,191 @@
+---
+name: ase-sync-import
+argument-hint: "[--help|-h] [--target|-t <target>[,...]] <hint>"
+description: >
+    Import information from foreign sources into a set of artifact kinds
+    (the target), generating or updating them to reflect the imported
+    information. Use when the user wants to "import", "ingest", or
+    "bring in" external sources like files, URLs, or pasted text into
+    artifacts like SPEC, ARCH, CODE, DOCS, TASK, INFR, or OTHR.
+user-invocable: true
+disable-model-invocation: false
+effort: xhigh
+---
+
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
+
+<skill name="ase-sync-import">
+    Import Foreign Sources into Artifact Set
+</skill>
+
+<expand name="getopt"
+    arg1="ase-sync-import"
+    arg2="--target|-t=SPEC,ARCH">
+    $ARGUMENTS
+</expand>
+
+<objective>
+    *Import* the information of the *foreign sources* (named by the
+    <hint/>) into the *target* artifact kinds, by reading the foreign
+    sources and generating or updating the target artifacts to faithfully
+    reflect the imported information:
+    <hint><getopt-arguments/></hint>.
+</objective>
+
+@${CLAUDE_SKILL_DIR}/../../meta/ase-format-meta.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-format-spec.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-format-arch.md
+@${CLAUDE_SKILL_DIR}/../../meta/ase-format-task.md
+
+Procedure
+---------
+
+<flow>
+
+1.  <step id="STEP 1: Determine Target">
+
+    1.  The recognized artifact kinds are the seven tokens `TASK`,
+        `SPEC`, `ARCH`, `CODE`, `DOCS`, `INFR`, and `OTHR`. Parse
+        <getopt-target/> as the comma-separated <target/> kind list.
+        Upper-case and trim every parsed kind token. Do not output
+        anything.
+
+    2.  <if condition="<target/> is empty">
+
+        Only output the following <template/> and then immediately *STOP*
+        processing the entire current skill:
+
+        <template>
+        ⧉ **ASE**: ☻ skill: **ase-sync-import**, ▶ ERROR: empty target artifact list
+        </template>
+
+        </if>
+
+    3.  If any token in <target/> is *not* one of the seven recognized
+        kinds, only output the following <template/> (with <kind/> set to
+        the first offending token) and then immediately *STOP* processing
+        the entire current skill:
+
+        <template>
+        ⧉ **ASE**: ☻ skill: **ase-sync-import**, ▶ ERROR: unknown or unsupported artifact kind: **<kind/>**
+        </template>
+
+    4.  <if condition="<hint/> is empty">
+
+        Only output the following <template/> and then immediately *STOP*
+        processing the entire current skill:
+
+        <template>
+        ⧉ **ASE**: ☻ skill: **ase-sync-import**, ▶ ERROR: empty source hint -- nothing to import from
+        </template>
+
+        </if>
+
+    5.  Report the resolved target and source hint with the following <template/>:
+
+        <template>
+        <ase-tpl-bullet-signal/> **TARGET**: <target/>
+        <ase-tpl-bullet-normal/> **SOURCE**: <hint/>
+        </template>
+
+    </step>
+
+2.  <step id="STEP 2: Ingest Foreign Sources">
+
+    1.  Do not output anything in this STEP 2.
+
+    2.  Interpret the <hint/> as the description of the *foreign sources*
+        to import from. The foreign sources are *external* to the ASE
+        artifact sets and may be local files or directories, remote URLs,
+        pasted text passages, or references to other documents.
+
+    3.  Read or fetch all foreign sources named by the <hint/>: read local
+        files and directories via the `Read` tool, and fetch remote URLs
+        via the available web tools. Build a precise understanding of the
