<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/docs, branch fix/render-graphs-no-shell</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>docs(plans): SDD fix-loop redesign implementation plan</title>
<updated>2026-07-19T19:36:33+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-15T18:28:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=eb1ff1f11f083ddd1a03e34d7e8f2d60f9d07f3c'/>
<id>eb1ff1f11f083ddd1a03e34d7e8f2d60f9d07f3c</id>
<content type='text'>
Eight tasks across two repos: new re-review template, template/reference
alignment, full SKILL.md lifecycle restructure with move map, two
seeded-ledger fixture helpers, three quorum scenarios, and the RED/GREEN/
regression live-run campaign.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Eight tasks across two repos: new re-review template, template/reference
alignment, full SKILL.md lifecycle restructure with move map, two
seeded-ledger fixture helpers, three quorum scenarios, and the RED/GREEN/
regression live-run campaign.
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(specs): SDD fix-loop redesign design spec</title>
<updated>2026-07-19T19:36:33+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-15T18:11:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=bea92dce1a6ccd2f3fc7470b4a2a28a93e461b32'/>
<id>bea92dce1a6ccd2f3fc7470b4a2a28a93e461b32</id>
<content type='text'>
Review-fix loop gets resume-the-implementer semantics, scoped
re-reviews, a five-round circuit breaker, and controller adjudication
at trip. SKILL.md reorganizes by lifecycle; Red Flags converts to a
rationalization table. Brainstormed with Jesse 2026-07-15.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Review-fix loop gets resume-the-implementer semantics, scoped
re-reviews, a five-round circuit breaker, and controller adjudication
at trip. SKILL.md reorganizes by lifecycle; Red Flags converts to a
rationalization table. Brainstormed with Jesse 2026-07-15.
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(windows): document shell:bash hook dispatch and the PowerShell/CMD fallback hazards</title>
<updated>2026-07-19T19:03:59+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-16T00:14:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=fe0b24390e80a9bbdf0298074fab4a8d79c2553a'/>
<id>fe0b24390e80a9bbdf0298074fab4a8d79c2553a</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>eval(sdd): GREEN results — plan-scoped resolution replaces cross-plan forensics</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T20:18:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=75f4e9414e447288f5136d49103849a79192ba57'/>
<id>75f4e9414e447288f5136d49103849a79192ba57</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>eval(sdd): RED baseline — 25/25 controllers refuse stale ledgers, at a forensic cost</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T19:22:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=9d9eae52f935c3110957786f502ebc49577d29ab'/>
<id>9d9eae52f935c3110957786f502ebc49577d29ab</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(specs): record eval re-scope — blind adoption did not reproduce, claims narrowed</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T19:08:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6ddb0bfcd95bc8230e3afd426ef01ec479f45c8e'/>
<id>6ddb0bfcd95bc8230e3afd426ef01ec479f45c8e</id>
<content type='text'>
25/25 baseline reps refused the stale foreign ledger via git forensics;
the spec's evaluation section now states the honest claims: structural
fix + measured disambiguation-cost delta + same-plan-resume regression
gate, shipping with explicit maintainer sign-off in place of a failing
S1 baseline.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
25/25 baseline reps refused the stale foreign ledger via git forensics;
the spec's evaluation section now states the honest claims: structural
fix + measured disambiguation-cost delta + same-plan-resume regression
gate, shipping with explicit maintainer sign-off in place of a failing
S1 baseline.
