@rse/ase 0.0.38 → 0.0.40

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":                              "0.0.38",
+    "version":                              "0.0.40",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

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

@@ -1,6 +1,6 @@
 {
     "name":        "ase",
-    "version":     "0.0.38",
+    "version":     "0.0.40",
     "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":     "0.0.38",
+    "version":     "0.0.40",
     "description": "Agentic Software Engineering (ASE)",
     "keywords":    [ "agentic", "software", "engineering" ],
     "homepage":    "https://ase.tools",

package/plugin/meta/ase-constitution.md

@@ -110,5 +110,6 @@ Tenets
 Persona
 -------
 
-@./ase-skill.md
+@./ase-control.md
 @./ase-persona.md
+

package/plugin/meta/ase-control.md

@@ -0,0 +1,63 @@
+
+Control Flow Constructs
+-----------------------
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <define name="<define-name/>"><define-body/></define>:
+
+    This specifies a *reusable definition* named <define-name/> and
+    an <define-body/> which can contain arbitrary information with
+    optional `<args/>` (or alternatively, individual `<arg1/>`,
+    `<arg2/>`, etc) and optional `<content/>` references from
+    subsequent <expand/> calls.
+    This construct is expanded into nothing.
+    Do not output anything.
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <expand name="<define-name/>" [arg1="<expand-arg1/>" [arg2="<expand-arg2/>]" [...]]]><expand-content/></expand>:
+
+    This specifies the *expansion* of previous <define/>.
+    This construct is expanded into the <define-body/> of <define/>
+    with `<args/>` substituted with `<expand-arg1/> <expand-arg2/>
+    [...]`, `<arg1/>` substituted with <expand-arg1/>, and `<content/>`
+    substituted with <expand-content/>.
+    Do not output anything else.
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <flow><flow-body/></flow>:
+
+    This specifies a *sequential flow* of <step/>s, which have
+    to be followed/executed in exactly the given order.
+    This construct is expanded to its <flow-body/>.
+    Do not output anything else.
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <step id="<id/>"><step-body/></step>:
+
+    This specifies a distinct *single step* in a <flow/>.
+    This construct is expanded to its <step-body/>.
+    Do not output anything else.
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <if condition="<if-condition/>"><if-body/></if>:
+
+    This specifies a simple condition which is expanded to <if-body/>
+    if <if-condition/> is met, or to empty string if <if-condition/> is
+    *not* met. Do not output anything else.
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <while condition="<while-condition/>"><while-body/></while>:
+
+    This specifies a <while-body/> which is *repeated* as long as
+    <while-condition/> is met. This construct is expanded to the
+    repetition of <while-body/>. Do not output anything else.
+
+-   *IMPORTANT*: You *MUST* honor the following control flow construct:
+    <for items="<for-item/> [...]"><for-body/></for>:
+
+    This specifies a <for-body/> which is *repeated* for all
+    <for-item/>s and where `<item/>` is expanded with the current
+    <for-item/> in <for-body/>. This construct is expanded to the
+    repetition of <for-body/>. A <break/> in <for-body/> can stop the
+    repetition early. Do not output anything else.
+

package/plugin/meta/ase-persona.md

@@ -61,3 +61,4 @@ Apply Persona
     -   Apply ruleset "level2": <expand name="level2"/>
     -   Apply ruleset "level3": <expand name="level3"/>
     </if>
+

package/plugin/meta/ase-skill.md

@@ -90,68 +90,6 @@ Skill Output
         Skills that report severity MUST support `ACCEPTED`
         in addition to `LOW`, `MEDIUM`, and `HIGH`.
 
-Skill Control Flow
-------------------
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <define name="<define-name/>"><define-body/></define>:
-
-    This specifies a *reusable definition* named <define-name/> and
-    an <define-body/> which can contain arbitrary information with
-    optional `<args/>` (or alternatively, individual `<arg1/>`,
-    `<arg2/>`, etc) and optional `<content/>` references from
-    subsequent <expand/> calls.
-    This construct is expanded into nothing.
-    Do not output anything.
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <expand name="<define-name/>" [arg1="<expand-arg1/>" [arg2="<expand-arg2/>]" [...]]]><expand-content/></expand>:
-
-    This specifies the *expansion* of previous <define/>.
-    This construct is expanded into the <define-body/> of <define/>
-    with `<args/>` substituted with `<expand-arg1/> <expand-arg2/>
-    [...]`, `<arg1/>` substituted with <expand-arg1/>, and `<content/>`
-    substituted with <expand-content/>.
-    Do not output anything else.
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <flow><flow-body/></flow>:
-
-    This specifies a *sequential flow* of <step/>s, which have
-    to be followed/executed in exactly the given order.
-    This construct is expanded to its <flow-body/>.
-    Do not output anything else.
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <step id="<id/>"><step-body/></step>:
-
-    This specifies a distinct *single step* in a <flow/>.
-    This construct is expanded to its <step-body/>.
-    Do not output anything else.
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <if condition="<if-condition/>"><if-body/></if>:
-
-    This specifies a simple condition which is expanded to <if-body/>
-    if <if-condition/> is met, or to empty string if <if-condition/> is
-    *not* met. Do not output anything else.
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <while condition="<while-condition/>"><while-body/></while>:
-
-    This specifies a <while-body/> which is *repeated* as long as
-    <while-condition/> is met. This construct is expanded to the
-    repetition of <while-body/>. Do not output anything else.
-
--   *IMPORTANT*: You *MUST* honor the following control flow construct:
-    <for items="<for-item/> [...]"><for-body/></for>:
-
-    This specifies a <for-body/> which is *repeated* for all
-    <for-item/>s and where `<item/>` is expanded with the current
-    <for-item/> in <for-body/>. This construct is expanded to the
-    repetition of <for-body/>. A <break/> in <for-body/> can stop the
-    repetition early. Do not output anything else.
-
 Skill Sequential Processing
 ---------------------------
 
