<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git, branch fix/windows-hook-shell-bash</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(windows): document shell:bash hook dispatch and the PowerShell/CMD fallback hazards</title>
<updated>2026-07-16T00:14:13+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=fd12428a5cd63a3a63f12eea6c4ffad780ecf36d'/>
<id>fd12428a5cd63a3a63f12eea6c4ffad780ecf36d</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(hooks): dispatch the SessionStart hook via Git Bash on Windows</title>
<updated>2026-07-16T00:13:35+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-16T00:13:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=390bc07abbae22f6bcbeaea98a0c7216dd9d5281'/>
<id>390bc07abbae22f6bcbeaea98a0c7216dd9d5281</id>
<content type='text'>
The SessionStart command string starts with a quoted path, which breaks
both Windows shells Claude Code may hand it to: PowerShell parses the
leading quoted string as an expression and dies on the next bareword
('Unexpected token session-start', #1751), and cmd.exe's /c quote rule
drops the outer quotes when the path contains a metacharacter, so a
profile dir like C:\Users\Name(External) truncates the command at the
'(' (#1918). Either way the bootstrap silently never loads.

Declare shell: "bash" on the hook. Claude Code &gt;= 2.1.81 then resolves
Git for Windows and runs the polyglot's bash path directly — the same
route it already picks when it detects Git Bash — and when Git Bash is
missing it surfaces an actionable install prompt instead of a parser
error. Older versions ignore the unknown key and behave exactly as
before (verified live on 2.0.77 and 2.1.80).

Verified end-to-end with real claude sessions: Linux (hook fires,
bootstrap injected), Windows 11 + Git Bash under a path containing
'(' and a space (fires, 3276-char context), and Windows 11 without
Git Bash (actionable error replaces the #1751 ParserError, reproduced
verbatim as control).

Fixes #1751
Fixes #1918
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The SessionStart command string starts with a quoted path, which breaks
both Windows shells Claude Code may hand it to: PowerShell parses the
leading quoted string as an expression and dies on the next bareword
('Unexpected token session-start', #1751), and cmd.exe's /c quote rule
drops the outer quotes when the path contains a metacharacter, so a
profile dir like C:\Users\Name(External) truncates the command at the
'(' (#1918). Either way the bootstrap silently never loads.

Declare shell: "bash" on the hook. Claude Code &gt;= 2.1.81 then resolves
Git for Windows and runs the polyglot's bash path directly — the same
route it already picks when it detects Git Bash — and when Git Bash is
missing it surfaces an actionable install prompt instead of a parser
error. Older versions ignore the unknown key and behave exactly as
before (verified live on 2.0.77 and 2.1.80).

Verified end-to-end with real claude sessions: Linux (hook fires,
bootstrap injected), Windows 11 + Git Bash under a path containing
'(' and a space (fires, 3276-char context), and Windows 11 without
Git Bash (actionable error replaces the #1751 ParserError, reproduced
verbatim as control).

Fixes #1751
Fixes #1918
</pre>
</div>
</content>
</entry>
<entry>
<title>docs: fix dead references to pruned claude-code-tools.md/copilot-tools.md</title>
<updated>2026-07-15T19:15:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-15T19:12:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=fb7b07088ed03da76508b8a70a87bf4f15b2412a'/>
<id>fb7b07088ed03da76508b8a70a87bf4f15b2412a</id>
<content type='text'>
e7ddc25 deleted claude-code-tools.md and copilot-tools.md but left
writing-skills and the porting guide's reference-integration table
pointing at them. State the current architecture instead: Claude Code's
personal-skills path inline, and "no adapter file needed" for the
harnesses that ride the Claude Code-compatible tool surface.

Reported by @rasibintang (#1969, with a fix proposed in #1970).

Fixes #1969
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
e7ddc25 deleted claude-code-tools.md and copilot-tools.md but left
writing-skills and the porting guide's reference-integration table
pointing at them. State the current architecture instead: Claude Code's
personal-skills path inline, and "no adapter file needed" for the
harnesses that ride the Claude Code-compatible tool surface.

Reported by @rasibintang (#1969, with a fix proposed in #1970).

