<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/skills/subagent-driven-development, branch dev</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>Merge pull request #2607 from obra/fix/2429-sdd-invocation-text</title>
<updated>2026-11-02T22:36:15+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-11-02T22:36:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=95b0413050c13f3dd974c0744ccfbb6c2721c38c'/>
<id>95b0413050c13f3dd974c0744ccfbb6c2721c38c</id>
<content type='text'>
skills(sdd, executing-plans): run helpers by absolute path from the working tree (#2429, #2525)</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
skills(sdd, executing-plans): run helpers by absolute path from the working tree (#2429, #2525)</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2606 from obra/fix/2429-sdd-repo-resolution</title>
<updated>2026-11-02T22:01:03+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-11-02T22:01:03+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=2f5dc3b335c05e8e3078c0be056c1001baa6b554'/>
<id>2f5dc3b335c05e8e3078c0be056c1001baa6b554</id>
<content type='text'>
fix(sdd): helpers act on the current directory's repo like git, with -C to override (#2429)</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(sdd): helpers act on the current directory's repo like git, with -C to override (#2429)</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2605 from obra/fix/2436-task-brief-unclosed-fence</title>
<updated>2026-11-02T21:50:41+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-11-02T21:50:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=862308e2b3dade2c6df424115d86e7307961a129'/>
<id>862308e2b3dade2c6df424115d86e7307961a129</id>
<content type='text'>
fix(sdd): task-brief refuses a brief that an unclosed code fence would run to EOF (#2436)</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(sdd): task-brief refuses a brief that an unclosed code fence would run to EOF (#2436)</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2604 from obra/fix/2459-2496-task-brief-headings</title>
<updated>2026-11-02T21:49:28+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-11-02T21:49:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6aeac7ed95b1c31394eca620518e26d592ebd68d'/>
<id>6aeac7ed95b1c31394eca620518e26d592ebd68d</id>
<content type='text'>
fix(sdd): task-brief finds alphanumeric task IDs and explains non-English headings (#2459, #2496)</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(sdd): task-brief finds alphanumeric task IDs and explains non-English headings (#2459, #2496)</pre>
</div>
</content>
</entry>
<entry>
<title>fix(sdd): task-brief refuses a brief an unclosed code fence would run to EOF</title>
<updated>2026-10-23T03:38:19+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T22:26:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=3735a50d5ab4c77ffa0ec7f0423d7414415c0aab'/>
<id>3735a50d5ab4c77ffa0ec7f0423d7414415c0aab</id>
<content type='text'>
task-brief ignores Task headings inside fenced code blocks by toggling a
flag on every ``` line. When a plan leaves a fence open (an edit deletes a
closing fence), the flag stays set for the rest of the file, every later
Task heading is invisible, and the requested task's brief runs to EOF.
The script then reported success: #2436 saw a 177-line task come back as
a 1159-line brief holding tasks 6 through 10, handed to an implementer as
its requirements.

The awk now notes whether a Task heading line appears inside the fence
that is still open at EOF. If one does while the requested task is being
captured, the task's end cannot be found, so task-brief deletes the
partial output and exits 4, naming the line where the fence opened. If
the open fence hides the requested heading itself, it names the fence
before the existing not-found error (exit 3), and suppresses the
"use the English word Task" hint, which would otherwise blame the
plan's English headings for what the fence did.

A fence left open that hides no Task heading changes nothing about the
brief, so it is still written, with a warning on stderr. Real plans do
this: in a corpus of 1,288 plans, refusing on any fence left open at EOF
blocked three correct briefs in two plans, each ending in a stray ``` that
hides no task. With this rule every brief in that corpus matches dev's.
An unclosed fence in a later task leaves an earlier task's brief alone.

