@rse/ase 0.9.57 → 0.9.59

package/plugin/package.json

@@ -6,7 +6,7 @@
     "homepage":                             "https://ase.tools",
     "repository":                           { "url": "git+https://github.com/rse/ase.git", "type": "git" },
     "bugs":                                 { "url": "https://github.com/rse/ase/issues" },
-    "version":                              "0.9.57",
+    "version":                              "0.9.59",
     "license":                              "Apache-2.0",
     "author": {
         "name":                             "Dr. Ralf S. Engelschall",

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

@@ -1,6 +1,6 @@
 ---
 name: ase-code-craft
-argument-hint: "[--help|-h] [--auto|-a] [--dry|-d] [--quick|-Q] [--next|-n <option>[,...]] [<task-id>:] <feature>"
+argument-hint: "[--help|-h] [--auto|-a] [--dry|-d] [--direct|-D] [--quick|-Q] [--next|-n <option>[,...]] [<task-id>:] <feature>"
 description: >
     Craft Source Code:
     Use when user wants to "create", "add", or "craft" a new feature from scratch.
@@ -10,6 +10,7 @@ effort: xhigh
 allowed-tools:
     - "Skill"
     - "Agent"
+    - "Read"
 ---
 
 @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
@@ -23,7 +24,7 @@ Craft Source Code
 
 <expand name="getopt"
     arg1="ase-code-craft"
-    arg2="--auto|-a --dry|-d --quick|-Q --next|-n=(none|DONE|EDIT|GRILL|PREFLIGHT|IMPLEMENT)...">
+    arg2="--auto|-a --dry|-d --direct|-D --quick|-Q --next|-n=(none|DONE|EDIT|GRILL|PREFLIGHT|IMPLEMENT)...">
     $ARGUMENTS
 </expand>
 
@@ -45,9 +46,18 @@ From scratch *craft* the following feature:
 Procedure
 ---------
 
+<if condition="<getopt-option-direct/> is not equal to 'true'">
 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(...)`.
+</if>
+<else>
+The `--direct`/`-D` mode applies the crafting *in place*, so STEP 4
+below *requires* `Edit` and `Write` to modify the affected artifacts.
+Every modification *MUST* still stay restricted to the artifacts the
+crafting actually demands, and you *MUST* *NOT* call
+`ase_task_save(...)`, as no task plan is composed at all.
+</else>
 
 <flow>
 
@@ -136,13 +146,41 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     </step>
 
-4.  <step id="STEP 4: Choose Feature Crafting Approaches">
+4.  <if condition="<getopt-option-direct/> is equal to 'true'">
+
+    <step id="STEP 4: Direct Feature Crafting">
+
+    1.  Directly craft the <feature/> by modifying the affected
+        *artifacts* with a corresponding, complete *change set*,
+        based on your gathered knowledge about the code base and your
+        internalized crafting tenets. Also, if a CHANGELOG.md
+        file exists, make an appropriate entry there, too.
+
+    2.  Output only the following <template/>:
+
+        <template>
+        ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **changes directly applied**
+        </template>
+
+    3.  Then *IMMEDIATELY* *STOP* all further skill processing. You
+        *MUST* *NOT* output anything else in this STEP 4 or after it --
+        *independent* of <ase-project-boxing/>, whose exposure rules
+        are explicitly *overridden* here. Especially, do not output a
+        change summary, a list of modified artifacts, a rationale, or
+        a unified diff of the changes.
+
+    </step>
+
+    </if>
+    <else>
+
+    <step id="STEP 4: Choose Feature Crafting Approaches">
 
     <expand name="code-approaches" arg1="feature" arg2="crafting"></expand>
 
     </step>
 
-5.  <step id="STEP 5: Compose Feature Crafting Plan">
+    <step id="STEP 5: 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
@@ -187,4 +225,6 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     </step>
 
+    </else>
+
 </flow>

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

@@ -9,6 +9,7 @@
     [`--help`|`-h`]
     [`--auto`|`-a`]
     [`--dry`|`-d`]
+    [`--direct`|`-D`]
     [`--quick`|`-Q`]
     [`--next`|`-n` *option*[,...]]
     [*task-id*:] *feature*
@@ -22,10 +23,11 @@ investigating the existing code base, internalizing crafting tenets
 preferred approach, and composing a corresponding *task plan* aligned
 with the existing architecture.
 