@@ -237,3 +175,4 @@ Skill Identification
   <template>
   ⧉ **ASE**: ◎ objective: **<objective/>**
   </template>
+

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":                              "0.0.38",
+    "version":                              "0.0.40",
     "license":                              "GPL-3.0-only",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

package/plugin/skills/ase-arch-analyze/SKILL.md

@@ -99,6 +99,7 @@ allowed-tools:
     - "Skill"
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 
@@ -302,11 +303,13 @@ interface quality, quality attributes, and architecture governance.
     - For <style/>, name the detected architecture style or
       "*undeclared*" if none is documented.
 
-    - For <rendered-diagram-as-fenced-code-block/>, emit *Mermaid*
-      source for a `flowchart TB` of the high-level component or
-      layer structure and invoke the `ase-meta-diagram` skill via the
-      `Skill` tool to render it. Show layers / slices / major
-      components and their dependency direction.
+    - For <rendered-diagram-as-fenced-code-block/>, build a Mermaid
+      specification <mermaid-spec/> for a `flowchart TB` of the
+      high-level component or layer structure and invoke the
+      `ase-meta-diagram` skill by calling the tool `Skill(skill:
+      "ase:ase-meta-diagram", args: <mermaid-spec/>)` to render it.
+      Show layers / slices / major components and their dependency
+      direction.
 
     - Mark detected *anomalies* directly in the Mermaid source.
       Because `!` and `?` are Mermaid special characters, *always

package/plugin/skills/ase-arch-discover/SKILL.md

@@ -15,6 +15,7 @@ allowed-tools:
     - "WebFetch"
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 

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

@@ -10,6 +10,7 @@ allowed-tools:
     - "Agent"
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 

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

@@ -11,6 +11,7 @@ allowed-tools:
     - "Skill"
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-dialog.md
@@ -74,7 +75,7 @@ permitted way to persist artifacts is via `task_save(...)`.
         <feature><text/></feature> and <ase-task-id><id/></ase-task-id>
         and call the `task_id(id: <ase-task-id/>, session:
         <ase-session-id/>)` tool from the `ase` MCP service to
-        implicitly switch the task.
+        implicitly switch the task. Do not output anything.
 
     3.  If <feature/> is empty,
         ask the user interactively, without a special tool, for the
@@ -92,7 +93,7 @@ permitted way to persist artifacts is via `task_save(...)`.
         which consists of two lower-case words concatenated with a
         `-` character. Then call the `task_id(id: <ase-task-id/>,
         session: <ase-session-id/>)` tool from the `ase` MCP service to
-        implicitly switch the task.
+        implicitly switch the task. Do not output anything.
         </if>
 
     5.  Report the task and feature with the following <template/>:
@@ -119,40 +120,12 @@ permitted way to persist artifacts is via `task_save(...)`.
 
     3.  Do not output anything in this step.
 
-3.  **Find Feature Crafting Approaches**:
+3.  **Internalize Crafting Tenets**:
 
-    1.  *Propose* corresponding *feature approach*, including optionally,
-        some *alternative* feature approaches.
-
-    2.  Annotate the approach you recommend with an <annotation/> of
-        ` ⚝ **RECOMMENDATION** ⚝`.
+    Internalize and honor the following tenets.
+    Do not output anything.
 
