<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/tests, branch codex/remove-readme-quickstart</title>
<subtitle>Agentic skills framework and development workflow
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/'/>
<entry>
<title>Drop devin-tools.md — not needed for correct operation</title>
<updated>2026-08-07T19:47:29+00:00</updated>
<author>
<name>Caio Lopes</name>
<email>caiodesalopes@gmail.com</email>
</author>
<published>2026-07-20T14:37:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=d21e171f5738700e05d4bd4cf056eea671c56b0f'/>
<id>d21e171f5738700e05d4bd4cf056eea671c56b0f</id>
<content type='text'>
Re-ran the clean-session acceptance test with the mapping file and the
SKILL.md Platform Adaptation pointer removed: using-superpowers and
brainstorming still auto-trigger first, and the full workflow chain
(writing-plans, executing-plans, TDD, verification) resolves every action
to Devin's native tools. Devin CLI's own system prompt already documents
its tools (skill invocation, subagent profiles, todo tracking, question
prompts), so the mapping was redundant. Test now validates the manifest only.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Re-ran the clean-session acceptance test with the mapping file and the
SKILL.md Platform Adaptation pointer removed: using-superpowers and
brainstorming still auto-trigger first, and the full workflow chain
(writing-plans, executing-plans, TDD, verification) resolves every action
to Devin's native tools. Devin CLI's own system prompt already documents
its tools (skill invocation, subagent profiles, todo tracking, question
prompts), so the mapping was redundant. Test now validates the manifest only.
</pre>
</div>
</content>
</entry>
<entry>
<title>feat: add Devin CLI support</title>
<updated>2026-08-07T19:47:29+00:00</updated>
<author>
<name>Caio Lopes</name>
<email>caiodesalopes@gmail.com</email>
</author>
<published>2026-07-16T13:46:34+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=09a567b6f4e3ee47aa64c5e8db81a075217bbbfa'/>
<id>09a567b6f4e3ee47aa64c5e8db81a075217bbbfa</id>
<content type='text'>
Devin CLI's `devin plugins install obra/superpowers` fails today because the
repo has no `.devin-plugin/plugin.json` manifest. Add the manifest (skills are
auto-discovered from the co-located skills/ directory), a Devin tool mapping
linked from using-superpowers' Platform Adaptation section, a README install
section, version tracking in .version-bump.json, a Codex-sync exclude for the
new dotdir, and a CI-safe test mirroring the kimi/antigravity test style.

Bootstrap rides Devin's native skill surfacing: every installed skill's
name + description is injected into the system prompt at session start with a
standing instruction to invoke matching skills via the native skill tool.
Acceptance test ("Let's make a react todo list") passes in a clean session:
using-superpowers and brainstorming auto-trigger before any code is written.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Devin CLI's `devin plugins install obra/superpowers` fails today because the
repo has no `.devin-plugin/plugin.json` manifest. Add the manifest (skills are
auto-discovered from the co-located skills/ directory), a Devin tool mapping
linked from using-superpowers' Platform Adaptation section, a README install
section, version tracking in .version-bump.json, a Codex-sync exclude for the
new dotdir, and a CI-safe test mirroring the kimi/antigravity test style.

Bootstrap rides Devin's native skill surfacing: every installed skill's
name + description is injected into the system prompt at session start with a
standing instruction to invoke matching skills via the native skill tool.
Acceptance test ("Let's make a react todo list") passes in a clean session:
using-superpowers and brainstorming auto-trigger before any code is written.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(release): wire Hermes into version bumps</title>
<updated>2026-08-06T23:21:12+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-08-06T21:47:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=5f8f500b1d8655607890b8439cb5c31b4301917c'/>
<id>5f8f500b1d8655607890b8439cb5c31b4301917c</id>
<content type='text'>
Register the Hermes YAML manifest alongside the existing JSON manifests. Route manifest reads and writes by extension through jq or Mike Farah yq v4, with field names and values passed as data.

