<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/tests, branch codex/openclaw-native-plugin</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 native OpenClaw plugin support</title>
<updated>2026-04-28T23:56:39+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-28T23:56:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=dc6082d7ff9dcfd15d16c71a883ae6cf51fb51cf'/>
<id>dc6082d7ff9dcfd15d16c71a883ae6cf51fb51cf</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(tests): make SDD integration test actually run its assertions</title>
<updated>2026-04-28T19:20:31+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@primeradiant.com</email>
</author>
<published>2026-04-28T19:20:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=e795530c2355eabcb1f17608d9d339dfafef2261'/>
<id>e795530c2355eabcb1f17608d9d339dfafef2261</id>
<content type='text'>
The SDD integration test silently bailed before printing any verification
results. Three independent bugs caused this:

1. `WORKING_DIR_ESCAPED` was computed from `$SCRIPT_DIR/../..` without
   resolving `..` segments. The resulting "directory" name contained
   literal `..` so `find` was looking in a path that doesn't exist.

2. With `set -euo pipefail`, the `find ... | sort -r | head -1` pipeline
   could exit non-zero (SIGPIPE on the producer when head closes early),
   killing the script silently before assertions ran.

3. The `claude -p` invocation never passed `--plugin-dir`, so it loaded
   the installed plugin instead of the working tree. Local edits to
   skills under test were not actually being tested.

Other adjustments:
- Run claude from inside the unique TEST_PROJECT directory instead of
  from the plugin root, so its session JSONL lives in its own
  `~/.claude/projects/` folder and doesn't race other concurrent
  claude sessions for "most recent file".
- Use the same character-normalization claude does (every non-alphanumeric
  becomes `-`) when computing the session dir name; macOS-resolved
  `/private/var/...` paths and tmp dirs with `.`/`_` in their names need
  this to round-trip correctly.
- Accept either `"name":"Agent"` or `"name":"Task"` in the subagent count
  — the harness renamed the tool but the test wasn't updated.

Verified on this branch: all six verification tests now pass against a
real end-to-end SDD run (skill invoked, 7 subagents dispatched, 6
TodoWrite calls, working code produced, tests pass, no extra features).
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The SDD integration test silently bailed before printing any verification
results. Three independent bugs caused this:

1. `WORKING_DIR_ESCAPED` was computed from `$SCRIPT_DIR/../..` without
   resolving `..` segments. The resulting "directory" name contained
   literal `..` so `find` was looking in a path that doesn't exist.

2. With `set -euo pipefail`, the `find ... | sort -r | head -1` pipeline
   could exit non-zero (SIGPIPE on the producer when head closes early),
   killing the script silently before assertions ran.

3. The `claude -p` invocation never passed `--plugin-dir`, so it loaded
   the installed plugin instead of the working tree. Local edits to
   skills under test were not actually being tested.

Other adjustments:
- Run claude from inside the unique TEST_PROJECT directory instead of
  from the plugin root, so its session JSONL lives in its own
  `~/.claude/projects/` folder and doesn't race other concurrent
  claude sessions for "most recent file".
- Use the same character-normalization claude does (every non-alphanumeric
  becomes `-`) when computing the session dir name; macOS-resolved
  `/private/var/...` paths and tmp dirs with `.`/`_` in their names need
  this to round-trip correctly.
- Accept either `"name":"Agent"` or `"name":"Task"` in the subagent count
  — the harness renamed the tool but the test wasn't updated.

Verified on this branch: all six verification tests now pass against a
real end-to-end SDD run (skill invoked, 7 subagents dispatched, 6
TodoWrite calls, working code produced, tests pass, no extra features).
</pre>
</div>
</content>
</entry>
<entry>
<title>Preserve Codex marketplace metadata</title>
<updated>2026-04-27T21:31:27+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-27T21:23:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=b1c15fd9f825be54c10da655245ec7dd67f88575'/>
<id>b1c15fd9f825be54c10da655245ec7dd67f88575</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>test(opencode): modernize integration tests</title>
<updated>2026-04-27T20:45:23+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-27T19:24:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=88eb6679ae5867f23821a7f00068a52933d36619'/>
<id>88eb6679ae5867f23821a7f00068a52933d36619</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>test(opencode): simplify bootstrap cache coverage</title>
<updated>2026-04-27T18:56:00+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-27T18:38:26+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=7e59af81488ceb21976eeb1c2d66fe21f8bf697b'/>
<id>7e59af81488ceb21976eeb1c2d66fe21f8bf697b</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>fix(opencode): cache bootstrap content at module level to eliminate per-step file I/O</title>
<updated>2026-04-27T18:56:00+00:00</updated>
<author>
<name>voidborne-d</name>
<email>voidborne-d@users.noreply.github.com</email>
</author>
<published>2026-04-20T13:54:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=c13a884c06af1d213f1a2debd13f13970ab74e45'/>
<id>c13a884c06af1d213f1a2debd13f13970ab74e45</id>
<content type='text'>
getBootstrapContent() called fs.existsSync + fs.readFileSync + regex
frontmatter parsing on every agent step with zero caching.  The
experimental.chat.messages.transform hook fires every step in opencode's
agent loop (messages are reloaded from DB each step via
filterCompactedEffect).  A 10-step turn triggered 10 redundant file
reads + 10 regex parses for content that never changes during a session.

