<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/skills, branch claude-code-platform-reference</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>Add Claude Code platform reference: a nested orchestrator for cheaper subagent-driven development</title>
<updated>2026-09-18T00:03:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-09-18T00:03:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=5b56e6f7ebe5012dd03bed2b9ebb9aa5ab8444af'/>
<id>5b56e6f7ebe5012dd03bed2b9ebb9aa5ab8444af</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2110 from obra/feat/verification-floor-tdd</title>
<updated>2026-09-17T22:50:19+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-09-17T22:50:19+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=dcc1b26bc513bd0d0c0781fce0383ef0ae4ac1e4'/>
<id>dcc1b26bc513bd0d0c0781fce0383ef0ae4ac1e4</id>
<content type='text'>
feat(tdd): the project's suite defines green, not just your test file</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
feat(tdd): the project's suite defines green, not just your test file</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2133 from obra/fix/review-base-sha-merge-base</title>
<updated>2026-09-17T22:49:04+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-09-17T22:49:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=8acf6d5acde7ed25fb360c9fc9b126b5e2c7b15a'/>
<id>8acf6d5acde7ed25fb360c9fc9b126b5e2c7b15a</id>
<content type='text'>
fix(requesting-code-review): anchor the multi-commit BASE_SHA alternative to the merge base</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(requesting-code-review): anchor the multi-commit BASE_SHA alternative to the merge base</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2134 from obra/fix/sdd-helpers-no-exec-bit</title>
<updated>2026-09-17T22:48:31+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-09-17T22:48:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=a2b2d1d5efdc9c24c2faf5577077be152be67cdd'/>
<id>a2b2d1d5efdc9c24c2faf5577077be152be67cdd</id>
<content type='text'>
fix(sdd): invoke sdd-workspace via bash so helpers survive stripped exec bits</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(sdd): invoke sdd-workspace via bash so helpers survive stripped exec bits</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2136 from obra/fix/review-package-range-guards</title>
<updated>2026-09-17T22:47:55+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-09-17T22:47:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b61242d8d030b9f7ac267e8d00d2955663b1b2fb'/>
<id>b61242d8d030b9f7ac267e8d00d2955663b1b2fb</id>
<content type='text'>
fix(sdd): reject empty or non-descendant BASE..HEAD ranges in review-package</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(sdd): reject empty or non-descendant BASE..HEAD ranges in review-package</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2301 from obra/fix/invoke-scripts-via-interpreter</title>
<updated>2026-09-17T22:31:09+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-09-17T22:31:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6f315218a74dcf3f1fed67554acd4d31f02247c3'/>
<id>6f315218a74dcf3f1fed67554acd4d31f02247c3</id>
<content type='text'>
Invoke bundled scripts through their interpreter in skill prose</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Invoke bundled scripts through their interpreter in skill prose</pre>
</div>
</content>
</entry>
<entry>
<title>Merge origin/dev into import/proving-it-works-skill</title>
<updated>2026-09-16T05:17:24+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-09-16T05:17:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b6bc1917464dffa26934398214924ddb257faf6c'/>
<id>b6bc1917464dffa26934398214924ddb257faf6c</id>
<content type='text'>
Co-Authored-By: Claude Fable 5.1 &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Co-Authored-By: Claude Fable 5.1 &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Invoke bundled scripts through their interpreter in skill prose</title>
<updated>2026-09-14T18:41:53+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-09-14T18:39:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=d3431eb5e3152cf1eb6077e0837f2fa2f9796e32'/>
<id>d3431eb5e3152cf1eb6077e0837f2fa2f9796e32</id>
<content type='text'>
Plugin packagers for other harnesses can strip executable bits from the
files they ship. The Codex marketplace cache delivered the SDD helpers as
0644 (#2040), and the MiniMax Code marketplace ships its repackaged copy
of our skills tree with every file at mode 600. On those installs every
bare invocation in our skill prose -- `scripts/start-server.sh ...`,
`scripts/review-package ...`, `./find-polluter.sh ...`,
`./render-graphs.js ...` -- fails with "Permission denied", so the
brainstorming visual companion, subagent-driven development, the
polluter bisection helper, and render-graphs are all broken there even
though the repo records the files as 100755.

Spell every script invocation in skills/**/*.md through its interpreter
instead: `bash` for the shell scripts (start-server.sh, stop-server.sh,
sdd-workspace, task-brief, review-package, find-polluter.sh) and `node`
for render-graphs.js, per each script's shebang. That form works whether
or not the exec bit survived packaging. The MiniMax Code marketplace
package independently applied exactly this edit to its copy of v6.2.0;
this brings the same pattern upstream so every packager gets it.

Nothing else in the prose changes. #2134 covers the complementary case
of a script exec'ing a sibling script (task-brief and review-package
calling sdd-workspace) and is still needed alongside this.

Record the rationale in docs/porting-to-a-new-harness.md (Part 6
distribution notes plus an Appendix B gotcha) and add a one-line note to
writing-skills' File Organization section so future skill authors don't
strip the prefixes.

Refs #2040, #2134.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Plugin packagers for other harnesses can strip executable bits from the
files they ship. The Codex marketplace cache delivered the SDD helpers as
0644 (#2040), and the MiniMax Code marketplace ships its repackaged copy
of our skills tree with every file at mode 600. On those installs every
bare invocation in our skill prose -- `scripts/start-server.sh ...`,
`scripts/review-package ...`, `./find-polluter.sh ...`,
`./render-graphs.js ...` -- fails with "Permission denied", so the
brainstorming visual companion, subagent-driven development, the
polluter bisection helper, and render-graphs are all broken there even
though the repo records the files as 100755.