+        *information* the foreign sources represent.
+
+    </step>
+
+3.  <step id="STEP 3: Generate or Update Artifacts">
+
+    1.  For all kinds in <target/>, call the `ase_artifact_list(kind: [
+        ... ])` tool of the `ase` MCP server *once*, passing the
+        lower-cased `kind` tokens, and read the returned `artifacts`
+        array of `{ kind, files }` objects to obtain the project-relative
+        file list per kind. Read all *existing* target artifacts to
+        understand their current state.
+
+    2.  Internalize and honor the artifact-format conventions:
+
+        -   the artifact-set/artifact/aspect meta information (`ase-format-meta.md`),
+        -   the `SPEC` format (`ase-format-spec.md`),
+        -   the `ARCH` format (`ase-format-arch.md`),
+        -   the `TASK` format (`ase-format-task.md`).
+
+        Whenever a target artifact belongs to one of these kinds, it
+        *MUST* be kept (or made) conformant to the corresponding format
+        (headings, structure, identifiers, and the `<timestamp-modified/>`
+        rule). The kinds `CODE`, `DOCS`, `INFR`, and `OTHR` have no
+        dedicated format contract and are treated as free-form.
+
+    3.  You *MUST* internalize and strictly honor the **GENERIC TENETS**,
+        the **CRAFTING TENETS**, and the **RECONCILIATION TENETS** of the
+        **ASE Tenets** when generating or updating in the following. Do
+        not output anything.
+
+    4.  Once call the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of
+        the `ase` MCP server to find out the current time and store it in
+        <timestamp-modified/>.
+
+    5.  *Generate or update* the <target/> artifact files so that they
+        faithfully *reflect* the information of the imported foreign
+        sources:
+
+        -   *Generate* a target artifact that does not yet exist but is
+            warranted by the imported information, using the current time
+            for both its `Created:` and `Modified:` timestamps.
+
+        -   *Update* an existing target artifact so it reflects the
+            imported information. Keep changes as *surgical* as possible:
+            change only what the imported information actually requires,
+            and do *not* rewrite unrelated parts of an artifact. Whenever
+            an existing artifact is changed and contains a `Modified:
+            <timestamp-modified-old/>` line, replace this with `Modified:
+            <timestamp-modified/>`.
+
+        Honor **No Fabrication**: never invent target content the foreign
+        sources do not support; if the sources are silent or ambiguous on
+        something the target needs, surface the gap rather than guessing.
+        Re-express the imported facts at the *target's* level of
+        abstraction (a SPEC states intent, an ARCH states structure).
+
+        Apply the generation/update directly to the target artifacts via
+        the `Write`/`Edit` tools.
+
+    6.  Report the performed changes with the following <template/>, listing
+        one bullet line per generated or updated file (with <file/> its
+        project-relative path and <note/> an ultra-brief description of
+        what was imported):
+
+        <template>
+        <ase-tpl-bullet-signal/> **IMPORTED ARTIFACTS**:
+
+        -   `<file/>`: <note/>
+        [...]
+        </template>
+
+        <if condition="no target artifact required any change">
+
+        Only output the following <template/>:
+
+        <template>
+        <ase-tpl-bullet-normal/> **IMPORTED ARTIFACTS**: none -- all targets already reflect the imported sources
+        </template>
+
+        </if>
+
+    </step>
+
+</flow>