Fixes #1969
</pre>
</div>
</content>
</entry>
<entry>
<title>test(pi): scope mapping assertions to the table, not whole file</title>
<updated>2026-07-15T18:10:55+00:00</updated>
<author>
<name>Gaurav Dubey</name>
<email>gauravdubey0107@gmail.com</email>
</author>
<published>2026-07-14T12:06:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=7a81eb71774fc430b9eb0bd17d042ba659a4c8ca'/>
<id>7a81eb71774fc430b9eb0bd17d042ba659a4c8ca</id>
<content type='text'>
The pi tokens (subagent, pi-subagents, Task, TODO.md) also appear in the
surrounding prose, so matching the whole file passed even with the mapping
table deleted — the exact regression this test exists to catch. Filter to
table rows (lines starting with '|') so the assertion fails when the table
is gone and passes on dev.

Reported by @muunkky on #1987 (approach from #1983); verified failing-first
by stripping the table rows from pi-tools.md.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The pi tokens (subagent, pi-subagents, Task, TODO.md) also appear in the
surrounding prose, so matching the whole file passed even with the mapping
table deleted — the exact regression this test exists to catch. Filter to
table rows (lines starting with '|') so the assertion fails when the table
is gone and passes on dev.

Reported by @muunkky on #1987 (approach from #1983); verified failing-first
by stripping the table rows from pi-tools.md.
</pre>
</div>
</content>
</entry>
<entry>
<title>test: realign antigravity + pi mapping assertions with pruned references</title>
<updated>2026-07-15T18:10:55+00:00</updated>
<author>
<name>Gaurav Dubey</name>
<email>gauravdubey0107@gmail.com</email>
</author>
<published>2026-07-12T14:24:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=2b1c06a849535517ef8b32c35f4df33288a0fe87'/>
<id>2b1c06a849535517ef8b32c35f4df33288a0fe87</id>
<content type='text'>
Commit e7ddc25 ('Prune per-harness tool-mapping boilerplate') deliberately
removed the skill-loading explainers and generic action-&gt;tool tables from
antigravity-tools.md and pi-tools.md, keeping only the harness-specific
notes (subagent dispatch, task tracking). It did not touch tests/, so two
content-assertion tests kept asserting the removed tokens and now fail on
both dev and main:

  - tests/antigravity/test-antigravity-tools.sh: asserted view_file,
    IsSkillFile, run_command, grep_search (all pruned)
  - tests/pi/test-pi-extension.mjs: asserted read/write/edit/bash (pruned)

Update both to assert only the surviving harness-specific mappings. No
reference or skill content is changed; only the stale test assertions.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Commit e7ddc25 ('Prune per-harness tool-mapping boilerplate') deliberately
removed the skill-loading explainers and generic action-&gt;tool tables from
antigravity-tools.md and pi-tools.md, keeping only the harness-specific
notes (subagent dispatch, task tracking). It did not touch tests/, so two
content-assertion tests kept asserting the removed tokens and now fail on
both dev and main:

  - tests/antigravity/test-antigravity-tools.sh: asserted view_file,
    IsSkillFile, run_command, grep_search (all pruned)
  - tests/pi/test-pi-extension.mjs: asserted read/write/edit/bash (pruned)

Update both to assert only the surviving harness-specific mappings. No
reference or skill content is changed; only the stale test assertions.
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): fold TDD Why Order Matters rebuttals into rationalization table</title>
<updated>2026-07-14T22:02:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:30:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=4562d18dcfc1ff7c65ec9aae5848539532724a1d'/>
<id>4562d18dcfc1ff7c65ec9aae5848539532724a1d</id>
<content type='text'>
The eval verdict on this cut: deleting Why Order Matters and trusting the
compressed one-line table rows measurably degrades test-first behavior under
the exact pressure the section rebutted ("just write it, tests after") —
control 8/10 → treatment 5/10 at n=10, corroborated on both Claude and Codex.
Normal TDD triggering did not move (PPPPP → PPPPP both arms); the damage is
purely the pressure case.

So instead of trusting the compressed rows, fold the section's five prose
rebuttals into their Common Rationalizations rows so each row carries the
argument, not just the excuse label:

- "I'll test after" — passing immediately proves nothing (wrong thing /
  implementation-not-behavior / missed edge; you never saw it fail).
- "Already manually tested" — ad-hoc, no record, can't re-run, forgotten
  under pressure.
- "Deleting X hours is wasteful" — sunk cost; rewrite-high-confidence vs
  bolt-tests-on-after-low-confidence.
- "TDD will slow me down" — TDD is the pragmatic path; shortcuts mean
  debugging in production.
- "Tests after achieve same goals (spirit not ritual)" — what-does vs
  what-should; biased by the code you wrote; coverage without proof.