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(plans): re-scope eval per maintainer decision — RED compiled, GREEN measures cost</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T19:07:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=194907435d46fb876cfada6e1842e0df4873761c'/>
<id>194907435d46fb876cfada6e1842e0df4873761c</id>
<content type='text'>
Three RED rounds (25 reps, three framings incl. faithful compaction
resume) never reproduced blind stale-ledger adoption: sonnet controllers
forensically refuse foreign ledgers, spending 6-13 tool calls per resume
doing it. Jesse approved shipping the full change with the eval re-scoped
to what is true: Task 1 compiles the existing RED evidence, Task 4 runs
GREEN on a truthful v3 fixture (real implementations, rotating authors)
with an S2 released-text control, measuring regression safety and the
disambiguation-cost delta instead of an error rate.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Three RED rounds (25 reps, three framings incl. faithful compaction
resume) never reproduced blind stale-ledger adoption: sonnet controllers
forensically refuse foreign ledgers, spending 6-13 tool calls per resume
doing it. Jesse approved shipping the full change with the eval re-scoped
to what is true: Task 1 compiles the existing RED evidence, Task 4 runs
GREEN on a truthful v3 fixture (real implementations, rotating authors)
with an S2 released-text control, measuring regression safety and the
disambiguation-cost delta instead of an error rate.
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(plans): fixture v2 — real cited commits, matched task counts</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T18:36:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=c10431b14cae8afe343afe5017bd777a178be1bd'/>
<id>c10431b14cae8afe343afe5017bd777a178be1bd</id>
<content type='text'>
Fixture v1 tripped the Task 1 STOP gate for the right reason: its
ledgers cited fabricated hashes, so RED agents dismissed them via git
forensics (S1 passed for the wrong mechanism, the S2 resume control
failed 5/5). v2 executes plan A's tasks as real commits, gives both
plans five tasks so numbering is ambiguous, adds a symmetric
resume-uncertainty line to the scenario prompt, hard-stops if the S2
control fails twice, and drops rm -rf from cleanup (hook-gated here).
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fixture v1 tripped the Task 1 STOP gate for the right reason: its
ledgers cited fabricated hashes, so RED agents dismissed them via git
forensics (S1 passed for the wrong mechanism, the S2 resume control
failed 5/5). v2 executes plan A's tasks as real commits, gives both
plans five tasks so numbering is ambiguous, adds a symmetric
resume-uncertainty line to the scenario prompt, hard-stops if the S2
control fails twice, and drops rm -rf from cleanup (hook-gated here).
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(plans): SDD plan-scoped workspace implementation plan</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T18:14:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=0da87665c8423bd5100991ecee0e738bbfa3433f'/>
<id>0da87665c8423bd5100991ecee0e738bbfa3433f</id>
<content type='text'>
Five tasks: RED baseline eval (writing-skills Iron Law — before any
skill edit), plan-scoped scripts via TDD, SKILL.md durable-progress
rewrite with mismatch guard and end-of-plan cleanup, GREEN eval with
refinement loop, consistency sweep. Eval = 5 fresh sonnet subagents per
scenario per arm, hand-scored.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Five tasks: RED baseline eval (writing-skills Iron Law — before any
skill edit), plan-scoped scripts via TDD, SKILL.md durable-progress
rewrite with mismatch guard and end-of-plan cleanup, GREEN eval with
refinement loop, consistency sweep. Eval = 5 fresh sonnet subagents per
scenario per arm, hand-scored.
</pre>
</div>
</content>
</entry>
<entry>
<title>docs(specs): SDD plan-scoped workspace design</title>
<updated>2026-07-19T19:03:18+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-06T18:06:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=20940deae86d367acedac0ac2554f77dbf86f139'/>
<id>20940deae86d367acedac0ac2554f77dbf86f139</id>
<content type='text'>
The .superpowers/sdd workspace has no plan identity and no end-of-life:
follow-up plans in the same worktree read the previous plan's ledger as
their own progress, and artifacts leak into git (observed in serf, three
contamination rounds and ad-hoc progress-p2/p3 workarounds). Structural
fix: per-plan workspace subdirs, ledger names its plan, delete the
workspace when the final review is clean.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The .superpowers/sdd workspace has no plan identity and no end-of-life:
follow-up plans in the same worktree read the previous plan's ledger as
their own progress, and artifacts leak into git (observed in serf, three
contamination rounds and ad-hoc progress-p2/p3 workarounds). Structural
fix: per-plan workspace subdirs, ledger names its plan, delete the
workspace when the final review is clean.
</pre>
</div>
</content>
</entry>
</feed>
