<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/skills/subagent-driven-development, branch inline-execution</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>Rebuild executing-plans as a first-class inline execution mode</title>
<updated>2026-09-18T00:14:38+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-09-17T22:51:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=2b89c4c3f375ab479c3bc0644a76fea78a0f44bb'/>
<id>2b89c4c3f375ab479c3bc0644a76fea78a0f44bb</id>
<content type='text'>
A cheaper execution mode alongside subagent-driven development: the
session implements every task itself under the same workspace, ledger
and stopping rules, with one fresh whole-branch review on the most
capable model at the end. Helper scripts task-start/task-done keep the
ledger and test log honest; the final fix pass re-grades findings and
fixes Critical/Important under TDD. writing-plans' handoff, SDD's
when-to-use text and two README lines change to match.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
A cheaper execution mode alongside subagent-driven development: the
session implements every task itself under the same workspace, ledger
and stopping rules, with one fresh whole-branch review on the most
capable model at the end. Helper scripts task-start/task-done keep the
ledger and test log honest; the final fix pass re-grades findings and
fixes Critical/Important under TDD. writing-plans' handoff, SDD's
when-to-use text and two README lines change to match.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(sdd): ownership markers stop same-basename plans sharing a workspace</title>
<updated>2026-09-17T22:51:11+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-08-13T00:35:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6692bd289f39931f37117af59ea32026fcebf94a'/>
<id>6692bd289f39931f37117af59ea32026fcebf94a</id>
<content type='text'>
sdd-workspace slugged workspaces by basename alone, so docs/alpha/plan.md
and docs/beta/plan.md resolved to one directory and task-brief silently
overwrote the other plan's brief — the single gitignored source of task
requirements, unrecoverable once clobbered.

Each workspace now records its owning plan in a plan-path marker
(repo-relative in-repo, absolute outside). Lookup keeps basename slugs
and existing behavior for the common case: a markerless workspace is
adopted in place (no migration break for in-flight plans), a marker
naming this plan is a match, and a marker naming a different plan
disambiguates with the plan's parent-directory name, then a counter.
Plan paths are normalized (CDPATH-guarded physical cd) so relative,
absolute, and ../ spellings of one plan share one workspace.

task-brief and review-package delegate to sdd-workspace and need no
changes. SKILL.md's workspace bullet no longer promises the exact
&lt;plan-basename&gt; path, since disambiguated workspaces differ.

Reported by @CRGDan; reproduction and test groundwork by @crisnahine
in PR #2120.

Fixes #2045
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
sdd-workspace slugged workspaces by basename alone, so docs/alpha/plan.md
and docs/beta/plan.md resolved to one directory and task-brief silently
overwrote the other plan's brief — the single gitignored source of task
requirements, unrecoverable once clobbered.

Each workspace now records its owning plan in a plan-path marker
(repo-relative in-repo, absolute outside). Lookup keeps basename slugs
and existing behavior for the common case: a markerless workspace is
adopted in place (no migration break for in-flight plans), a marker
naming this plan is a match, and a marker naming a different plan
disambiguates with the plan's parent-directory name, then a counter.
Plan paths are normalized (CDPATH-guarded physical cd) so relative,
absolute, and ../ spellings of one plan share one workspace.

task-brief and review-package delegate to sdd-workspace and need no
changes. SKILL.md's workspace bullet no longer promises the exact
&lt;plan-basename&gt; path, since disambiguated workspaces differ.

Reported by @CRGDan; reproduction and test groundwork by @crisnahine
in PR #2120.

Fixes #2045
</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>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>fix(sdd): reject empty or non-descendant BASE..HEAD ranges in review-package</title>
<updated>2026-08-13T00:29:29+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-08-13T00:29:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=99f9f00869e3e774e9abe9a29ccfccb8957ec5da'/>
<id>99f9f00869e3e774e9abe9a29ccfccb8957ec5da</id>
<content type='text'>
When an SDD implementer commits to the wrong branch (#2050), the
BASE..HEAD range handed to review-package is either empty or not rooted
at BASE. Both cases previously produced a review package silently —
an empty one lets the reviewer approve "clean" work that isn't there.

Add two mechanical guards after BASE/HEAD validation, exiting 3 (vs 2
for usage errors) so callers can distinguish range problems:

- git merge-base --is-ancestor BASE HEAD, else "HEAD is not a
  descendant of BASE"
- git rev-list --count BASE..HEAD &gt; 0, else "empty commit range"

Guard shape credits the analysis in closed PR #2082 by @stantheman0128.

Fixes #2050
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
When an SDD implementer commits to the wrong branch (#2050), the
BASE..HEAD range handed to review-package is either empty or not rooted
at BASE. Both cases previously produced a review package silently —
an empty one lets the reviewer approve "clean" work that isn't there.

