<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git, branch codex/explore-interactive-prototypes</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>feat: add Alpine visual companion mockups</title>
<updated>2026-05-27T23:22:48+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-05-08T22:52:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=63101959b52594edb2eabedddbf75b6e23c45152'/>
<id>63101959b52594edb2eabedddbf75b6e23c45152</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Revert "Make visual-companion.md script paths skill-rooted, not plugin-rooted"</title>
<updated>2026-05-24T00:01:46+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-24T00:01:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=8811b0f2d77da52c4552f0fdf48c0af0dcec83f2'/>
<id>8811b0f2d77da52c4552f0fdf48c0af0dcec83f2</id>
<content type='text'>
This reverts commit e9f518828911f85dd313eb2ac4824075bbc70d7b.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This reverts commit e9f518828911f85dd313eb2ac4824075bbc70d7b.
</pre>
</div>
</content>
</entry>
<entry>
<title>Revert "Probe per-user Git Bash and Scoop before falling back to PATH on Windows"</title>
<updated>2026-05-24T00:00:15+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-24T00:00:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=d48bec6cc38daf4def0c816e49bfcb92f4605fb3'/>
<id>d48bec6cc38daf4def0c816e49bfcb92f4605fb3</id>
<content type='text'>
This reverts commit a8f0738e3a76f3ade5530af9bd0c37cedadd3c44.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This reverts commit a8f0738e3a76f3ade5530af9bd0c37cedadd3c44.
</pre>
</div>
</content>
</entry>
<entry>
<title>Probe per-user Git Bash and Scoop before falling back to PATH on Windows</title>
<updated>2026-05-23T23:58:56+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-23T23:58:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=a8f0738e3a76f3ade5530af9bd0c37cedadd3c44'/>
<id>a8f0738e3a76f3ade5530af9bd0c37cedadd3c44</id>
<content type='text'>
Stock Windows 10/11 ships C:\Windows\System32\bash.exe (the WSL
launcher) as the first match for `where bash`. WSL's bash cannot
execute Windows-style script paths, so when Git Bash is installed
outside the two standard system locations -- specifically the
per-user "Only for me" Git for Windows installer
(%LOCALAPPDATA%\Programs\Git) or a Scoop install
(%USERPROFILE%\scoop\apps\git\current\usr\bin) -- run-hook.cmd
silently fails: WSL prints "Windows Subsystem for Linux must be
updated", the script returns 0, and Superpowers' SessionStart
bootstrap is never injected. From the user's perspective skills
auto-trigger inconsistently or not at all, with no surfaced error.

Add explicit probes for both locations between the existing system-
wide Git for Windows checks and the `where bash` fallback. Also add
a comment to the fallback documenting the WSL-launcher trap so future
maintainers understand why the explicit probes must come first.

Verified on a Windows 11 VM (dockur/windows 11, Git Bash 2.x, Node
22):
- System Git present: existing probe still matches (no regression)
- System Git absent, per-user Git present via junction: new probe
  matches, hook produces valid 6422-byte JSON, exit 0
- All Git probes absent: confirmed WSL trap fires
  ("Windows Subsystem for Linux must be updated") and the hook exits 0
  silently, demonstrating the original bug

Existing tests/hooks/test-session-start.sh still passes on macOS (7/7).

Reported by @ytchenak in #1607.

Co-authored-by: ytchenak &lt;ytchenak@users.noreply.github.com&gt;
Closes #1607.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Stock Windows 10/11 ships C:\Windows\System32\bash.exe (the WSL
launcher) as the first match for `where bash`. WSL's bash cannot
execute Windows-style script paths, so when Git Bash is installed
outside the two standard system locations -- specifically the
per-user "Only for me" Git for Windows installer
(%LOCALAPPDATA%\Programs\Git) or a Scoop install
(%USERPROFILE%\scoop\apps\git\current\usr\bin) -- run-hook.cmd
silently fails: WSL prints "Windows Subsystem for Linux must be
updated", the script returns 0, and Superpowers' SessionStart
bootstrap is never injected. From the user's perspective skills
auto-trigger inconsistently or not at all, with no surfaced error.

Add explicit probes for both locations between the existing system-
wide Git for Windows checks and the `where bash` fallback. Also add
a comment to the fallback documenting the WSL-launcher trap so future
maintainers understand why the explicit probes must come first.