-The skill does *not* directly modify source files. It persists the
-plan via `ase_task_save` and then hands off to `ase-task-edit`,
-`ase-task-preflight`, or `ase-task-implement`, as selected by
-`--next`.
+By default the skill does *not* directly modify source files. It
+persists the plan via `ase_task_save` and then hands off to
+`ase-task-edit`, `ase-task-preflight`, or `ase-task-implement`, as
+selected by `--next`. Only under `--direct` it skips the plan
+entirely and applies the change set to the affected artifacts itself.
 
 ##  OPTIONS
 
@@ -40,6 +42,15 @@ plan via `ase_task_save` and then hands off to `ase-task-edit`,
     type-checker, or program execution) once the source files have
     been modified.
 
+`--direct`|`-D`:
+    Craft the feature *immediately* and *in place*: skip the
+    feature approaches, the interactive dialog, and the entire task
+    plan ceremony, and directly apply the complete change set to the
+    affected artifacts, including a corresponding entry in an existing
+    `CHANGELOG.md` file. In this mode `--auto`, `--dry`, `--quick`, and
+    `--next` have no effect, as neither approaches are proposed nor a
+    plan is composed.
+
 `--quick`|`-Q`:
     Shorthand alias for `-a -d -n IMPLEMENT,DELETE`: automatically pick
     the recommended feature approach, compose the plan *without* the

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

@@ -169,7 +169,28 @@ Procedure
 3.  <step id="STEP 3: Detect Target Collisions"
         condition="<getopt-option-dry/> is not equal `true`">
 
-    1.  Determine the *existing worktrees* and *existing branches* by
+    1.  Determine the *worktree directory* of every part by calling the
+        `ase_worktree_path(id: "<part-id/>", create: true)` tool of the
+        `ase` MCP server once per <part-id/> of <parts/> and capturing
+        its output into the <part-dir/> of that part.
+
+        You *MUST* *NEVER* assemble such a path yourself, as only this
+        tool rejects a path leading through a symbolic link, through a
+        non-directory, or out of the repository -- a path both `git
+        worktree add` and `git worktree remove` would otherwise silently
+        follow and thereby write outside the repository.
+
+        <if condition="this tool call fails for any part">
+        Only output the following <template/> and then immediately *STOP*
+        processing the entire current skill, leaving the working copy and
+        *all* existing worktrees and branches untouched:
+
+        <template>
+        ⧉ **ASE**: ✪ skill: **ase-code-dissect**, ▶ ERROR: unsafe worktree directory -- cannot create worktrees
+        </template>
+        </if>
+
+    2.  Determine the *existing worktrees* and *existing branches* by
         running the corresponding commands (taken exactly as given) and
         capturing their outputs:
 
@@ -177,11 +198,11 @@ Procedure
 
         `git branch --list`
 
-    2.  Set <collisions/> to all <part-id/> of <parts/> for which either
-        a worktree directory `<repo-root/>/.ase/worktree/<part-id/>` or
-        a branch `<part-id/>` already exists.
+    3.  Set <collisions/> to all <part-id/> of <parts/> for which either
+        the worktree directory <part-dir/> or a branch `<part-id/>`
+        already exists.
 
-    3.  <if condition="<collisions/> is not empty AND <getopt-option-force/> is not equal `true`">
+    4.  <if condition="<collisions/> is not empty AND <getopt-option-force/> is not equal `true`">
         Only output the following <template/> -- with <collisions/>
         rendered as a comma-separated list of code spans -- and then
         immediately *STOP* processing the entire current skill, leaving
@@ -202,13 +223,13 @@ Procedure
         </ase-tpl-hint>
         </if>
 
-    4.  <if condition="<collisions/> is not empty AND <getopt-option-force/> is equal `true`">
+    5.  <if condition="<collisions/> is not empty AND <getopt-option-force/> is equal `true`">
         *Remove* every colliding target by running the corresponding
         commands (taken exactly as given) per colliding <part-id/>, and
         silently ignore the failure of an individual command when the
         corresponding worktree or branch does not exist:
 
-        `git worktree remove --force "<repo-root/>/.ase/worktree/<part-id/>"`
+        `git worktree remove --force "<part-dir/>"`
 