Spell every script invocation in skills/**/*.md through its interpreter
instead: `bash` for the shell scripts (start-server.sh, stop-server.sh,
sdd-workspace, task-brief, review-package, find-polluter.sh) and `node`
for render-graphs.js, per each script's shebang. That form works whether
or not the exec bit survived packaging. The MiniMax Code marketplace
package independently applied exactly this edit to its copy of v6.2.0;
this brings the same pattern upstream so every packager gets it.

Nothing else in the prose changes. #2134 covers the complementary case
of a script exec'ing a sibling script (task-brief and review-package
calling sdd-workspace) and is still needed alongside this.

Record the rationale in docs/porting-to-a-new-harness.md (Part 6
distribution notes plus an Appendix B gotcha) and add a one-line note to
writing-skills' File Organization section so future skill authors don't
strip the prefixes.

Refs #2040, #2134.
</pre>
</div>
</content>
</entry>
<entry>
<title>Reject invalid chat transcripts and propagate browser cleanup failures</title>
<updated>2026-09-12T03:38:31+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-09-12T03:38:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=2c3c59ce3f5edf2c37bf40d270e7cc76a8bddae6'/>
<id>2c3c59ce3f5edf2c37bf40d270e7cc76a8bddae6</id>
<content type='text'>
Address the two final whole-PR findings from the consolidated movie repair
brief. A fresh openai-chat response must provide a speech-bearing string
transcript even when local ASR is off; null must not reuse the no-transcript
sentinel belonging to deterministic engines or cached accepted audio.
Preserve the bounded candidate loop and rejected-byte evidence.

Report failed Windows tree termination as OSError so the recorder owner's
existing per-child handler continues all cleanup and retains failure metadata.
Card rendering checks its acquired browser handle before acting on the PID,
propagates wait failure, and reports locked-profile removal instead of
allowing a pending successful return to hide incomplete cleanup.

Add fake HTTP/process/filesystem boundary regressions for both findings,
including real adapter invocation, accepted chat cache reuse, ASR modes,
normal completed cards, and serve cleanup after a failed leader later exits.
Correct the rejected-chat fixture to use the chat engine. No media or native
browser execution was performed; Drew retains personal video acceptance.

Validation: expected RED failures retained; 40 focused tests and the single
75-test contracts entrypoint pass. Full evidence and self-review are in
.superpowers/sdd/2026-09-11-movie-committee-repairs/final-fix-report.md.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Address the two final whole-PR findings from the consolidated movie repair
brief. A fresh openai-chat response must provide a speech-bearing string
transcript even when local ASR is off; null must not reuse the no-transcript
sentinel belonging to deterministic engines or cached accepted audio.
Preserve the bounded candidate loop and rejected-byte evidence.

Report failed Windows tree termination as OSError so the recorder owner's
existing per-child handler continues all cleanup and retains failure metadata.
Card rendering checks its acquired browser handle before acting on the PID,
propagates wait failure, and reports locked-profile removal instead of
allowing a pending successful return to hide incomplete cleanup.

Add fake HTTP/process/filesystem boundary regressions for both findings,
including real adapter invocation, accepted chat cache reuse, ASR modes,
normal completed cards, and serve cleanup after a failed leader later exits.
Correct the rejected-chat fixture to use the chat engine. No media or native
browser execution was performed; Drew retains personal video acceptance.

Validation: expected RED failures retained; 40 focused tests and the single
75-test contracts entrypoint pass. Full evidence and self-review are in
.superpowers/sdd/2026-09-11-movie-committee-repairs/final-fix-report.md.
</pre>
</div>
</content>
</entry>
<entry>
<title>docs: make proof-movie recipes preserve failures</title>
<updated>2026-09-12T03:16:33+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-09-12T03:16:33+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b206e0cbe1aaf4b37b6c34e44ecf00cb23466840'/>
<id>b206e0cbe1aaf4b37b6c34e44ecf00cb23466840</id>
<content type='text'>
Repair the shipped Unix, logging, subtitle, cursor, narration, and recorder guidance against the literal fake-boundary failures recorded for Task 4. The primary pipeline and subtitle recipe now fail fast, measured offsets reach subtitle generation, producer logging preserves the real status under the pipefail owner, and cursor mouseup restores the released state.

Document the accepted narration/cache contract, cooperative recorder cleanup limits, and the safe contracts-suite entrypoint without changing Windows recipes or the existing evidence and human-viewing gates. Include the controller-owned plan bookkeeping and record the executable RED/GREEN results while leaving independent fresh-reader trials pending.

Prompt: implement Task 4 focused executable movie-guide corrections after Tasks 1-3, using writing-skills and only fake producers, text fixtures, and fake DOM execution.

Verification: python3 .superpowers/review/pr2214/committee/recipe-probes.py; uv run --script tests/proving-it-works-with-a-movie/run-tests.py --suite contracts; git diff --check.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Repair the shipped Unix, logging, subtitle, cursor, narration, and recorder guidance against the literal fake-boundary failures recorded for Task 4. The primary pipeline and subtitle recipe now fail fast, measured offsets reach subtitle generation, producer logging preserves the real status under the pipefail owner, and cursor mouseup restores the released state.

Document the accepted narration/cache contract, cooperative recorder cleanup limits, and the safe contracts-suite entrypoint without changing Windows recipes or the existing evidence and human-viewing gates. Include the controller-owned plan bookkeeping and record the executable RED/GREEN results while leaving independent fresh-reader trials pending.

Prompt: implement Task 4 focused executable movie-guide corrections after Tasks 1-3, using writing-skills and only fake producers, text fixtures, and fake DOM execution.

Verification: python3 .superpowers/review/pr2214/committee/recipe-probes.py; uv run --script tests/proving-it-works-with-a-movie/run-tests.py --suite contracts; git diff --check.
</pre>
</div>
</content>
</entry>
</feed>