package/plugin/skills/ase-sync-import/help.md

@@ -0,0 +1,80 @@
+
+##  NAME
+
+`ase-sync-import` - Import Foreign Sources into Artifact Set
+
+##  SYNOPSIS
+
+`ase-sync-import`
+    [`--help`|`-h`]
+    [`--target`|`-t` *target*[,...]]
+    *hint*
+
+##  DESCRIPTION
+
+The `ase-sync-import` skill imports information from *foreign sources*
+into a set of artifact kinds (the *target*), generating or updating the
+target artifacts so they faithfully *reflect* the imported information.
+Unlike `ase-sync-reconcile`, which syncs *between* existing ASE artifact
+kinds, `ase-sync-import` brings in information from *external* sources
+that live outside the ASE artifact sets.
+
+The *foreign sources* are named by the free-form *hint* argument and may
+be local files or directories, remote URLs, pasted text passages, or
+references to other documents. Local files are read via the `Read` tool
+and remote URLs are fetched via the available web tools.
+
+The *target* is a comma-separated list over the seven recognized
+artifact kinds `SPEC` (Specification), `ARCH` (Architecture), `CODE`
+(Source Code), `DOCS` (Documentation), `TASK` (Task Plans), `INFR`
+(Infrastructure), and `OTHR` (catch-all). It defaults to `SPEC,ARCH`.
+The file lists for the involved kinds are resolved via the
+`ase_artifact_list` MCP tool of the `ase` MCP server.
+
+While importing, the skill honors the artifact-format conventions of
+`ase-format-meta.md`, `ase-format-spec.md`, `ase-format-arch.md`, and
+`ase-format-task.md`; the kinds `CODE`, `DOCS`, `INFR`, and `OTHR` have
+no dedicated format contract and are treated as free-form. A target
+artifact that does not yet exist but is warranted by the imported
+information is *generated* from scratch, while an existing target
+artifact is *surgically updated* to reflect the imported information.
+
+##  OPTIONS
+
+`--target`|`-t` *target*[,...]:
+    The comma-separated list of artifact kinds to generate or update.
+    Defaults to `SPEC,ARCH`. The skill errors out on an empty target or
+    an unknown/unsupported kind.
+
+##  ARGUMENTS
+
+*hint*:
+    The mandatory free-form description of the foreign sources to import
+    from (e.g. a file path, directory, URL, or pasted text). The skill
+    errors out on an empty hint.
+
+##  EXAMPLES
+
+Import a foreign requirements document into the specification:
+
+```text
+❯ /ase-sync-import -t SPEC docs/legacy/requirements.txt
+```
+
+Import an external design write-up into the architecture, defaulting
+both specification and architecture as targets:
+
+```text
+❯ /ase-sync-import https://example.com/design-notes.html
+```
+
+Import a pasted feature description into a task plan:
+
+```text
+❯ /ase-sync-import -t TASK the new export feature must support CSV and JSON
+```
+
+##  SEE ALSO
+
+[`ase-sync-reconcile`](../ase-sync-reconcile/help.md),
+[`ase-task-implement`](../ase-task-implement/help.md)

package/plugin/skills/ase-sync-reconcile/SKILL.md

@@ -1,11 +1,12 @@
 ---
 name: ase-sync-reconcile
-argument-hint: "[--help|-h] <target>[,...] [<source>[,...]]"
+argument-hint: "[--help|-h] [--bidirectional|-b] [--target|-t <target>[,...]] [--source|-s <source>[,...]] [<hint>]"
 description: >
-    Reconcile one set of artifact kinds (the target) to reflect the current
-    state of another set of artifact kinds (the source). Use when the
-    user wants to "reconcile", "sync", "align", or "update" artifacts like
-    SPEC, ARCH, CODE, DOCS, TASK, INFR, or OTHR against each other.
+    Reconcile one set of artifact kinds (the target) to reflect the
+    current state of another set of artifact kinds (the source), while
+    optionally honoring a filtering hint. Use when the user wants to
+    "reconcile", "sync", "align", or "update" artifacts like SPEC, ARCH,
+    CODE, DOCS, TASK, INFR, or OTHR against each other.
 user-invocable: true
 disable-model-invocation: false
 effort: xhigh
@@ -16,18 +17,20 @@ effort: xhigh
 @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
 
 <skill name="ase-sync-reconcile">
-    Reconcile Artifacts from Artifacts
+    Reconcile Artifact Set to Artifact Set
 </skill>
 
-<expand name="getopt" arg1="ase-sync-reconcile">
+<expand name="getopt"
+    arg1="ase-sync-reconcile"
+    arg2="--bidirectional|-b --target|-t=CODE,DOCS,INFR,OTHR --source|-s=AUTO">
     $ARGUMENTS
 </expand>
 
 <objective>
     *Reconcile* the *target* artifact kinds to *reflect* the *current
     state* of the *source* artifact kinds, by reading the source
-    artifacts and adjusting the target artifacts accordingly:
-    <request><getopt-arguments/></request>.
+    artifacts and aligning the target artifacts accordingly:
+    <hint><getopt-arguments/></hint>.
 </objective>
 