Verified on a Windows 11 VM (dockur/windows 11, Git Bash 2.x, Node
22):
- System Git present: existing probe still matches (no regression)
- System Git absent, per-user Git present via junction: new probe
  matches, hook produces valid 6422-byte JSON, exit 0
- All Git probes absent: confirmed WSL trap fires
  ("Windows Subsystem for Linux must be updated") and the hook exits 0
  silently, demonstrating the original bug

Existing tests/hooks/test-session-start.sh still passes on macOS (7/7).

Reported by @ytchenak in #1607.

Co-authored-by: ytchenak &lt;ytchenak@users.noreply.github.com&gt;
Closes #1607.
</pre>
</div>
</content>
</entry>
<entry>
<title>Pipe SessionStart hook printf through cat to absorb EPIPE on Windows</title>
<updated>2026-05-23T23:55:46+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-23T23:55:46+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=f36bad5b78d04c7aaef7f9f45df92d6734c02e73'/>
<id>f36bad5b78d04c7aaef7f9f45df92d6734c02e73</id>
<content type='text'>
On Windows + Git Bash, the SessionStart hook prints a confusing
diagnostic at every startup ("printf: write error: Permission denied")
when Claude Code closes the hook's stdout pipe before the printf has
finished writing. The hook still runs to completion and context still
gets injected, but the diagnostic surfaces every session because
Git Bash's printf reports EPIPE as "Permission denied" (not "Broken
pipe" like Linux) and our `set -euo pipefail` lets that error escape.

Piping each printf through `cat` makes the external cat process the
recipient of any SIGPIPE / EPIPE. cat's failure does not propagate to
the parent bash under pipefail because cat is the last command in the
pipeline and exits cleanly when the pipe stays open long enough to
hold the data. On macOS/Linux the cat passthrough is transparent (no
behavior change, no measurable cost).

Verified:
- Existing tests/hooks/test-session-start.sh: 7/7 pass on macOS
- Manual run on Windows 11 + Git Bash 5.2 + Node 22 produces valid JSON,
  clean stderr, and exit 0
- JSON output is byte-identical to the unpatched hook

Reported by @silvertakana in #1612, attribution preserved in the
Co-authored-by trailer below — this is the same fix shape the original
PR proposed.

Co-authored-by: silvertakana &lt;silvertakana@users.noreply.github.com&gt;
Closes #1612.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
On Windows + Git Bash, the SessionStart hook prints a confusing
diagnostic at every startup ("printf: write error: Permission denied")
when Claude Code closes the hook's stdout pipe before the printf has
finished writing. The hook still runs to completion and context still
gets injected, but the diagnostic surfaces every session because
Git Bash's printf reports EPIPE as "Permission denied" (not "Broken
pipe" like Linux) and our `set -euo pipefail` lets that error escape.

Piping each printf through `cat` makes the external cat process the
recipient of any SIGPIPE / EPIPE. cat's failure does not propagate to
the parent bash under pipefail because cat is the last command in the
pipeline and exits cleanly when the pipe stays open long enough to
hold the data. On macOS/Linux the cat passthrough is transparent (no
behavior change, no measurable cost).

Verified:
- Existing tests/hooks/test-session-start.sh: 7/7 pass on macOS
- Manual run on Windows 11 + Git Bash 5.2 + Node 22 produces valid JSON,
  clean stderr, and exit 0
- JSON output is byte-identical to the unpatched hook

Reported by @silvertakana in #1612, attribution preserved in the
Co-authored-by trailer below — this is the same fix shape the original
PR proposed.

Co-authored-by: silvertakana &lt;silvertakana@users.noreply.github.com&gt;
Closes #1612.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(systematic-debugging): defuse Claude Code ultrathink keyword scanner trigger (#1558)</title>
<updated>2026-05-23T23:51:00+00:00</updated>
<author>
<name>Nick Galatis</name>
<email>social@wefixit.gr</email>
</author>
<published>2026-05-23T23:51:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=21ad401e909d7b5e4b0f48f5111669ea87118d11'/>
<id>21ad401e909d7b5e4b0f48f5111669ea87118d11</id>
<content type='text'>
The "Signals You're Doing It Wrong" bullet in systematic-debugging/SKILL.md
contains the literal token Claude Code's runtime scans for in tool result
bodies. Every Skill-tool invocation of this skill caused the harness to
inject a spurious system-reminder claiming the user requested deeper
reasoning, silently bumping every session into extended thinking.