The plan path reaches awk through the environment rather than -v, which
would interpret the backslashes of a Windows path as escapes. The fence
rule itself is unchanged, so this composes with #2304's CommonMark fence
tracking: a correct parser still cannot close a fence the author never
closed.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
task-brief ignores Task headings inside fenced code blocks by toggling a
flag on every ``` line. When a plan leaves a fence open (an edit deletes a
closing fence), the flag stays set for the rest of the file, every later
Task heading is invisible, and the requested task's brief runs to EOF.
The script then reported success: #2436 saw a 177-line task come back as
a 1159-line brief holding tasks 6 through 10, handed to an implementer as
its requirements.

The awk now notes whether a Task heading line appears inside the fence
that is still open at EOF. If one does while the requested task is being
captured, the task's end cannot be found, so task-brief deletes the
partial output and exits 4, naming the line where the fence opened. If
the open fence hides the requested heading itself, it names the fence
before the existing not-found error (exit 3), and suppresses the
"use the English word Task" hint, which would otherwise blame the
plan's English headings for what the fence did.

A fence left open that hides no Task heading changes nothing about the
brief, so it is still written, with a warning on stderr. Real plans do
this: in a corpus of 1,288 plans, refusing on any fence left open at EOF
blocked three correct briefs in two plans, each ending in a stray ``` that
hides no task. With this rule every brief in that corpus matches dev's.
An unclosed fence in a later task leaves an earlier task's brief alone.

The plan path reaches awk through the environment rather than -v, which
would interpret the backslashes of a Windows path as escapes. The fence
rule itself is unchanged, so this composes with #2304's CommonMark fence
tracking: a correct parser still cannot close a fence the author never
closed.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(sdd): task-brief says when a plan's task headings are not in English</title>
<updated>2026-10-23T03:38:19+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T22:32:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=750ba92008b88850f6ab321706c7f840bbfff503'/>
<id>750ba92008b88850f6ab321706c7f840bbfff503</id>
<content type='text'>
task-brief recognizes only the English word `Task` in a task heading.
writing-plans' template shows `### Task N:` but never says the word is
machine-read, so a model writing a plan in Spanish writes `## Tarea 1:`.
task-brief and task-start then report "task 1 not found in plan-es.md
(no heading matching 'Task 1')", which reads as "this plan has no task 1"
and sends the controller looking for a task that is on line 3 (#2496).

When a plan has no Task headings at all, task-brief now prints, before the
existing not-found line, that task headings must use the English word
"Task" whatever the plan's language, and lists up to five headings shaped
like tasks (`&lt;word&gt; &lt;id-with-a-digit&gt;`). A plan that has Task headings,
just not the requested one, still gets only the not-found line, so asking
for Task 9 of an eight-task plan stays quiet.

This deliberately does not accept other words. Plans commonly carry
`Phase 1`, `Chunk 2` and `Step 1` headings, and a word-agnostic rule
would turn them into tasks. Keeping the word fixed in the plans
themselves is a writing-plans wording change, which needs evals.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
task-brief recognizes only the English word `Task` in a task heading.
writing-plans' template shows `### Task N:` but never says the word is
machine-read, so a model writing a plan in Spanish writes `## Tarea 1:`.
task-brief and task-start then report "task 1 not found in plan-es.md
(no heading matching 'Task 1')", which reads as "this plan has no task 1"
and sends the controller looking for a task that is on line 3 (#2496).

When a plan has no Task headings at all, task-brief now prints, before the
existing not-found line, that task headings must use the English word
"Task" whatever the plan's language, and lists up to five headings shaped
like tasks (`&lt;word&gt; &lt;id-with-a-digit&gt;`). A plan that has Task headings,
just not the requested one, still gets only the not-found line, so asking
for Task 9 of an eight-task plan stays quiet.