-    3.  Report each approach with the following <template/>:
-
-        <template>
-        &#x1F535; **APPROACH A<n/>**<annotation/>: *<summary/>*
-        - [...]
-        - [...]
-        - [...]
-        <optional-diagram/>
-        </template>
-
-        Hints:
-
-        -   Give a short one-sentence <summary/> of the feature approach plus
-            *precise* and *brief* feature information. Try to keep the
-            number of bullet points in the range of 1-4.
-
-        -   In case of a *complex feature situation* only, visualize it with
-            an optional diagram <optional-diagram/> by invoking the
-            `ase-meta-diagram` skill via the `Skill` tool. For *current vs.
-            proposed* comparisons, render each side as a *separate*
-            `ase-meta-diagram` invocation and stack the rendered blocks
-            *vertically* (labels `**Before:**` / `**After:**`); never
-            side-by-side. Omit <optional-diagram/> entirely for simple or
-            purely local situation.
-
-        *Recommended* Tenets (generic):
+    1.  *Recommended* Tenets (generic):
 
         -   **Surgical Changes**:
             Keep source code changes always as small as possible.
@@ -170,20 +143,73 @@ permitted way to persist artifacts is via `task_save(...)`.
             Strictly align with the existing code base by exactly following its
             coding style, its structure, its naming conventions, etc.
 
-        *Essential* Tenets (specific):
+    2.  *Essential* Tenets (feature crafting specific):
 
         -   **High Cohesion, Low Coupling**:
             Strike for a set of small, focused parts (high cohesion) connected by
             thin, explicit wires (low coupling).
 
-4.  **Choose Feature Crafting Approach**:
+4.  **Find Feature Crafting Approaches**:
+
+    You *MUST* perform the following sub-steps *internally* and *without
+    any output* until and including the recommendation decision. Only
+    sub-step 4 below is allowed to produce output.
+
+    1.  *Propose* corresponding *feature approach*, including optionally,
+        some *alternative* feature approaches. Do *not* output anything
+        in this sub-step.
+
+    2.  *Reflect* on and *critique* the proposed approaches by deriving,
+        per approach, a small set of concrete *pros* and *cons*. Do
+        *not* output anything in this sub-step.
+
+    3.  Based on the reflection, *decide* which approach to recommend
+        and annotate it with an <annotation/> of
+        ` ⚝ **RECOMMENDATION** ⚝`. All other approaches receive an
+        empty <annotation/>. Do *not* output anything in this sub-step.
+
+    4.  *Now* report each approach with the following <template/>,
+        inlining its pros/cons derived in sub-step 2:
+
+        <template>
+        &#x1F535; **APPROACH A<n/>**<annotation/>: *<summary/>*
+        ● [...]
+        ● [...]
+        ● [...]
+        ⊕ *pro*: [...]
+        ⊖ *con*: [...]
+        <optional-diagram/>
+        </template>
+
+        Hints:
+
+        -   Give a short one-sentence <summary/> of the feature approach plus
+            *precise* and *brief* feature information. Try to keep the
+            number of bullet points (●) in the range of 1-4.
+
+        -   In case of a *complex feature situation* only, visualize
+            it with an optional diagram <optional-diagram/> by building
+            a Mermaid specification <mermaid-spec/> (e.g. `flowchart
+            TB`, `stateDiagram-v2`, `sequenceDiagram`, `classDiagram`,
+            or `erDiagram`, depending on intent) and invoking the
+            `ase-meta-diagram` skill by calling the tool `Skill(skill:
+            "ase:ase-meta-diagram", args: <mermaid-spec/>)`. For
+            *current vs. proposed* comparisons, render each side as
+            a *separate* `ase-meta-diagram` invocation and stack the
+            rendered blocks *vertically* (labels `**Before:**` /
+            `**After:**`); never side-by-side. Omit <optional-diagram/>
+            entirely for simple or purely local situation.
+
+5.  **Choose Feature Crafting Approach**:
 
     1.  If <getopt-option-auto/> is equal `false`:
         Let the *user interactively choose* the preferred feature
         approach A<n/> with the help of the <user-dialog-tool/> tool.
-        Use the header `Select Approach` and *single-selection* only
-        and provide small *code change previews*. Mark your recommended
-        feature approach with ` ⚝ **RECOMMENDATION** ⚝` here again.
+        Use the header `Select Approach`, use `A<n/>: <short-summary/>`
+        for the option (where <short-summary/> is an ultra brief summary
+        of the approach A<n/>), and *single-selection* only and provide
+        small *code change previews*. Mark your recommended feature
+        approach with ` ⚝ **RECOMMENDATION** ⚝` here again.
 