Replace the bullet's spelling so the contiguous letter sequence the scanner
matches is broken with a hyphen. The signal text remains recognizable to
the agent and the documented action ("Question fundamentals, not just
symptoms") is unchanged.

Fixes obra/superpowers#1283</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The "Signals You're Doing It Wrong" bullet in systematic-debugging/SKILL.md
contains the literal token Claude Code's runtime scans for in tool result
bodies. Every Skill-tool invocation of this skill caused the harness to
inject a spurious system-reminder claiming the user requested deeper
reasoning, silently bumping every session into extended thinking.

Replace the bullet's spelling so the contiguous letter sequence the scanner
matches is broken with a hyphen. The signal text remains recognizable to
the agent and the documented action ("Question fundamentals, not just
symptoms") is unchanged.

Fixes obra/superpowers#1283</pre>
</div>
</content>
</entry>
<entry>
<title>Make visual-companion.md script paths skill-rooted, not plugin-rooted</title>
<updated>2026-05-23T23:42:13+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-23T23:42:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=e9f518828911f85dd313eb2ac4824075bbc70d7b'/>
<id>e9f518828911f85dd313eb2ac4824075bbc70d7b</id>
<content type='text'>
Issue #1134: agents reading visual-companion.md see bare commands like
`scripts/start-server.sh`, correctly identify the plugin install
directory, then look for `&lt;plugin&gt;/scripts/start-server.sh` instead of
`&lt;plugin&gt;/skills/brainstorming/scripts/start-server.sh`. The file
doesn't exist at the plugin-rooted path, so the agent concludes the
visual companion isn't available and falls back to text-only
brainstorming.

Multiple independent reproductions in the issue thread, plus one user's
agent self-reported: "I assumed the scripts folder was in the root
directory of the plugin, it didn't realize it could have been talking
about the skill folder itself."

Change all `scripts/&lt;file&gt;` references in visual-companion.md to
`skills/brainstorming/scripts/&lt;file&gt;`. Agents that correctly identify
the plugin root will now join to the right path.

Closes #1134.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Issue #1134: agents reading visual-companion.md see bare commands like
`scripts/start-server.sh`, correctly identify the plugin install
directory, then look for `&lt;plugin&gt;/scripts/start-server.sh` instead of
`&lt;plugin&gt;/skills/brainstorming/scripts/start-server.sh`. The file
doesn't exist at the plugin-rooted path, so the agent concludes the
visual companion isn't available and falls back to text-only
brainstorming.

Multiple independent reproductions in the issue thread, plus one user's
agent self-reported: "I assumed the scripts folder was in the root
directory of the plugin, it didn't realize it could have been talking
about the skill folder itself."

Change all `scripts/&lt;file&gt;` references in visual-companion.md to
`skills/brainstorming/scripts/&lt;file&gt;`. Agents that correctly identify
the plugin root will now join to the right path.

Closes #1134.
</pre>
</div>
</content>
</entry>
<entry>
<title>Align windows-lifecycle test with current brainstorm server layout</title>
<updated>2026-05-23T23:36:45+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-23T23:36:45+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=eef50b96f0b4f4d449eb66850f68635c7ee0439f'/>
<id>eef50b96f0b4f4d449eb66850f68635c7ee0439f</id>
<content type='text'>
The test had drifted behind three server implementation changes and no
longer ran against the actual server:

- Server entrypoint renamed from server.js to server.cjs; the test still
  invoked node on server.js and failed with MODULE_NOT_FOUND.
- Server state moved to a state/ subdirectory (state/server-info,
  state/server.pid); the test still waited on .server-info and wrote
  .server.pid at the session root.
- Owner-PID startup validation now keeps the server running when the
  owner PID is dead at startup: it logs owner-pid-invalid, disables
  owner monitoring, and falls back to the idle timeout. The test still
  expected the server to self-terminate within 60s of a dead-at-startup
  owner.

Update file/path references to match the current server, and rewrite
the dead-at-startup test to assert the current behavior: server
survives, log contains owner-pid-invalid, log does not contain a
spurious "owner process exited" line.