 @${CLAUDE_SKILL_DIR}/../../meta/ase-format-meta.md
@@ -38,22 +41,16 @@ effort: xhigh
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 <flow>
 
 1.  <step id="STEP 1: Determine Target and Source">
 
     1.  The recognized artifact kinds are the seven tokens `TASK`,
         `SPEC`, `ARCH`, `CODE`, `DOCS`, `INFR`, and `OTHR`. Parse
-        <getopt-arguments/> as one or two whitespace-separated fields:
-        the *first* field is the comma-separated <target/> kind list, the
-        optional *second* field is the comma-separated <source/> kind list.
-        Upper-case and trim every parsed kind token.
+        <getopt-target/> as the comma-separated <target/> kind list and
+        <getopt-source/> as the comma-separated <source/> kind list.
+        Upper-case and trim every parsed kind token. Do not output
+        anything.
 
     2.  <if condition="<target/> is empty">
 
@@ -61,12 +58,20 @@ explicitly requested by this procedure via outputs based on a <template/>!
         processing the entire current skill:
 
         <template>
-        ⧉ **ASE**: ☻ skill: **ase-sync-reconcile**, ▶ ERROR: missing target argument
+        ⧉ **ASE**: ☻ skill: **ase-sync-reconcile**, ▶ ERROR: empty target artifact list
         </template>
 
         </if>
 
-    3.  If any token in <target/> or <source/> is *not* one of the seven
+    3.  <if condition="<source/> is equal 'AUTO'">
+
+        Set <source/> to the seven recognized kinds
+        `TASK,SPEC,ARCH,CODE,DOCS,INFR,OTHR` *minus* all kinds present
+        in <target/>. Do not output anything.
+
+        </if>
+
+    4.  If any token in <target/> or <source/> is *not* one of the seven
         recognized kinds, only output the following <template/> (with
         <kind/> set to the first offending token) and then immediately
         *STOP* processing the entire current skill:
@@ -75,24 +80,24 @@ explicitly requested by this procedure via outputs based on a <template/>!
         ⧉ **ASE**: ☻ skill: **ase-sync-reconcile**, ▶ ERROR: unknown artifact kind: **<kind/>**
         </template>
 
-    4.  <if condition="<source/> is empty">
+    5.  <if condition="<getopt-bidirectional/> is not 'true'">
 
-        Set <source/> to the seven recognized kinds
-        `TASK,SPEC,ARCH,CODE,DOCS,INFR,OTHR` *minus* all kinds present
-        in <target/> (preserving that fixed order). Do not output
-        anything.
+        Remove from <source/> any kind that is also present in <target/>
+        (a kind is never its own source).
 
-        </if>
+        <if condition="<source/> is empty">
 
-    5.  Remove from <source/> any kind that is also present in <target/>
-        (a kind is never its own source). If <source/> is then empty,
-        only output the following <template/> and then immediately *STOP*
+        Only output the following <template/> and then immediately *STOP*
         processing the entire current skill:
 
         <template>
         ⧉ **ASE**: ☻ skill: **ase-sync-reconcile**, ▶ ERROR: empty source -- nothing to update from
         </template>
 
+        </if>
+
+        </if>
+
     6.  Report the resolved target and source with the following <template/>:
 
         <template>
@@ -102,7 +107,7 @@ explicitly requested by this procedure via outputs based on a <template/>!
 
     </step>
 
-2.  <step id="STEP 2: Resolve and Read Artifact Files">
+2.  <step id="STEP 2: Resolve and Read Artifacts">
 
     1.  Do not output anything in this STEP 2.
 
@@ -112,52 +117,76 @@ explicitly requested by this procedure via outputs based on a <template/>!
         read the returned `artifacts` array of `{ kind, files }` objects
         to obtain the project-relative file list per kind.
 
-    3.  Read all <source/> artifact files previously resolved and build a
-        precise understanding of the *current state* they represent.
+    3.  <if condition="<hint/> is not empty">
+
+        Honor the filtering <hint/> to reduce the source and/or target
+        artifacts and/or the aspects of those artifacts you should take
+        into account.
+
+        </if>
+
+    4.  Read all (optionally filtered) source and target artifacts
+        previously resolved and build a precise understanding of the
+        *current state* they represent.
 