Preflight every present manifest before the mutating bump loop so a deterministic YAML read failure cannot leave earlier JSON manifests partially updated. Cover check, audit, bump, registry wiring, and byte-for-byte no-partial-write behavior with one focused fixture test.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Register the Hermes YAML manifest alongside the existing JSON manifests. Route manifest reads and writes by extension through jq or Mike Farah yq v4, with field names and values passed as data.

Preflight every present manifest before the mutating bump loop so a deterministic YAML read failure cannot leave earlier JSON manifests partially updated. Cover check, audit, bump, registry wiring, and byte-for-byte no-partial-write behavior with one focused fixture test.
</pre>
</div>
</content>
</entry>
<entry>
<title>test(writing-skills): cover render-graphs execution</title>
<updated>2026-08-06T05:38:40+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-07-02T21:09:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=02654f93bf723eb1e3c8c4c6e74bd338f990b1c2'/>
<id>02654f93bf723eb1e3c8c4c6e74bd338f990b1c2</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>test(hermes): realign suite with the pre_llm_call mechanism; slim docs to the README section</title>
<updated>2026-07-23T23:05:54+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-23T23:05:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b6613057ae5cb1ecb634f12e52cc47a260caf0e4'/>
<id>b6613057ae5cb1ecb634f12e52cc47a260caf0e4</id>
<content type='text'>
The 20-test suite still exercised the dead on_session_start/inject_message
mechanism (17 failures against the rewritten plugin). Rewritten for the
real contract: pre_llm_call registration + first-turn-only context return,
register_skill receiving pathlib.Path (the conftest mock now raises on str,
mirroring hermes' AttributeError that silently disables a plugin), both
install layouts resolving skills, loud failure when skills are missing,
tool mapping sourced verbatim from hermes-tools.md, and a bootstrap-size
guard against hermes' 10k-char context spill threshold. 19 tests, passing.

Install docs collapse into the README section per maintainer direction:
docs/README.hermes.md and .hermes-plugin/INSTALL.md are gone; the README
carries the two-line install plus the compaction caveat. plugin.yaml
version aligned to 6.1.1.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The 20-test suite still exercised the dead on_session_start/inject_message
mechanism (17 failures against the rewritten plugin). Rewritten for the
real contract: pre_llm_call registration + first-turn-only context return,
register_skill receiving pathlib.Path (the conftest mock now raises on str,
mirroring hermes' AttributeError that silently disables a plugin), both
install layouts resolving skills, loud failure when skills are missing,
tool mapping sourced verbatim from hermes-tools.md, and a bootstrap-size
guard against hermes' 10k-char context spill threshold. 19 tests, passing.

Install docs collapse into the README section per maintainer direction:
docs/README.hermes.md and .hermes-plugin/INSTALL.md are gone; the README
carries the two-line install plus the compaction caveat. plugin.yaml
version aligned to 6.1.1.
</pre>
</div>
</content>
</entry>
<entry>
<title>feat(hermes): Hermes Agent harness support, rebased to a Hermes-only diff</title>
<updated>2026-07-23T19:18:13+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-23T19:18:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=7b177613c03a00042e67422dce8fc7814ae248c3'/>
<id>7b177613c03a00042e67422dce8fc7814ae248c3</id>
<content type='text'>
Rebase of PR #1922 onto current dev: the ~14 files of v6.1.0-era
codex/release drift are dropped, the porting-guide edits (stale against
the post-prune rewrite, no Hermes content) are dropped, and the Hermes
surface is kept intact: .hermes-plugin/ (on_session_start bootstrap
injection), tests/hermes/ (20 tests, passing), docs/README.hermes.md,
references/hermes-tools.md, the Platform Adaptation row, README section,
and Python ignores.

Known open items from review, unchanged by this rebase: the injection
mechanism uses ctx.inject_message from on_session_start, which the
official plugin guide does not document (pre_llm_call returning
{"context": ...} is the sanctioned path), skills are not registered via
ctx.register_skill, and the acceptance transcript predates the fix.