     2.  If <getopt-option-auto/> is equal `true`:
         Set <n/> to the number of the feature approach A<n/> you recommend.
@@ -193,7 +219,7 @@ permitted way to persist artifacts is via `task_save(...)`.
         ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **auto-chosen approach A<n/>**
         </template>
 
-5.  **Compose Feature Crafting Plan**:
+6.  **Compose Feature Crafting Plan**:
 
     1.  *Compose a feature plan* for the chosen feature A<n/> by
         closely aligning to the existing architecture and the existing
@@ -220,59 +246,9 @@ permitted way to persist artifacts is via `task_save(...)`.
         ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **plan created**
         </template>
 
-    5.  *Determine next step*:
-
-        -   If <getopt-option-next/> matches the regex `^(DONE|EDIT|PREFLIGHT|IMPLEMENT)$`:
-            Honor the pre-selection what to do as the next step.
-            Set <result><getopt-option-next/></result>.
-
-        -   If <getopt-option-next/> is equal to `none`:
-            Let the *user interactively choose* what to do as the next step.
-
-            <expand name="user-dialog">
-                Next Step: How would you like to proceed with the plan?
-                DONE: Stop processing.
-                EDIT: Hand processing off to editing.
-                PREFLIGHT: Hand processing off to preflighting.
-                IMPLEMENT: Hand processing off to implementation.
-            </expand>
-
-    6.  Check the tool <result/> and dispatch accordingly:
-
-        -   If <result/> is `DONE` or `CANCEL`:
-            Only output the following <template/> and then *STOP*.
-
-            <template>
-            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **done**
-            </template>
-
-        -   If <result/> is `EDIT`:
-            Only output the following <template/> and then use the
-            `Skill` tool to invoke the `ase:ase-task-edit` skill in
-            order to edit the plan. Immediately stop processing the
-            current skill once the `Skill` tool was used.
-
-            <template>
-            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **hand off to edit**
-            </template>
-
-        -   If <result/> is `PREFLIGHT`:
-            Only output the following <template/> and then use the
-            `Skill` tool to invoke the `ase:ase-task-preflight` skill in
-            order to preflight the plan. Immediately stop processing the
-            current skill once the `Skill` tool was used.
-
-            <template>
-            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **hand off to preflight**
-            </template>
-
-        -   If <result/> is `IMPLEMENT`:
-            Only output the following <template/> and then use the
-            `Skill` tool to invoke the `ase:ase-task-implement` skill in
-            order to implement the plan. Immediately stop processing the
-            current skill once the `Skill` tool was used.
-
-            <template>
-            ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ✪ plan: **<words/>** words, ▶ status: **hand off to implement**
-            </template>
+    5.  Directly pass-through control to the `ase:ase-task-edit` skill.
+        Set <args></args> (set args to empty). If <getopt-option-next/>
+        is not equal `none`, set <args><args/> --next
+        <getopt-option-next/></args> (append to args). Then call the
+        tool `Skill(skill: "ase:ase-task-edit", args: <args/>)`.
 

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

@@ -12,6 +12,7 @@ allowed-tools:
     - "Agent"
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 
@@ -72,10 +73,12 @@ code and *explain* it in *brief*, *standardized*, and *concise* way.
     Second, draw a diagram to show the control or data flow, code or
     data structure, or code or data relationships. What gives the best
     overall overview of the code?
-    Choose the Mermaid diagram type per intent: `classDiagram` for
-    class/method structure, `sequenceDiagram` for actor/message flow,
-    or `flowchart TB` for boxes-and-lines component layouts.
-    Invoke the `ase-meta-diagram` skill via the `Skill` tool to render the
+    Build a Mermaid specification <mermaid-spec/>, choosing the Mermaid
+    diagram type per intent: `classDiagram` for class/method structure,
+    `sequenceDiagram` for actor/message flow, or `flowchart TB` for
+    boxes-and-lines component layouts. Then invoke the
+    `ase-meta-diagram` skill by calling the tool `Skill(skill:
+    "ase:ase-meta-diagram", args: <mermaid-spec/>)` to render the
     diagram. Do *not* hand-draw.
 
     Keep your explanation *brief* and *concise*.

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

@@ -14,6 +14,7 @@ allowed-tools:
     - "Skill"
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md
 
@@ -90,11 +91,13 @@ Give *insights* into the project through the source code of $ARGUMENTS.
     🔵 **MODULE STRUCTURE**:
     </template>
 
-    Find all modules (or OOP classes) and draw a `flowchart TB`
-    diagram with all modules as boxes and the imports between modules
-    as the directed edges. Invoke the `ase-meta-diagram` skill via the
-    `Skill` tool to render the diagram. Do not display any further
-    explanation except for this diagram.
+    Find all modules (or OOP classes) and build a Mermaid specification
+    <mermaid-spec/> for a `flowchart TB` diagram with all modules as
+    boxes and the imports between modules as the directed edges. Then
+    invoke the `ase-meta-diagram` skill by calling the tool
+    `Skill(skill: "ase:ase-meta-diagram", args: <mermaid-spec/>)`
+    to render the diagram. Do not display any further explanation except
+    for this diagram.
     </step>
 </flow>
 

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

@@ -8,6 +8,7 @@ disable-model-invocation: false
 effort: medium
 ---
 
+@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-persona.md
 @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md