Verified locally: 9 passed, 0 failed, 3 skipped (Windows-only).
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The test had drifted behind three server implementation changes and no
longer ran against the actual server:

- Server entrypoint renamed from server.js to server.cjs; the test still
  invoked node on server.js and failed with MODULE_NOT_FOUND.
- Server state moved to a state/ subdirectory (state/server-info,
  state/server.pid); the test still waited on .server-info and wrote
  .server.pid at the session root.
- Owner-PID startup validation now keeps the server running when the
  owner PID is dead at startup: it logs owner-pid-invalid, disables
  owner monitoring, and falls back to the idle timeout. The test still
  expected the server to self-terminate within 60s of a dead-at-startup
  owner.

Update file/path references to match the current server, and rewrite
the dead-at-startup test to assert the current behavior: server
survives, log contains owner-pid-invalid, log does not contain a
spurious "owner process exited" line.

Verified locally: 9 passed, 0 failed, 3 skipped (Windows-only).
</pre>
</div>
</content>
</entry>
<entry>
<title>Convert curly to square brackets in code-reviewer.md placeholders</title>
<updated>2026-05-23T23:14:24+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-23T23:14:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=e1d3f71e0d8123c42938e52e052cce2227dd0e48'/>
<id>e1d3f71e0d8123c42938e52e052cce2227dd0e48</id>
<content type='text'>
Matches the style used by the spec-reviewer-prompt.md and
code-quality-reviewer-prompt.md call sites, which already use square
brackets ([VAR] or [VAR — description]). No semantic change — these
placeholders are filled in by the controller; nothing programmatic
substitutes them.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Matches the style used by the spec-reviewer-prompt.md and
code-quality-reviewer-prompt.md call sites, which already use square
brackets ([VAR] or [VAR — description]). No semantic change — these
placeholders are filled in by the controller; nothing programmatic
substitutes them.
</pre>
</div>
</content>
</entry>
<entry>
<title>Scope spec reviewer to task diff and make reviewers read-only</title>
<updated>2026-05-23T23:14:05+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-05-23T23:14:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b2212dc9135efff326167bdff0323ee4a3dcb5a5'/>
<id>b2212dc9135efff326167bdff0323ee4a3dcb5a5</id>
<content type='text'>
Two problems with the SDD reviewer prompts on dev:

- spec-reviewer-prompt.md never received a git range, so the
  general-purpose subagent had to crawl the entire codebase to find what
  changed. Reporter measured 20-33 minute spec reviews on simple tasks
  (#1538).
- Neither reviewer prompt told the subagent that review is read-only.
  A spec reviewer running `git checkout &lt;parent-sha&gt;` for historical
  comparison silently detached HEAD on the controller's branch, then
  subsequent task commits accumulated on the detached HEAD and were
  effectively orphaned (#1543, reproduced independently in #1543's
  thread).

Add a Git Range to Review section to spec-reviewer-prompt.md that
mirrors the one code-reviewer.md already has, plus a Read-Only Review
section in both reviewer prompt templates stating the principle: do
not mutate the working tree, the index, HEAD, or branch state. Allow
inspecting other revisions via a separate temporary worktree, so the
read-only rule does not block legitimate historical comparison.

Closes #1538.
Closes #1543.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Two problems with the SDD reviewer prompts on dev:

- spec-reviewer-prompt.md never received a git range, so the
  general-purpose subagent had to crawl the entire codebase to find what
  changed. Reporter measured 20-33 minute spec reviews on simple tasks
  (#1538).
- Neither reviewer prompt told the subagent that review is read-only.
  A spec reviewer running `git checkout &lt;parent-sha&gt;` for historical
  comparison silently detached HEAD on the controller's branch, then
  subsequent task commits accumulated on the detached HEAD and were
  effectively orphaned (#1543, reproduced independently in #1543's
  thread).

Add a Git Range to Review section to spec-reviewer-prompt.md that
mirrors the one code-reviewer.md already has, plus a Read-Only Review
section in both reviewer prompt templates stating the principle: do
not mutate the working tree, the index, HEAD, or branch state. Allow
inspecting other revisions via a separate temporary worktree, so the
read-only rule does not block legitimate historical comparison.

Closes #1538.
Closes #1543.
</pre>
</div>
</content>
</entry>
</feed>