         `git worktree prune`
 
@@ -255,7 +276,7 @@ Procedure
             git-ignored, so the worktree itself never shows up as a
             change:
 
-            `git worktree add "<repo-root/>/.ase/worktree/<part-id/>"`
+            `git worktree add "<part-dir/>"`
 
             <if condition="this command fails">
             Only output the following <template/>, then *continue* with
@@ -270,7 +291,7 @@ Procedure
         4.  Apply the patch *inside* the freshly created worktree by
             running the corresponding command (taken exactly as given):
 
-            `git -C "<repo-root/>/.ase/worktree/<part-id/>" apply --whitespace=nowarn "<tmp-dir/>/ase-dissect-<part-id/>.patch"`
+            `git -C "<part-dir/>" apply --whitespace=nowarn "<tmp-dir/>/ase-dissect-<part-id/>.patch"`
 
             <if condition="this command fails">
             Only output the following <template/>, then *continue* with

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

@@ -208,6 +208,20 @@ related to a set of code quality aspects.
             1.  Set <file/>         to the `file`         field of <item/>.
                 Set <change-hunks/> to the `change-hunks` field of <item/>.
 
+                Unless <ase-project-boxing/> is equal `grey` (where the
+                full unified diff is suppressed and no context lines are
+                rendered at all), *silently* read the current content of
+                <file/> with the `Read` tool - reusing the content read
+                for the same <file/> earlier in this iteration, unless
+                an `Edit` was applied to it in between - and set
+                <file-lines/> to its lines, *stripped* of the
+                line-number prefixes the tool adds. Set <file-lines/>
+                to empty if the file cannot be read.
+
+                This content is the *authoritative* source of the
+                context lines of substep 2 below, so the rendered diff
+                shows real context even when a sub-agent supplied none.
+
                 Unless <ase-project-boxing/> is equal `grey` (where the
                 full unified diff is suppressed and this per-file header is
                 unused), set <diff-file/> to the following <template/>:
@@ -240,6 +254,18 @@ related to a set of code quality aspects.
                     to its *last* two lines and <context-after/> to its
                     *first* two lines.
 
+                    Then, whenever <file-lines/> is non-empty,
+                    *re-derive* both context parts from it, *overriding*
+                    the sub-agent supplied values: set <context-before/>
+                    to the *up to two* lines of <file-lines/> directly
+                    *before* line <line/> (empty if <line/> is `1`) and
+                    <context-after/> to the *up to two* lines of
+                    <file-lines/> starting at line (<line/> + <n/>),
+                    where <n/> is the number of lines in <old-text/>
+                    (empty if that line is beyond the end of the file).
+                    Keep the sub-agent supplied values only when
+                    <file-lines/> is empty.
+
                 2.  *Skip* this substep entirely when <ase-project-boxing/>
                     is equal `grey` - the full unified diff is suppressed
                     there, so none of the <hunk-body/>, <old-count/>,

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

@@ -1,6 +1,6 @@
 ---
 name: ase-code-refactor
-argument-hint: "[--help|-h] [--auto|-a] [--dry|-d] [--quick|-Q] [--next|-n <option>[,...]] [<task-id>:] <request>"
+argument-hint: "[--help|-h] [--auto|-a] [--dry|-d] [--direct|-D] [--quick|-Q] [--next|-n <option>[,...]] [<task-id>:] <request>"
 description: >
     Refactor Code:
     Use when user wants to "refactor" or "change" the code base.
@@ -10,6 +10,7 @@ effort: xhigh
 allowed-tools:
     - "Skill"
     - "Agent"
+    - "Read"
 ---
 
 @${CLAUDE_SKILL_DIR}/../../meta/ase-control.md
@@ -23,7 +24,7 @@ Refactor Source Code
 
 <expand name="getopt"
     arg1="ase-code-refactor"
-    arg2="--auto|-a --dry|-d --quick|-Q --next|-n=(none|DONE|EDIT|GRILL|PREFLIGHT|IMPLEMENT)...">
+    arg2="--auto|-a --dry|-d --direct|-D --quick|-Q --next|-n=(none|DONE|EDIT|GRILL|PREFLIGHT|IMPLEMENT)...">
     $ARGUMENTS
 </expand>
 