This deliberately does not accept other words. Plans commonly carry
`Phase 1`, `Chunk 2` and `Step 1` headings, and a word-agnostic rule
would turn them into tasks. Keeping the word fixed in the plans
themselves is a writing-plans wording change, which needs evals.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(sdd): task-brief recognizes alphanumeric task IDs and matches them whole</title>
<updated>2026-10-23T03:38:19+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T22:31:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=f75c01fd9b320060c301e2c6591dfc74a8436f15'/>
<id>f75c01fd9b320060c301e2c6591dfc74a8436f15</id>
<content type='text'>
task-brief only treated `Task` followed by digits as a task heading, and
found the requested task by splicing TASK_NUMBER into a regex followed
by `([^0-9]|$)`. Plans that number tasks by lane (`### Task A1`,
`### Task B2`) could not be extracted at all: `task-brief plan.md A1`
exits 3 "task A1 not found" (#2459). Among 1,288 distinct plans in Jesse's
own repositories, 19 plans have such headings (262 headings, IDs like A1,
M3a, F.2, W0), and none of those tasks could be briefed.

The same splice made the match a prefix match: Task 6 also took a sibling
Task 6b (#2175), Task 1 took Task 1.1 and 1.2, Task 2.1 took Task 201
because `.` is any character, and an ID like `6(` crashed awk (#2405).

A task heading is now `Task` followed by an ID made of letters and digits,
optionally dot-separated, that contains at least one digit. The digit is
what keeps `## Task Overview` or `#### Task notes` from becoming a task
boundary. awk extracts the heading's ID and compares it to TASK_NUMBER as
a whole string, so TASK_NUMBER never reaches awk as a regex.

A deeper Task heading whose ID extends the requested one with a letter or
dot is a sub-task and stays in the parent's brief, as the prefix match
happened to do before: plans in that corpus nest `#### Task 1a` under
`### Task 1`, and a Task 1 brief without its sub-tasks would lose most of
its requirements. A sub-task's own brief ends at its next sibling. Depth
alone is not the test, because plans also drift from `## Task 1` to
`### Task 2`, and those are siblings.

The heading word stays the English literal `Task`, which is what
writing-plans' template uses. Widening it to any word would turn the
`Phase 1`, `Chunk 2` and `Step 1` headings that plans commonly carry
(308, 182 and 56 of them in the same corpus) into tasks.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
task-brief only treated `Task` followed by digits as a task heading, and
found the requested task by splicing TASK_NUMBER into a regex followed
by `([^0-9]|$)`. Plans that number tasks by lane (`### Task A1`,
`### Task B2`) could not be extracted at all: `task-brief plan.md A1`
exits 3 "task A1 not found" (#2459). Among 1,288 distinct plans in Jesse's
own repositories, 19 plans have such headings (262 headings, IDs like A1,
M3a, F.2, W0), and none of those tasks could be briefed.

The same splice made the match a prefix match: Task 6 also took a sibling
Task 6b (#2175), Task 1 took Task 1.1 and 1.2, Task 2.1 took Task 201
because `.` is any character, and an ID like `6(` crashed awk (#2405).

A task heading is now `Task` followed by an ID made of letters and digits,
optionally dot-separated, that contains at least one digit. The digit is
what keeps `## Task Overview` or `#### Task notes` from becoming a task
boundary. awk extracts the heading's ID and compares it to TASK_NUMBER as
a whole string, so TASK_NUMBER never reaches awk as a regex.

A deeper Task heading whose ID extends the requested one with a letter or
dot is a sub-task and stays in the parent's brief, as the prefix match
happened to do before: plans in that corpus nest `#### Task 1a` under
`### Task 1`, and a Task 1 brief without its sub-tasks would lose most of
its requirements. A sub-task's own brief ends at its next sibling. Depth
alone is not the test, because plans also drift from `## Task 1` to
`### Task 2`, and those are siblings.

The heading word stays the English literal `Task`, which is what
writing-plans' template uses. Widening it to any word would turn the
`Phase 1`, `Chunk 2` and `Step 1` headings that plans commonly carry
(308, 182 and 56 of them in the same corpus) into tasks.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(sdd): say "by its absolute path" at every helper invocation, and test it</title>
<updated>2026-10-23T00:22:00+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-23T00:08:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=402cfdeed9665ada0b220be12f6ddbd417fb956c'/>
<id>402cfdeed9665ada0b220be12f6ddbd417fb956c</id>
<content type='text'>
The SKILL.md change left skill-relative helper calls elsewhere under
skills/: final-review.md (the final whole-branch review package and its
re-review), fix-loop.md (the scoped re-review), the reviewer prompt
templates' placeholder descriptions, and executing-plans' task-start and
task-done. Each now carries the same qualifier: run the script by its
absolute path, from the working tree you're executing in. Nothing else
in those files changes.

tests/sdd-helper-paths/test-sdd-helper-paths.sh is a structural test
that fails when any skills/ markdown names a helper (sdd-workspace,
task-brief, review-package, task-start, task-done) by a relative
scripts/ path without "by its absolute path" within the next few lines.
It failed on 8 references before this change and passes on all 14
after.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The SKILL.md change left skill-relative helper calls elsewhere under
skills/: final-review.md (the final whole-branch review package and its
re-review), fix-loop.md (the scoped re-review), the reviewer prompt
templates' placeholder descriptions, and executing-plans' task-start and
task-done. Each now carries the same qualifier: run the script by its
absolute path, from the working tree you're executing in. Nothing else
in those files changes.

tests/sdd-helper-paths/test-sdd-helper-paths.sh is a structural test
that fails when any skills/ markdown names a helper (sdd-workspace,
task-brief, review-package, task-start, task-done) by a relative
scripts/ path without "by its absolute path" within the next few lines.
It failed on 8 references before this change and passes on all 14
after.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(sdd): run every SDD helper by absolute path from the working tree</title>
<updated>2026-10-23T00:22:00+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-23T00:00:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=74500c1deba9ba141c9c147e4c78e566282b195f'/>
<id>74500c1deba9ba141c9c147e4c78e566282b195f</id>
<content type='text'>
Following the code change that makes the helpers act only on the
current directory's working tree, give SDD's other skill-relative
`bash scripts/&lt;helper&gt;` invocations (sdd-workspace, task-brief, the
final-review review-package, and the DONE step's review-package) the
same short qualifier executing-plans now uses: run it by its absolute
path, from the working tree you're executing in. In the cwd eval the
one agent that cd'd into the skill directory did it first at the
sdd-workspace line, which never said "from this skill's directory".

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Following the code change that makes the helpers act only on the
current directory's working tree, give SDD's other skill-relative
`bash scripts/&lt;helper&gt;` invocations (sdd-workspace, task-brief, the
final-review review-package, and the DONE step's review-package) the
same short qualifier executing-plans now uses: run it by its absolute
path, from the working tree you're executing in. In the cwd eval the
one agent that cd'd into the skill directory did it first at the
sdd-workspace line, which never said "from this skill's directory".

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(sdd): stop pointing script invocations at the skill directory</title>
<updated>2026-10-23T00:22:00+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T23:29:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6ab1c795ae461987dfb6bfceea094aed6b7f4717'/>
<id>6ab1c795ae461987dfb6bfceea094aed6b7f4717</id>
<content type='text'>
SDD's DONE step said to run review-package "from this skill's directory",
and executing-plans named the scripts by ../subagent-driven-development
paths relative to its own skill directory. The scripts act on the git
repository of the current directory, like git, so an agent that cd's
into the skill directory moves them off the working tree it is
executing in: in 6.3 that silently wrote SDD state into the plugin
cache; now they fall back to the plan's repository or stop with the
no-repo error.

Drop "from this skill's directory" and say to run executing-plans'
two cross-skill scripts by absolute path from the working tree being
executed in.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
SDD's DONE step said to run review-package "from this skill's directory",
and executing-plans named the scripts by ../subagent-driven-development
paths relative to its own skill directory. The scripts act on the git
repository of the current directory, like git, so an agent that cd's
into the skill directory moves them off the working tree it is
executing in: in 6.3 that silently wrote SDD state into the plugin
cache; now they fall back to the plan's repository or stop with the
no-repo error.

Drop "from this skill's directory" and say to run executing-plans'
two cross-skill scripts by absolute path from the working tree being
executed in.

Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
</feed>