Co-authored-by: kumarabd &lt;kumarabd@users.noreply.github.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Rebase of PR #1922 onto current dev: the ~14 files of v6.1.0-era
codex/release drift are dropped, the porting-guide edits (stale against
the post-prune rewrite, no Hermes content) are dropped, and the Hermes
surface is kept intact: .hermes-plugin/ (on_session_start bootstrap
injection), tests/hermes/ (20 tests, passing), docs/README.hermes.md,
references/hermes-tools.md, the Platform Adaptation row, README section,
and Python ignores.

Known open items from review, unchanged by this rebase: the injection
mechanism uses ctx.inject_message from on_session_start, which the
official plugin guide does not document (pre_llm_call returning
{"context": ...} is the sanctioned path), skills are not registered via
ctx.register_skill, and the acceptance transcript predates the fix.

Co-authored-by: kumarabd &lt;kumarabd@users.noreply.github.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(systematic-debugging): find-polluter accepts ./-prefixed patterns and matches top-level tests</title>
<updated>2026-07-23T17:54:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-07-23T17:54:50+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=0146173544e48a6bc970b2a7cca1e16c2c697a6d'/>
<id>0146173544e48a6bc970b2a7cca1e16c2c697a6d</id>
<content type='text'>
Follow-up to #2011 (which fixed the ./-prefix mismatch for the documented
pattern form): strip a leading ./ from the caller's pattern instead of
double-prefixing it into a never-matching ././ form, and also match the
pattern with '**/' collapsed, since find -path cannot match '**/' against
zero directory levels and silently skipped files directly under the base
directory (src/top.test.ts vs src/**/*.test.ts).

Adds a deterministic test suite for the script with a stubbed npm.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Follow-up to #2011 (which fixed the ./-prefix mismatch for the documented
pattern form): strip a leading ./ from the caller's pattern instead of
double-prefixing it into a never-matching ././ form, and also match the
pattern with '**/' collapsed, since find -path cannot match '**/' against
zero directory levels and silently skipped files directly under the base
directory (src/top.test.ts vs src/**/*.test.ts).

Adds a deterministic test suite for the script with a stubbed npm.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(tests): stop the SDD skill test flaking on timing and prose case</title>
<updated>2026-07-19T19:04:46+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-16T04:00:15+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=0634449ca6b8198556a60f0f59ae70493b13fe1b'/>
<id>0634449ca6b8198556a60f0f59ae70493b13fe1b</id>
<content type='text'>
tests/claude-code/test-subagent-driven-development.sh failed
intermittently for two independent reasons:

- Budget mismatch: the file runs 9 prompts with a 90s timeout each
  (810s worst case) inside the runner's 600s per-file ceiling, so slow
  backend days produced spurious timeouts. Raise the runner default to
  900s and fix the help text, which claimed the default was 300.
- Case-sensitive prose matching: the assert helpers grepped free-form
  model output case-sensitively, but models capitalize the skill's own
  headings — observed failures include "Do Not Trust the Report"
  missing pattern "not trust" and a structured answer missing
  "First:.*spec.*compliance". Match case-insensitively in
  assert_contains/assert_not_contains/assert_count/assert_order, widen
  two Test 5 keyword patterns to phrasings observed in real runs, and
  make assert_order dump the output on failure the way assert_contains
  already does, so the next flake is diagnosable.