@@ -45,9 +46,18 @@ to `true`, <getopt-option-dry/> to `true`, and <getopt-option-next/> to
 Procedure
 ---------
 
+<if condition="<getopt-option-direct/> is not equal to 'true'">
 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(...)`.
+</if>
+<else>
+The `--direct`/`-D` mode applies the refactoring *in place*, so STEP 4
+below *requires* `Edit` and `Write` to modify the affected artifacts.
+Every modification *MUST* still stay restricted to the artifacts the
+refactoring actually demands, and you *MUST* *NOT* call
+`ase_task_save(...)`, as no task plan is composed at all.
+</else>
 
 <flow>
 
@@ -136,13 +146,41 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     </step>
 
-4.  <step id="STEP 4: Choose Refactoring Approaches">
+4.  <if condition="<getopt-option-direct/> is equal to 'true'">
+
+    <step id="STEP 4: Direct Refactoring">
+
+    1.  Directly apply the refactoring <request/> by modifying the
+        affected *artifacts* with a corresponding, complete *change set*,
+        based on your gathered knowledge about the code base and your
+        internalized refactoring tenets. Also, if a CHANGELOG.md
+        file exists, make an appropriate entry there, too.
+
+    2.  Output only the following <template/>:
+
+        <template>
+        ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **changes directly applied**
+        </template>
+
+    3.  Then *IMMEDIATELY* *STOP* all further skill processing. You
+        *MUST* *NOT* output anything else in this STEP 4 or after it --
+        *independent* of <ase-project-boxing/>, whose exposure rules
+        are explicitly *overridden* here. Especially, do not output a
+        change summary, a list of modified artifacts, a rationale, or
+        a unified diff of the changes.
+
+    </step>
+
+    </if>
+    <else>
+
+    <step id="STEP 4: Choose Refactoring Approaches">
 
     <expand name="code-approaches" arg1="refactoring" arg2="refactoring"></expand>
 
     </step>
 
-5.  <step id="STEP 5: Compose Refactoring Plan">
+    <step id="STEP 5: Compose Refactoring Plan">
 
     1.  *Compose a refactoring plan* for the chosen refactoring A<n/> by
         closely aligning to the existing architecture and the existing
@@ -187,5 +225,7 @@ permitted way to persist artifacts is via `ase_task_save(...)`.
 
     </step>
 
+    </else>
+
 </flow>
 

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

@@ -9,6 +9,7 @@
     [`--help`|`-h`]
     [`--auto`|`-a`]
     [`--dry`|`-d`]
+    [`--direct`|`-D`]
     [`--quick`|`-Q`]
     [`--next`|`-n` *option*[,...]]
     [*task-id*:] *request*
@@ -22,10 +23,11 @@ clear interfaces, ...), proposing one or more *refactoring approaches*
 with pros and cons, letting the user pick the preferred approach,
 and composing a corresponding *task plan*.
 
-The skill does *not* directly modify source files. It persists the
-plan via `ase_task_save` and then hands off to `ase-task-edit`,
-`ase-task-preflight`, or `ase-task-implement`, as selected by
-`--next`.
+By default the skill does *not* directly modify source files. It
+persists the plan via `ase_task_save` and then hands off to
+`ase-task-edit`, `ase-task-preflight`, or `ase-task-implement`, as
+selected by `--next`. Only under `--direct` it skips the plan
+entirely and applies the change set to the affected artifacts itself.
 
 ##  OPTIONS
 
@@ -40,6 +42,15 @@ plan via `ase_task_save` and then hands off to `ase-task-edit`,
     type-checker, or program execution) once the source files have
     been modified.
 
+`--direct`|`-D`:
+    Apply the refactoring *immediately* and *in place*: skip the
+    refactoring approaches, the interactive dialog, and the entire task
+    plan ceremony, and directly apply the complete change set to the
+    affected artifacts, including a corresponding entry in an existing
+    `CHANGELOG.md` file. In this mode `--auto`, `--dry`, `--quick`, and
+    `--next` have no effect, as neither approaches are proposed nor a
+    plan is composed.
+
 `--quick`|`-Q`:
     Shorthand alias for `-a -d -n IMPLEMENT,DELETE`: automatically pick
     the recommended refactoring approach, compose the plan *without* the

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

@@ -206,8 +206,18 @@ resolution actually demands, and you *MUST* *NOT* call
         internalized problem resolution tenets. Also, if a CHANGELOG.md
         file exists, make an appropriate entry there, too.
 