     </step>
 
-3.  <step id="STEP 3: Internalize Artifact Formats">
+3.  <step id="STEP 3: Update Artifacts">
 
-    1.  Do not output anything in this STEP 3.
+    1.  Internalize and honor the artifact-format conventions:
 
-    2.  Internalize and honor the artifact-format conventions imported above:
-        -   the artifact-set/artifact/aspect meta information of `ase-format-meta.md`,
-        -   the `SPEC` format of `ase-format-spec.md`,
-        -   the `ARCH` format of `ase-format-arch.md`,
-        -   the `TASK` format of `ase-format-task.md`.
+        -   the artifact-set/artifact/aspect meta information (`ase-format-meta.md`),
+        -   the `SPEC` format (`ase-format-spec.md`),
+        -   the `ARCH` format (`ase-format-arch.md`),
+        -   the `TASK` format (`ase-format-task.md`).
 
-        Whenever a target artifact belongs to one of these formatted
+        Whenever a target artifact belongs to one of these
         kinds, the update *MUST* keep it conformant to the
         corresponding format (headings, structure, identifiers, and the
         `<timestamp-modified/>` rule). The kinds `CODE`, `DOCS`, `INFR`,
         and `OTHR` have no dedicated format contract and are treated as
         free-form.
 
-    </step>
+    2.  You *MUST* internalize and strictly honor the **GENERIC TENETS**,
+        the **RECONCILIATION TENETS**, the **REFACTORING TENETS**, and
+        the **CRAFTING TENETS** of the **ASE Tenets** when updating in
+        the following. Do not output anything.
+
+    3.  Once call the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of
+        the `ase` MCP server to find out the current time and store it in
+        <timestamp-modified/>.
+
+    4.  <if condition="<getopt-bidirectional/> is equal 'true'">
+
+        *Bidirectionally update* the <target/> and <source/> artifacts
+        so that they faithfully *reflect the current state* of each
+        other.
+
+        </if>
+        <else>
+
+        *Unidirectionally update* the <target/> artifact files so that
+        they faithfully *reflect the current state* of the <source/>
+        artifacts.
+
+        </else>
 
-4.  <step id="STEP 4: Update Target Artifacts">
+        Keep changes as *surgical* as possible: change only what the
+        input state actually requires, and do *not* rewrite unrelated
+        parts of an output artifact.
 
-    1.  You *MUST* internalize and strictly honor the **GENERIC TENETS**,
-        the **RECONCILIATION TENETS**, the **REFACTORING TENETS**, and the
-        **CRAFTING TENETS** of the **ASE Tenets** when updating in the following. Do not
-        output anything.
+        Apply the update directly to the output artifacts via the
+        `Write`/`Edit` tools.
 
-    2.  *Update* the <target/> artifact files so that they faithfully
-        *reflect the current state* of the <source/> artifacts. Apply the
-        update *directly* to the target files via `Write`/`Edit`, keeping
-        changes as *surgical* as possible: change only what the source
-        state actually requires, and do *not* rewrite unrelated parts of a
-        target artifact.
+        For each formatted output artifact kind, strictly honor its
+        format contract.
 
-        For each formatted target kind, honor its format contract
-        internalized in STEP 3 and, whenever a target artifact is
-        changed, update its `<timestamp-modified/>` line via a call to
-        the `ase_timestamp(format: "yyyy-LL-dd HH:mm")` tool of the
-        `ase` MCP server.
+        Whenever an output artifact is changed and contains a `Modified:
+        <timestamp-modified-old/>` line, replace this with `Modified:
+        <timestamp-modified/>`.
 