Add two mechanical guards after BASE/HEAD validation, exiting 3 (vs 2
for usage errors) so callers can distinguish range problems:

- git merge-base --is-ancestor BASE HEAD, else "HEAD is not a
  descendant of BASE"
- git rev-list --count BASE..HEAD &gt; 0, else "empty commit range"

Guard shape credits the analysis in closed PR #2082 by @stantheman0128.

Fixes #2050
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(sdd): invoke sdd-workspace via bash so helpers survive stripped exec bits</title>
<updated>2026-08-13T00:27:52+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-08-13T00:27:52+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=0be49879b1c51a479d2013a14fe42ed9bd10ce32'/>
<id>0be49879b1c51a479d2013a14fe42ed9bd10ce32</id>
<content type='text'>
Codex marketplace users hit 'Permission denied' running SDD helpers:
some extractors (Python zipfile) discard Unix mode attributes when
unpacking the package, so task-brief's and review-package's direct exec
of their sibling sdd-workspace fails. Our packaging preserves 0755
(git archive | tar -xpf, asserted by the existing packaging test) — the
bits are lost on the consumer side, which no packaging change can reach.
Invoking the sibling via "${BASH:-bash}" makes the exec bit irrelevant.

TDD: new regression case copies the helpers, chmod -x, runs task-brief
via bash — RED with the reported rc=126 Permission denied, GREEN after.

Reported in #2040 (michaelholcomb-creator). Fixes #2040.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Codex marketplace users hit 'Permission denied' running SDD helpers:
some extractors (Python zipfile) discard Unix mode attributes when
unpacking the package, so task-brief's and review-package's direct exec
of their sibling sdd-workspace fails. Our packaging preserves 0755
(git archive | tar -xpf, asserted by the existing packaging test) — the
bits are lost on the consumer side, which no packaging change can reach.
Invoking the sibling via "${BASH:-bash}" makes the exec bit irrelevant.

TDD: new regression case copies the helpers, chmod -x, runs task-brief
via bash — RED with the reported rc=126 Permission denied, GREEN after.

Reported in #2040 (michaelholcomb-creator). Fixes #2040.
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2089 from obra/fix/x13-illegibility</title>
<updated>2026-08-06T23:10:58+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-08-06T23:10:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=cfb310c69ab6d1c332828de8fc580056006860fb'/>
<id>cfb310c69ab6d1c332828de8fc580056006860fb</id>
<content type='text'>
fix(sdd): reviewers re-read illegible evidence instead of re-running to regenerate it</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(sdd): reviewers re-read illegible evidence instead of re-running to regenerate it</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #2086 from obra/fix/spec-travels-with-plan</title>
<updated>2026-08-06T22:13:54+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@ritter.dev</email>
</author>
<published>2026-08-06T22:13:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=fdd1763d7738eee75592aa0f4a6f365d36df0f47'/>
<id>fdd1763d7738eee75592aa0f4a6f365d36df0f47</id>
<content type='text'>
fix(planning): the spec travels with the plan</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
fix(planning): the spec travels with the plan</pre>
</div>
</content>
</entry>
<entry>
<title>fix(sdd): task reviewers re-read illegible evidence instead of re-running to regenerate it</title>
<updated>2026-08-05T01:24:10+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-08-05T01:24:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=80b82abd8d5a43f629b9b0ca55336d63f3da5680'/>
<id>80b82abd8d5a43f629b9b0ca55336d63f3da5680</id>
<content type='text'>
Interrogation of reviewers who bypassed test-evidence leases showed a
convergent driver: when the report or receipt looked truncated or
couldn't be located, re-running the suite felt cheaper than re-reading —
evidence got regenerated instead of read. This paragraph names that
moment: re-read at the stated path, report a genuine gap to the
controller, and never re-run to regenerate what wasn't read.

Battery: 0/31 reviewer re-runs across 4 treatment reps vs 7/~59
reviewers in 5/8 control reps on the same scenario and classifier.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Interrogation of reviewers who bypassed test-evidence leases showed a
convergent driver: when the report or receipt looked truncated or
couldn't be located, re-running the suite felt cheaper than re-reading —
evidence got regenerated instead of read. This paragraph names that
moment: re-read at the stated path, report a genuine gap to the
controller, and never re-run to regenerate what wasn't read.

Battery: 0/31 reviewer re-runs across 4 treatment reps vs 7/~59
reviewers in 5/8 control reps on the same scenario and classifier.

Claude-Session: https://claude.ai/code/session_0185AJr98gHx5EmwqNeft4Sy
</pre>
</div>
</content>
</entry>
</feed>