Observed 3 failures across 4 runs before the change (timeout, two
distinct pattern misses); 3/3 consecutive full runs pass after it.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
tests/claude-code/test-subagent-driven-development.sh failed
intermittently for two independent reasons:

- Budget mismatch: the file runs 9 prompts with a 90s timeout each
  (810s worst case) inside the runner's 600s per-file ceiling, so slow
  backend days produced spurious timeouts. Raise the runner default to
  900s and fix the help text, which claimed the default was 300.
- Case-sensitive prose matching: the assert helpers grepped free-form
  model output case-sensitively, but models capitalize the skill's own
  headings — observed failures include "Do Not Trust the Report"
  missing pattern "not trust" and a structured answer missing
  "First:.*spec.*compliance". Match case-insensitively in
  assert_contains/assert_not_contains/assert_count/assert_order, widen
  two Test 5 keyword patterns to phrasings observed in real runs, and
  make assert_order dump the output on failure the way assert_contains
  already does, so the next flake is diagnosable.

Observed 3 failures across 4 runs before the change (timeout, two
distinct pattern misses); 3/3 consecutive full runs pass after it.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(codex): make package script and its test portable beyond macOS/bsdtar</title>
<updated>2026-07-19T19:04:46+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-16T03:32:25+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=3fe3cb0530794f0b0b613a4f015e094efd61431d'/>
<id>3fe3cb0530794f0b0b613a4f015e094efd61431d</id>
<content type='text'>
The packaging pipeline only worked on a Mac with default umask, for
three stacked reasons:

- The deterministic-metadata tar flags (--uid/--gid/--uname/--gname)
  are bsdtar spellings; GNU tar rejects them, so the tar.gz archive
  step died on Linux. Detect the tar flavor and use --owner=:0
  --group=:0 --numeric-owner on GNU tar, which writes byte-identical
  ustar headers (uid/gid 0, empty uname/gname).
- Staged file modes depended on two umasks canceling out: git archive
  masks entry modes with tar.umask (git default 0002 -&gt; 775), and the
  unflagged tar extraction re-masked with the process umask (022 on
  macOS -&gt; 755, but 002 elsewhere -&gt; 775). Pin tar.umask=0022 on the
  archive call and extract with -p so staged modes are canonical
  755/644 on every machine.
- The test's timestamp assertion parsed bsdtar's -tv column layout and
  expected epoch 0 rendered in a US timezone ("Dec 31 1969"); GNU tar
  uses different columns and UTC hosts render "1970-01-01". Assert
  mtime == 0 via python3 tarfile instead, matching how the test
  already checks zip timestamps.

tests/codex/test-package-codex-plugin.sh now passes on Linux/GNU tar;
the bsdtar branch preserves the exact flags that passed on macOS.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The packaging pipeline only worked on a Mac with default umask, for
three stacked reasons:

- The deterministic-metadata tar flags (--uid/--gid/--uname/--gname)
  are bsdtar spellings; GNU tar rejects them, so the tar.gz archive
  step died on Linux. Detect the tar flavor and use --owner=:0
  --group=:0 --numeric-owner on GNU tar, which writes byte-identical
  ustar headers (uid/gid 0, empty uname/gname).
- Staged file modes depended on two umasks canceling out: git archive
  masks entry modes with tar.umask (git default 0002 -&gt; 775), and the
  unflagged tar extraction re-masked with the process umask (022 on
  macOS -&gt; 755, but 002 elsewhere -&gt; 775). Pin tar.umask=0022 on the
  archive call and extract with -p so staged modes are canonical
  755/644 on every machine.
- The test's timestamp assertion parsed bsdtar's -tv column layout and
  expected epoch 0 rendered in a US timezone ("Dec 31 1969"); GNU tar
  uses different columns and UTC hosts render "1970-01-01". Assert
  mtime == 0 via python3 tarfile instead, matching how the test
  already checks zip timestamps.

tests/codex/test-package-codex-plugin.sh now passes on Linux/GNU tar;
the bsdtar branch preserves the exact flags that passed on macOS.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(hooks): dispatch the SessionStart hook via Git Bash on Windows</title>
<updated>2026-07-19T19:03:59+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-07-16T00:13:35+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=df78c6bfafb55db2d17c1c61bab2b532a9aa3e09'/>
<id>df78c6bfafb55db2d17c1c61bab2b532a9aa3e09</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>
</feed>