-    3.  Report the performed update with the following <template/>, listing
-        one bullet line per changed target file (with <file/> its
+    5.  Report the performed updates with the following <template/>, listing
+        one bullet line per changed output file (with <file/> its
         project-relative path and <note/> an ultra-brief description of
         what was reconciled):
 
@@ -165,14 +194,15 @@ explicitly requested by this procedure via outputs based on a <template/>!
         <ase-tpl-bullet-signal/> **UPDATED ARTIFACTS**:
 
         -   `<file/>`: <note/>
+        [...]
         </template>
 
-        <if condition="no target artifact required any change">
+        <if condition="no output artifact required any change">
 
-        Instead, only output the following <template/>:
+        Only output the following <template/>:
 
         <template>
-        <ase-tpl-bullet-normal/> **UPDATED ARTIFACTS**: none -- target already reflects source state.
+        <ase-tpl-bullet-normal/> **UPDATED ARTIFACTS**: none -- all outputs already reflected source state
         </template>
 
         </if>

package/plugin/skills/ase-sync-reconcile/help.md

@@ -1,66 +1,89 @@
 
 ##  NAME
 
-`ase-sync-reconcile` - Reconcile Artifacts from Artifacts
+`ase-sync-reconcile` - Reconcile Artifact Set to Artifact Set
 
 ##  SYNOPSIS
 
 `ase-sync-reconcile`
     [`--help`|`-h`]
-    *target*[,...]
-    [*source*[,...]]
+    [`--bidirectional`|`-b`]
+    [`--target`|`-t` *target*[,...]]
+    [`--source`|`-s` *source*[,...]]
+    [*hint*]
 
 ##  DESCRIPTION
 
 The `ase-sync-reconcile` skill reconciles one set of artifact kinds (the
 *target*) to *reflect* the *current state* of another set of artifact
 kinds (the *source*). It reads the source artifacts and then adjusts the
-target artifacts *directly* and *surgically* to match the source state.
+target artifacts *directly* and *surgically* to match the source state,
+while optionally honoring a filtering *hint*.
 
 Both *target* and *source* are comma-separated lists over the seven
 recognized artifact kinds `SPEC` (Specification), `ARCH` (Architecture),
 `CODE` (Source Code), `DOCS` (Documentation), `TASK` (Task Plans), `INFR`
-(Infrastructure), and `OTHR` (catch-all). When *source* is omitted, it
-defaults to all seven kinds *minus* the kinds listed in *target*. A kind
-present in *target* is never used as its own source.
-
-The file lists for the kinds `SPEC`, `ARCH`, `CODE`, `DOCS`, `INFR`, and
-`OTHR` are resolved via the `ase_artifact_list` MCP tool; the `TASK` kind
-is resolved generically from the `.ase/task/*/plan.md` task plans. While
-reconciling, the skill honors the artifact-format conventions of
-`ase-format-meta.md`, `ase-format-spec.md`, `ase-format-arch.md`, and
-`ase-format-task.md`; the kinds `CODE`, `DOCS`, `INFR`, and `OTHR` are
-treated as free-form.
+(Infrastructure), and `OTHR` (catch-all). When *source* is `auto`, it
+resolves to all seven kinds *minus* the kinds listed in *target*. Unless
+`--bidirectional` is given, a kind present in *target* is never used as
+its own source.
+
+The file lists for all involved kinds are resolved via the
+`ase_artifact_list` MCP tool of the `ase` MCP server. While reconciling,
+the skill honors the artifact-format conventions of `ase-format-meta.md`,
+`ase-format-spec.md`, `ase-format-arch.md`, and `ase-format-task.md`;
+the kinds `CODE`, `DOCS`, `INFR`, and `OTHR` have no dedicated format
+contract and are treated as free-form.
+
+##  OPTIONS
+
+`--bidirectional`|`-b`:
+    Reconcile the *target* and *source* artifacts so that they
+    faithfully reflect the current state of *each other*, instead of
+    only updating the *target* from the *source*. With this flag, a kind
+    present in *target* is *not* removed from *source*.
+
+`--target`|`-t` *target*[,...]:
+    The comma-separated list of artifact kinds to update. Required (the
+    skill errors out on an empty target).
+
+`--source`|`-s` *source*[,...]:
+    The comma-separated list of artifact kinds to update *from*. The
+    special value `auto` resolves to all recognized kinds except those
+    in *target*.
 