-    2.  Do not output anything else in this STEP 4. Especially, do not
-        output a change summary or a unified diff of the changes.
+    2.  Output only the following <template/>:
+
+        <template>
+        ⧉ **ASE**: ◉ task: **<ase-task-id/>**, ▶ status: **changes directly applied**
+        </template>
+
+    3.  Then *IMMEDIATELY* *STOP* all further skill processing. You
+        *MUST* *NOT* output anything else in this STEP 4 or after it --
+        *independent* of <ase-project-boxing/>, whose exposure rules
+        are explicitly *overridden* here. Especially, do not output a
+        change summary, a list of modified artifacts, a rationale, or
+        a unified diff of the changes.
 
     </step>
 

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

@@ -163,6 +163,27 @@ Analyze documents for spelling, punctuation, or grammar errors
             <context-before/> to its *last* two lines and
             <context-after/> to its *first* two lines.
 
+            Then, unless <ase-project-boxing/> is equal `grey` (where
+            the full unified diff is suppressed and no context lines are
+            rendered at all), *silently* read the current content of
+            <file/> with the `Read` tool - reusing the content read for
+            the same <file/> earlier in this iteration, unless an `Edit`
+            was applied to it in between - and set <file-lines/> to its
+            lines, *stripped* of the line-number prefixes the tool adds.
+            Set <file-lines/> to empty if the file cannot be read.
+
+            Whenever <file-lines/> is non-empty, *re-derive* both
+            context parts from it, *overriding* the sub-agent supplied
+            values, so the rendered diff shows real context even when a
+            sub-agent supplied none: set <context-before/> to the *up to
+            two* lines of <file-lines/> directly *before* line <line/>
+            (empty if <line/> is `1`) and <context-after/> to the *up
+            to two* lines of <file-lines/> starting at line (<line/> +
+            <n/>), where <n/> is the number of lines in <old-text/>
+            (empty if that line is beyond the end of the document).
+            Keep the sub-agent supplied values only when <file-lines/>
+            is empty.
+
         2.  Report the problem with the following <template/>:
 
             <template>

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

@@ -82,25 +82,29 @@ Procedure
         directly usable as both a directory and a branch name. Do not
         output anything.
 
-    2.  Determine the *repository root* by running the corresponding
-        command (taken exactly as given) and capturing its output into
-        <repo-root/>:
-
-        `git rev-parse --show-toplevel`
-
-        <if condition="this command fails">
-        The current directory is not a Git repository, so no worktree can be
-        created. Only output the following <template/> and then
-        immediately *STOP* processing the entire current skill, leaving
-        the working copy *untouched*:
+    2.  Determine the *worktree directory* by calling the
+        `ase_worktree_path(id: "<worktree-name/>", create: true)` tool of
+        the `ase` MCP server and capturing its output into
+        <worktree-dir/>.
+
+        You *MUST* *NEVER* assemble this path yourself, as only this tool
+        rejects a path leading through a symbolic link, through a
+        non-directory, or out of the repository -- a path `git worktree
+        add` would otherwise silently follow and thereby write outside
+        the repository.
+
+        <if condition="this tool call fails">
+        Either the current directory is not a Git repository or the
+        worktree directory is unsafe, so no worktree can be created. Only
+        output the following <template/> and then immediately *STOP*
+        processing the entire current skill, leaving the working copy
+        *untouched*:
 
         <template>
-        ⧉ **ASE**: ☻ skill: **ase-task-implement**, ▶ ERROR: no Git repository -- cannot create worktree
+        ⧉ **ASE**: ☻ skill: **ase-task-implement**, ▶ ERROR: no Git repository or unsafe worktree directory -- cannot create worktree
         </template>
         </if>
 
-        Then set <worktree-dir><repo-root/>/.ase/worktree/<worktree-name/></worktree-dir>.
-
     3.  Determine the *existing worktrees* and *existing branches* by
         running the corresponding commands (taken exactly as given) and
         capturing their outputs: