<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/tests, branch fix/codex-scripts-in-worktrees</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>fix(codex): accept linked git worktrees as checkouts</title>
<updated>2026-10-23T03:48:33+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-23T03:47:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=f713233eee9143d0a798976fd0d11609f91c0b5c'/>
<id>f713233eee9143d0a798976fd0d11609f91c0b5c</id>
<content type='text'>
package-codex-plugin.sh and sync-to-codex-plugin.sh checked for a
checkout with [[ -d .git ]]. In a linked worktree .git is a file, so
both scripts died with "not a git checkout" there, and
tests/codex/test-package-codex-plugin.sh failed 9 checks when run from
any worktree. Test that .git exists instead: it covers both layouts
and still requires the path to be the root of a checkout, which
matters for sync's user-supplied --local path. The scripts' later git
commands already work in worktrees.

Regression tests run the package script from a linked worktree of the
repo, and a sync preview from a linked upstream worktree into a linked
destination worktree. The package test is adapted from #1910.

Co-authored-by: tianma-if &lt;tianma-if@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
package-codex-plugin.sh and sync-to-codex-plugin.sh checked for a
checkout with [[ -d .git ]]. In a linked worktree .git is a file, so
both scripts died with "not a git checkout" there, and
tests/codex/test-package-codex-plugin.sh failed 9 checks when run from
any worktree. Test that .git exists instead: it covers both layouts
and still requires the path to be the root of a checkout, which
matters for sync's user-supplied --local path. The scripts' later git
commands already work in worktrees.

Regression tests run the package script from a linked worktree of the
repo, and a sync preview from a linked upstream worktree into a linked
destination worktree. The package test is adapted from #1910.

Co-authored-by: tianma-if &lt;tianma-if@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2598 from obra/fix/2394-pi-skill-filters</title>
<updated>2026-10-22T22:13:52+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-10-22T22:13:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b58deb3b948d4c305feeac122700100419ee2777'/>
<id>b58deb3b948d4c305feeac122700100419ee2777</id>
<content type='text'>
fix(pi): stop resources_discover from bypassing package skill filters</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(pi): stop resources_discover from bypassing package skill filters</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2594 from obra/fix/2503-run-hook-no-bash</title>
<updated>2026-10-22T22:05:26+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-10-22T22:05:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=7e2e91942b26418f0e1bb506f952288f4187c70b'/>
<id>7e2e91942b26418f0e1bb506f952288f4187c70b</id>
<content type='text'>
fix(hooks): fall back to zsh, or exit quietly, when bash is missing on Unix (#2503)</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(hooks): fall back to zsh, or exit quietly, when bash is missing on Unix (#2503)</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2593 from obra/fix/2081-session-start-forks</title>
<updated>2026-10-22T22:04:15+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-10-22T22:04:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=4a2a185a37ddf186e79749b4a95b4f11242be882'/>
<id>4a2a185a37ddf186e79749b4a95b4f11242be882</id>
<content type='text'>
fix(hooks): start no child processes in the SessionStart hook (#2081)</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(hooks): start no child processes in the SessionStart hook (#2081)</pre>
</div>
</content>
</entry>
<entry>
<title>fix(hooks): fall back to zsh, or exit quietly, when bash is missing on Unix (#2503)</title>
<updated>2026-10-22T21:19:08+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T21:19:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=3cbe5575758e409ac083c694cfc45ccfde50c0cd'/>
<id>3cbe5575758e409ac083c694cfc45ccfde50c0cd</id>
<content type='text'>
On a Unix system without bash, the harness can't honour shell:"bash" and
runs run-hook.cmd with zsh or sh. $BASH is unset there, so the wrapper's
exec "${BASH:-bash}" fails with "command not found: bash" (zsh) or
"exec: bash: not found" (sh), the hook exits 127, and the bootstrap is
lost on every session start.

Keep $BASH first, so the empty-PATH case from #2310 still works, then look
for bash on PATH, then zsh, which runs session-start unchanged (its output
is byte-identical to bash's, including for a SKILL.md full of backslashes,
quotes, tabs and CRs). With neither shell, exit 0 quietly, as the Windows
half already does.

Reproduced with Claude Code 2.1.308 in an alpine container with zsh and no
bash: the hook exited 127 and no bootstrap reached the model before the
change; after it the hook exits 0 and the bootstrap arrives.

Tests run the wrapper under real zsh and under a non-bash sh with a PATH
that holds only zsh, and under that sh with neither shell. They skip where
zsh is absent or sh is bash (Git Bash, macOS).

Co-authored-by: Twot &lt;twotnguyen@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
On a Unix system without bash, the harness can't honour shell:"bash" and
runs run-hook.cmd with zsh or sh. $BASH is unset there, so the wrapper's
exec "${BASH:-bash}" fails with "command not found: bash" (zsh) or
"exec: bash: not found" (sh), the hook exits 127, and the bootstrap is
lost on every session start.

Keep $BASH first, so the empty-PATH case from #2310 still works, then look
for bash on PATH, then zsh, which runs session-start unchanged (its output
is byte-identical to bash's, including for a SKILL.md full of backslashes,
quotes, tabs and CRs). With neither shell, exit 0 quietly, as the Windows
half already does.

Reproduced with Claude Code 2.1.308 in an alpine container with zsh and no
bash: the hook exited 127 and no bootstrap reached the model before the
change; after it the hook exits 0 and the bootstrap arrives.

Tests run the wrapper under real zsh and under a non-bash sh with a PATH
that holds only zsh, and under that sh with neither shell. They skip where
zsh is absent or sh is bash (Git Bash, macOS).

Co-authored-by: Twot &lt;twotnguyen@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(hooks): start no child processes in the SessionStart hook (#2081)</title>
<updated>2026-10-22T21:16:09+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T21:16:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=328685babd94e11910516025dee12e32a6d49de1'/>
<id>328685babd94e11910516025dee12e32a6d49de1</id>
<content type='text'>
On Windows, Git Bash emulates fork(), so every command substitution and
pipe costs tens of milliseconds. The SessionStart hook runs on every
startup, /clear and compaction, and on dev it forked six times: the
$(cd ... &amp;&amp; pwd) in run-hook.cmd and twice in session-start,
$(escape_for_json ...), and printf | cat.

Resolve paths with parameter expansion, read the skill with the read
builtin, have escape_for_json assign a variable, and absorb EPIPE with
trap '' PIPE plus printf 2&gt;/dev/null || true instead of piping through
cat. The cat pipe also turned an early-closed stdout into exit 141 under
pipefail; the new emit_json exits 0 there.

Measured on Windows 11 (VM, Git Bash 5.2), 21 interleaved runs of
run-hook.cmd session-start: median 116 ms before, 46 ms after, against a
25 ms floor for one bash start (the wrapper starts two). Claude Code
2.1.308 logged the hook at 181-421 ms before and 137-146 ms after. Output
is byte-identical to dev across all five output shapes, two working
directories, normal and empty PATH, direct and through the wrapper (40/40
on Linux), and its sha256 matches on Windows.

Tests: the cat-stub case, which asserted the pipe, is replaced by a
closed-stdout case, and a new case counts process creations with strace
on Linux (5 in session-start and 6 through the wrapper on dev, 0 after).

Co-authored-by: willow &lt;willowite@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
On Windows, Git Bash emulates fork(), so every command substitution and
pipe costs tens of milliseconds. The SessionStart hook runs on every
startup, /clear and compaction, and on dev it forked six times: the
$(cd ... &amp;&amp; pwd) in run-hook.cmd and twice in session-start,
$(escape_for_json ...), and printf | cat.

Resolve paths with parameter expansion, read the skill with the read
builtin, have escape_for_json assign a variable, and absorb EPIPE with
trap '' PIPE plus printf 2&gt;/dev/null || true instead of piping through
cat. The cat pipe also turned an early-closed stdout into exit 141 under
pipefail; the new emit_json exits 0 there.

Measured on Windows 11 (VM, Git Bash 5.2), 21 interleaved runs of
run-hook.cmd session-start: median 116 ms before, 46 ms after, against a
25 ms floor for one bash start (the wrapper starts two). Claude Code
2.1.308 logged the hook at 181-421 ms before and 137-146 ms after. Output
is byte-identical to dev across all five output shapes, two working
directories, normal and empty PATH, direct and through the wrapper (40/40
on Linux), and its sha256 matches on Windows.

Tests: the cat-stub case, which asserted the pipe, is replaced by a
closed-stdout case, and a new case counts process creations with strace
on Linux (5 in session-start and 6 through the wrapper on dev, 0 after).

Co-authored-by: willow &lt;willowite@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(hooks): add a powershell form of the SessionStart command for Copilot on Windows (#2189)</title>
<updated>2026-10-22T20:56:46+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T20:56:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=0a4d60db4faf3628abc3e6be4fc3e1a0697c69de'/>
<id>0a4d60db4faf3628abc3e6be4fc3e1a0697c69de</id>
<content type='text'>
GitHub Copilot on Windows (Copilot CLI and VS Code Copilot) runs a hook's
command through PowerShell and ignores shell:"bash". PowerShell parses
"&lt;root&gt;/hooks/run-hook.cmd" session-start as a string expression followed
by a bareword, fails with "Unexpected token 'session-start'", and the
using-superpowers bootstrap never reaches the session.

Copilot prefers a hook's powershell key over command when it is present, so
add one that runs the same wrapper with the &amp; call operator. Claude Code
ignores the key and keeps dispatching command through Git Bash.

Verified on Windows 11 in a VM: Copilot CLI 1.0.103 logged the ParserError
and sent no bootstrap before the change, and ran the hook and sent the
bootstrap after it. Claude Code 2.1.308 ran the hook and sent the bootstrap
both before and after.

The new test in test-run-hook-cmd-windows.sh runs the hooks.json powershell
value through powershell.exe against a plugin root with a space in its path.

Co-authored-by: Tugrul Guner &lt;tugrulguner@users.noreply.github.com&gt;
Co-authored-by: Serge ARADJ &lt;orty@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
GitHub Copilot on Windows (Copilot CLI and VS Code Copilot) runs a hook's
command through PowerShell and ignores shell:"bash". PowerShell parses
"&lt;root&gt;/hooks/run-hook.cmd" session-start as a string expression followed
by a bareword, fails with "Unexpected token 'session-start'", and the
using-superpowers bootstrap never reaches the session.

Copilot prefers a hook's powershell key over command when it is present, so
add one that runs the same wrapper with the &amp; call operator. Claude Code
ignores the key and keeps dispatching command through Git Bash.

Verified on Windows 11 in a VM: Copilot CLI 1.0.103 logged the ParserError
and sent no bootstrap before the change, and ran the hook and sent the
bootstrap after it. Claude Code 2.1.308 ran the hook and sent the bootstrap
both before and after.

The new test in test-run-hook-cmd-windows.sh runs the hooks.json powershell
value through powershell.exe against a plugin root with a space in its path.

Co-authored-by: Tugrul Guner &lt;tugrulguner@users.noreply.github.com&gt;
Co-authored-by: Serge ARADJ &lt;orty@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(pi): stop resources_discover from bypassing package skill filters</title>
<updated>2026-10-22T20:51:39+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-22T20:51:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=7455441f77de6c33b3f2f25159fa9dc6d2cc1305'/>
<id>7455441f77de6c33b3f2f25159fa9dc6d2cc1305</id>
<content type='text'>
The pi extension registered a resources_discover handler that returned
the whole skills/ directory. pi applies a package's `skills` filter
(the one `pi config` writes) only to manifest-declared resources;
paths an extension contributes are merged afterwards, unfiltered. So
with `"skills": []` or an allowlist on the superpowers package entry,
pi 0.85.1 still loaded all 15 skills, every one attributed to
extension:superpowers.

package.json already declares `pi.skills: ["./skills"]`, and pi loads
that with the user's filter applied, so the handler was redundant for
package installs, including the README's `pi -e /path/to/superpowers`.
Remove it. The bootstrap handlers are unchanged. The porting guide now
names the manifest as pi's discovery mechanism.

Verified against the real pi 0.85.1 CLI (RPC get_commands, no model
call): skills [] loads 0 (was 15), an allowlist of using-superpowers
loads 1 (was 15), no filter loads 15, `pi -e &lt;checkout&gt;` loads 15.

Fixes #2394

Co-authored-by: m2dumpling &lt;224757904+m2dumpling@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The pi extension registered a resources_discover handler that returned
the whole skills/ directory. pi applies a package's `skills` filter
(the one `pi config` writes) only to manifest-declared resources;
paths an extension contributes are merged afterwards, unfiltered. So
with `"skills": []` or an allowlist on the superpowers package entry,
pi 0.85.1 still loaded all 15 skills, every one attributed to
extension:superpowers.

package.json already declares `pi.skills: ["./skills"]`, and pi loads
that with the user's filter applied, so the handler was redundant for
package installs, including the README's `pi -e /path/to/superpowers`.
Remove it. The bootstrap handlers are unchanged. The porting guide now
names the manifest as pi's discovery mechanism.

Verified against the real pi 0.85.1 CLI (RPC get_commands, no model
call): skills [] loads 0 (was 15), an allowlist of using-superpowers
loads 1 (was 15), no filter loads 15, `pi -e &lt;checkout&gt;` loads 15.

Fixes #2394

Co-authored-by: m2dumpling &lt;224757904+m2dumpling@users.noreply.github.com&gt;
Claude-Session: https://claude.ai/code/session_01SHANcr4A71nzuU9et4Fnba
</pre>
</div>
</content>
</entry>
<entry>
<title>test(brainstorm-server): wait for file events instead of sleeping</title>
<updated>2026-10-21T20:12:44+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-10-21T20:12:44+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=e8d28a06aa8d1fe7d46057ee804b1e2385e836df'/>
<id>e8d28a06aa8d1fe7d46057ee804b1e2385e836df</id>
<content type='text'>
On macOS, fs.watch (FSEvents) delivered events anywhere from ~100ms to
2.4s after the write on Node 26.10 / Darwin 27, and sometimes held an
event back to deliver it in a batch with a later one. The file-watching
tests slept a fixed 500ms, so they failed when an event came late, and a
late event from one test could trigger a reload or clear state/events
during another. Six tests failed on v7.0.0 and on dev, a different six
each run.

The tests now poll for the outcome with a 5s timeout, wait until the
server logs the exact screen event they caused, and drain in-flight
events with a barrier file before asserting that nothing reloaded or
that state/events survived. 15 consecutive runs pass; dropping the
server's .html/dotfile filter still fails both negative tests.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
On macOS, fs.watch (FSEvents) delivered events anywhere from ~100ms to
2.4s after the write on Node 26.10 / Darwin 27, and sometimes held an
event back to deliver it in a batch with a later one. The file-watching
tests slept a fixed 500ms, so they failed when an event came late, and a
late event from one test could trigger a reload or clear state/events
during another. Six tests failed on v7.0.0 and on dev, a different six
each run.

The tests now poll for the outcome with a 5s timeout, wait until the
server logs the exact screen event they caused, and drain in-flight
events with a barrier file before asserting that nothing reloaded or
that state/events survived. 15 consecutive runs pass; dropping the
server's .html/dotfile filter still fails both negative tests.
</pre>
</div>
</content>
</entry>
<entry>
<title>subagent-driven-development: move situational content to references/ so SKILL.md survives compaction (#2565)</title>
<updated>2026-10-21T19:34:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-10-21T19:34:50+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=8a14cf8f9bbf099c59252030fa7e0dc934896aa4'/>
<id>8a14cf8f9bbf099c59252030fa7e0dc934896aa4</id>
<content type='text'>
After a compaction, Claude Code re-attaches each invoked skill truncated to
20,000 characters (#2481). SDD was 32,358, so everything from the fix loop
on (the five-round cap, the breaker, the ledger round line, the final
review's single fix wave, Finish) was gone for the rest of a long session.
One reported task ran 18 fix rounds after that.

Content SDD only needs at particular moments now lives in references/,
behind a pointer at the step that needs it: fix-loop.md (read before every
round), final-review.md (with Finish), handling-reports.md (non-DONE
statuses), resuming.md (an existing ledger), preflight.md (the conflict
scan before Task 1), batching.md, and cannot-verify.md. Those reads come
fresh from disk, so they don't depend on what survived compaction. The
Process graph shows the fix loop and final review as pointer nodes, and
the illustrative Example Workflow is gone. SKILL.md is 19,506 bytes.

tests/skill-size/test-skill-size.sh fails when any SKILL.md reaches 20,000
bytes. It still fails for writing-skills and executing-plans.

Claude-Session: https://claude.ai/code/session_01EgKgPPzKtNA2okiCmqb11F</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
After a compaction, Claude Code re-attaches each invoked skill truncated to
20,000 characters (#2481). SDD was 32,358, so everything from the fix loop
on (the five-round cap, the breaker, the ledger round line, the final
review's single fix wave, Finish) was gone for the rest of a long session.
One reported task ran 18 fix rounds after that.

Content SDD only needs at particular moments now lives in references/,
behind a pointer at the step that needs it: fix-loop.md (read before every
round), final-review.md (with Finish), handling-reports.md (non-DONE
statuses), resuming.md (an existing ledger), preflight.md (the conflict
scan before Task 1), batching.md, and cannot-verify.md. Those reads come
fresh from disk, so they don't depend on what survived compaction. The
Process graph shows the fix loop and final review as pointer nodes, and
the illustrative Example Workflow is gone. SKILL.md is 19,506 bytes.

tests/skill-size/test-skill-size.sh fails when any SKILL.md reaches 20,000
bytes. It still fails for writing-skills and executing-plans.

Claude-Session: https://claude.ai/code/session_01EgKgPPzKtNA2okiCmqb11F</pre>
</div>
</content>
</entry>
</feed>