Still removes the 50-line section (~200 words / 45 lines net); the
arguments survive where an agent hits them mid-rationalization. Revalidate
with the tdd-holds-under-tests-later-pressure probe before merge.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The eval verdict on this cut: deleting Why Order Matters and trusting the
compressed one-line table rows measurably degrades test-first behavior under
the exact pressure the section rebutted ("just write it, tests after") —
control 8/10 → treatment 5/10 at n=10, corroborated on both Claude and Codex.
Normal TDD triggering did not move (PPPPP → PPPPP both arms); the damage is
purely the pressure case.

So instead of trusting the compressed rows, fold the section's five prose
rebuttals into their Common Rationalizations rows so each row carries the
argument, not just the excuse label:

- "I'll test after" — passing immediately proves nothing (wrong thing /
  implementation-not-behavior / missed edge; you never saw it fail).
- "Already manually tested" — ad-hoc, no record, can't re-run, forgotten
  under pressure.
- "Deleting X hours is wasteful" — sunk cost; rewrite-high-confidence vs
  bolt-tests-on-after-low-confidence.
- "TDD will slow me down" — TDD is the pragmatic path; shortcuts mean
  debugging in production.
- "Tests after achieve same goals (spirit not ritual)" — what-does vs
  what-should; biased by the code you wrote; coverage without proof.

Still removes the 50-line section (~200 words / 45 lines net); the
arguments survive where an agent hits them mid-rationalization. Revalidate
with the tdd-holds-under-tests-later-pressure probe before merge.
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): drop The Bottom Line recap from receiving-code-review</title>
<updated>2026-07-14T22:02:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:29:40+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=14603727c895aae3e855074c0a44c9fbfa6e9ced'/>
<id>14603727c895aae3e855074c0a44c9fbfa6e9ced</id>
<content type='text'>
Restates the evaluate-don't-obey frame, verification rule, and
no-performative-agreement rule, each detailed earlier at point of use.
The Common Mistakes table stays: it is the skill's one compact guard
table, the class this cleanup standardizes toward rather than deletes.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Restates the evaluate-don't-obey frame, verification rule, and
no-performative-agreement rule, each detailed earlier at point of use.
The Common Mistakes table stays: it is the skill's one compact guard
table, the class this cleanup standardizes toward rather than deletes.
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): drop The Bottom Line recap from writing-skills</title>
<updated>2026-07-14T22:02:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:29:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=019e79cc461dd1af097e1bf30eee9d7875b18732'/>
<id>019e79cc461dd1af097e1bf30eee9d7875b18732</id>
<content type='text'>
Restates the Iron Law, the RED-GREEN-REFACTOR mapping, and the
TDD-for-docs framing, all stated in full earlier in the file.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Restates the Iron Law, the RED-GREEN-REFACTOR mapping, and the
TDD-for-docs framing, all stated in full earlier in the file.
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): drop Remember recap from writing-plans</title>
<updated>2026-07-14T22:02:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:28:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=d74653cf748949a52ddb90f773b6a459b5d8494c'/>
<id>d74653cf748949a52ddb90f773b6a459b5d8494c</id>
<content type='text'>
All four lines restate the Overview (DRY/YAGNI/TDD/frequent commits),
Task Structure (exact paths, commands with expected output), and No
Placeholders (complete code in every step).
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
All four lines restate the Overview (DRY/YAGNI/TDD/frequent commits),
Task Structure (exact paths, commands with expected output), and No
Placeholders (complete code in every step).
</pre>
</div>
</content>
</entry>
<entry>
<title>refactor(skills): fold brainstorming Key Principles into points of use</title>
<updated>2026-07-14T22:02:16+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-05T19:27:58+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=3550dd05cd41e1da429b13193a88155f8eea5941'/>
<id>3550dd05cd41e1da429b13193a88155f8eea5941</id>
<content type='text'>
Five of six principles restated the Checklist and Process sections
verbatim-in-spirit. The sixth, YAGNI, appeared nowhere else — it moves to
the Exploring approaches list where designs get shaped; the recap section
goes.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Five of six principles restated the Checklist and Process sections
verbatim-in-spirit. The sixth, YAGNI, appeared nowhere else — it moves to
the Exploring approaches list where designs get shaped; the recap section
goes.
</pre>
</div>
</content>
</entry>
</feed>