Changes:
- Add module-level _bootstrapCache (undefined = not loaded, null = file
  missing) so the first call reads and parses SKILL.md, all subsequent
  calls return the cached string with zero filesystem access
- Cache the null sentinel when SKILL.md is missing, preventing repeated
  fs.existsSync probes
- Add _testing export (resetCache/getCache) for test infrastructure
- Clarify the injection guard comment explaining how it interacts with
  opencode's per-step message reloading
- Add 15 regression tests covering cache behavior, fs call counts,
  injection guard, missing file sentinel, cache reset, and source audit

Fixes #1202
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
getBootstrapContent() called fs.existsSync + fs.readFileSync + regex
frontmatter parsing on every agent step with zero caching.  The
experimental.chat.messages.transform hook fires every step in opencode's
agent loop (messages are reloaded from DB each step via
filterCompactedEffect).  A 10-step turn triggered 10 redundant file
reads + 10 regex parses for content that never changes during a session.

Changes:
- Add module-level _bootstrapCache (undefined = not loaded, null = file
  missing) so the first call reads and parses SKILL.md, all subsequent
  calls return the cached string with zero filesystem access
- Cache the null sentinel when SKILL.md is missing, preventing repeated
  fs.existsSync probes
- Add _testing export (resetCache/getCache) for test infrastructure
- Clarify the injection guard comment explaining how it interacts with
  opencode's per-step message reloading
- Add 15 regression tests covering cache behavior, fs call counts,
  injection guard, missing file sentinel, cache reset, and source audit

Fixes #1202
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge remote-tracking branch 'origin/main' into dev</title>
<updated>2026-04-27T18:42:51+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-27T18:42:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=1ca87f861f43a59c41fc6b3ce583f870c1467204'/>
<id>1ca87f861f43a59c41fc6b3ce583f870c1467204</id>
<content type='text'>
# Conflicts:
#	.claude-plugin/marketplace.json
#	.claude-plugin/plugin.json
#	.cursor-plugin/plugin.json
#	RELEASE-NOTES.md
#	gemini-extension.json
#	package.json
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
# Conflicts:
#	.claude-plugin/marketplace.json
#	.claude-plugin/plugin.json
#	.cursor-plugin/plugin.json
#	RELEASE-NOTES.md
#	gemini-extension.json
#	package.json
</pre>
</div>
</content>
</entry>
<entry>
<title>Use committed Codex plugin files in sync script</title>
<updated>2026-04-24T02:02:37+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2026-04-24T01:31:11+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=6efe32c9e2dd002d0c394e861e0529675d1ab32e'/>
<id>6efe32c9e2dd002d0c394e861e0529675d1ab32e</id>
<content type='text'>
- commit .codex-plugin/plugin.json and brand assets in this repo
- sync tracked Codex plugin files instead of generating or seeding them
- honor upstream gitignored files during rsync
- cover the new sync behavior with regression tests
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- commit .codex-plugin/plugin.json and brand assets in this repo
- sync tracked Codex plugin files instead of generating or seeding them
- honor upstream gitignored files during rsync
- cover the new sync behavior with regression tests
</pre>
</div>
</content>
</entry>
<entry>
<title>fix: Step 1a validated through TDD — explicit naming + consent bridge (PRI-974)</title>
<updated>2026-04-07T00:13:19+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-06T23:07:50+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=61ad4821daf3c14b4ef71e50ea6a3bb652311b9b'/>
<id>61ad4821daf3c14b4ef71e50ea6a3bb652311b9b</id>
<content type='text'>
Step 1a failed at 2/6 with the spec's original abstract text ("use your
native tool"). Three REFACTOR iterations found what works (50/50 runs):

1. Explicit tool naming — "do you have EnterWorktree, WorktreeCreate..."
   transforms interpretation into factual toolkit check
2. Consent bridge — "user's consent is your authorization" directly
   addresses EnterWorktree's "ONLY when user explicitly asks" guardrail
3. Red Flag entry naming the specific anti-pattern

File split was tested but proven unnecessary — the fix is the Step 1a
text quality, not physical separation of git commands. Control test
with full 240-line skill (all git commands visible) passed 20/20.

Test script updated: supports batch runs (./test.sh green 20), "all"
phase, and checks absence of git worktree add (reliable signal) rather
than presence of EnterWorktree text (agent sometimes omits tool name).

Co-Authored-By: Claude Opus 4.6 (1M context) &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Step 1a failed at 2/6 with the spec's original abstract text ("use your
native tool"). Three REFACTOR iterations found what works (50/50 runs):

1. Explicit tool naming — "do you have EnterWorktree, WorktreeCreate..."
   transforms interpretation into factual toolkit check
2. Consent bridge — "user's consent is your authorization" directly
   addresses EnterWorktree's "ONLY when user explicitly asks" guardrail
3. Red Flag entry naming the specific anti-pattern

File split was tested but proven unnecessary — the fix is the Step 1a
text quality, not physical separation of git commands. Control test
with full 240-line skill (all git commands visible) passed 20/20.

Test script updated: supports batch runs (./test.sh green 20), "all"
phase, and checks absence of git worktree add (reliable signal) rather
than presence of EnterWorktree text (agent sometimes omits tool name).

Co-Authored-By: Claude Opus 4.6 (1M context) &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>test: add RED/GREEN validation for native worktree preference (PRI-974)</title>
<updated>2026-04-07T00:13:19+00:00</updated>
<author>
<name>Drew Ritter</name>
<email>drew@primeradiant.com</email>
</author>
<published>2026-04-06T21:27:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=abaaf8a6e6ade9be52fd33ad0c5c8af0d91bbb8a'/>
<id>abaaf8a6e6ade9be52fd33ad0c5c8af0d91bbb8a</id>
<content type='text'>
Gate test for Step 1a — validates agents prefer EnterWorktree over
git worktree add on Claude Code. Must pass before skill rewrite.

Co-Authored-By: Claude Opus 4.6 (1M context) &lt;noreply@anthropic.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Gate test for Step 1a — validates agents prefer EnterWorktree over
git worktree add on Claude Code. Must pass before skill rewrite.

Co-Authored-By: Claude Opus 4.6 (1M context) &lt;noreply@anthropic.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