 ##  ARGUMENTS
 
-*target*[,...]:
-    The comma-separated list of artifact kinds to update.
-
-*source*[,...]:
-    The comma-separated list of artifact kinds to update *from*. When
-    omitted, it defaults to all recognized kinds except those in *target*.
+*hint*:
+    An optional free-form filtering hint that narrows the source and/or
+    target artifacts, or the aspects of those artifacts to take into
+    account during reconciliation.
 
 ##  EXAMPLES
 
-Reconcile the specification to reflect the current source code:
+Reconcile the code and documentation
+to reflect the current specification and architecture
+in a "forward engineering" approach:
 
 ```text
-❯ /ase-sync-reconcile SPEC CODE
+❯ /ase-sync-reconcile -t CODE,DOCS -s SPEC,ARCH
 ```
 
-Reconcile specification and architecture from everything else:
+Reconcile specification and architecture from everything else
+in a "reverse engineering" approach:
 
 ```text
-❯ /ase-sync-reconcile SPEC,ARCH
+❯ /ase-sync-reconcile -t SPEC,ARCH -s CODE,DOCS
 ```
 
-Reconcile the documentation from the code and the architecture:
+Bidirectionally reconcile specification and architecture against
+each other, limited to the authentication aspect:
 
 ```text
-❯ /ase-sync-reconcile DOCS CODE,ARCH
+❯ /ase-sync-reconcile -b -t SPEC -s ARCH authentication
 ```
 
 ##  SEE ALSO
 
-[`ase-meta-changelog`](../ase-meta-changelog/help.md), [`ase-arch-analyze`](../ase-arch-analyze/help.md), [`ase-arch-discover`](../ase-arch-discover/help.md).
+[`ase-meta-changelog`](../ase-meta-changelog/help.md),
+[`ase-task-implement`](../ase-task-implement/help.md)

package/plugin/skills/ase-task-condense/SKILL.md

@@ -35,12 +35,6 @@ semantics exactly.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <instruction><getopt-arguments/></instruction> initially.

package/plugin/skills/ase-task-delete/SKILL.md

@@ -29,12 +29,6 @@ Delete a Task Plan
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <id><getopt-arguments/></id> initially, with any leading and trailing

package/plugin/skills/ase-task-edit/SKILL.md

@@ -39,12 +39,6 @@ preflight.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 <define name="apply-refinement">
 Treat the <instruction/> as a *refinement instruction* for
 the plan, and update <content/> in-place by *applying* the

package/plugin/skills/ase-task-grill/SKILL.md

@@ -36,12 +36,6 @@ task plan until reaching a shared understanding.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <id><getopt-arguments/></id> initially.

package/plugin/skills/ase-task-implement/SKILL.md

@@ -35,12 +35,6 @@ with a corresponding, complete *change set*.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <instruction><getopt-arguments/></instruction> initially.

package/plugin/skills/ase-task-preflight/SKILL.md

@@ -35,12 +35,6 @@ for a corresponding, *complete source code change set*.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <instruction><getopt-arguments/></instruction> initially.

package/plugin/skills/ase-task-reboot/SKILL.md

@@ -35,12 +35,6 @@ based on the existing *WHAT* and *WHY*.
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <instruction><getopt-arguments/></instruction> initially.

package/plugin/skills/ase-task-rename/SKILL.md

@@ -29,12 +29,6 @@ Rename a Task Plan
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Parse <arguments><getopt-arguments/></arguments> into a whitespace-separated

package/plugin/skills/ase-task-view/SKILL.md

@@ -31,12 +31,6 @@ View a Task Plan
 Procedure
 ---------
 
-You *MUST* follow the following numbered items *strictly* *sequentially*!
-You *MUST* not skip any numbered item during processing!
-
-You *MUST* *NOT* output anything in this entire procedure, *except* when
-explicitly requested by this procedure via outputs based on a <template/>!
-
 1.  **Determine Task:**
 
     1.  Set <id><getopt-arguments/></id> initially, with any leading and trailing