<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git, branch f/codex</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 Codex superpowers integration</title>
<updated>2025-10-28T00:23:47+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-28T00:23:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=113d18ec28c8a4b6226f40d4a218990d8b9aed50'/>
<id>113d18ec28c8a4b6226f40d4a218990d8b9aed50</id>
<content type='text'>
- Single unified script: superpowers-codex with bootstrap/use-skill/find-skills commands
- Cross-platform Node.js implementation (works on Windows, macOS, Linux)
- Namespaced skills: superpowers:skill-name for core, skill-name for personal
- Personal skills override superpowers skills when names match
- Clean skill display: shows name/description without raw frontmatter
- Helpful context: shows supporting files directory for each skill
- Tool mapping for Codex: TodoWrite→update_plan, Skill→superpowers-codex, etc.
- Subagent orchestration instructions for codex --yolo exec
- Updated terminology: "Superpowers skills" instead of "Core skills"
- Bootstrap integration with AGENTS.md for automatic startup
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- Single unified script: superpowers-codex with bootstrap/use-skill/find-skills commands
- Cross-platform Node.js implementation (works on Windows, macOS, Linux)
- Namespaced skills: superpowers:skill-name for core, skill-name for personal
- Personal skills override superpowers skills when names match
- Clean skill display: shows name/description without raw frontmatter
- Helpful context: shows supporting files directory for each skill
- Tool mapping for Codex: TodoWrite→update_plan, Skill→superpowers-codex, etc.
- Subagent orchestration instructions for codex --yolo exec
- Updated terminology: "Superpowers skills" instead of "Core skills"
- Bootstrap integration with AGENTS.md for automatic startup
</pre>
</div>
</content>
</entry>
<entry>
<title>Release v3.2.3: Update using-superpowers to use Skill tool</title>
<updated>2025-10-23T23:34:55+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-23T23:34:55+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=19e2997334eef29d0b4ab3c40a4bc124d200d1fb'/>
<id>19e2997334eef29d0b4ab3c40a4bc124d200d1fb</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Update using-superpowers skill to use Skill tool instead of Read tool</title>
<updated>2025-10-23T23:34:05+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-23T23:34:05+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=c88b0d674f4fd1fdf76648036016313239bfbbcd'/>
<id>c88b0d674f4fd1fdf76648036016313239bfbbcd</id>
<content type='text'>
The Skill tool is the proper mechanism for invoking skills, not the Read tool.
Updated the bootstrap instructions and anti-rationalization guidance to reflect this.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The Skill tool is the proper mechanism for invoking skills, not the Read tool.
Updated the bootstrap instructions and anti-rationalization guidance to reflect this.
</pre>
</div>
</content>
</entry>
<entry>
<title>Release v3.2.2: Strengthen using-superpowers against agent rationalization</title>
<updated>2025-10-22T03:12:56+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-22T03:12:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=17bbc2b130f817f7b2e8aade82284b5887864c51'/>
<id>17bbc2b130f817f7b2e8aade82284b5887864c51</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Strengthen using-superpowers skill against agent rationalization</title>
<updated>2025-10-22T03:01:06+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-22T03:01:06+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=f6ee98a41a3087b1432ab94ef404ec766431aa5b'/>
<id>f6ee98a41a3087b1432ab94ef404ec766431aa5b</id>
<content type='text'>
Add three layers of enforcement to prevent agents from skipping skill usage:

1. EXTREMELY-IMPORTANT block with absolute language
   - "If even 1% chance a skill applies, you MUST read it"
   - "You do not have a choice. You cannot rationalize your way out."

2. MANDATORY FIRST RESPONSE PROTOCOL checklist
   - 5-step process agents must complete before any response
   - Explicit "responding without this = failure" consequence

3. Common Rationalizations section with 8 specific patterns
   - "This is just a simple question" → WRONG
   - "I can check files quickly" → WRONG
   - "Let me gather information first" → WRONG
   - Plus 5 more common evasion patterns

These changes address observed agent behavior where they rationalize
around skill usage despite clear instructions. The forceful language
and pre-emptive counter-arguments aim to make rationalization harder.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Add three layers of enforcement to prevent agents from skipping skill usage:

1. EXTREMELY-IMPORTANT block with absolute language
   - "If even 1% chance a skill applies, you MUST read it"
   - "You do not have a choice. You cannot rationalize your way out."

2. MANDATORY FIRST RESPONSE PROTOCOL checklist
   - 5-step process agents must complete before any response
   - Explicit "responding without this = failure" consequence

3. Common Rationalizations section with 8 specific patterns
   - "This is just a simple question" → WRONG
   - "I can check files quickly" → WRONG
   - "Let me gather information first" → WRONG
   - Plus 5 more common evasion patterns

These changes address observed agent behavior where they rationalize
around skill usage despite clear instructions. The forceful language
and pre-emptive counter-arguments aim to make rationalization harder.
</pre>
</div>
</content>
</entry>
<entry>
<title>Release v3.2.1: Add code-reviewer agent to plugin</title>
<updated>2025-10-20T17:19:24+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-20T17:19:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=e3d881b7b6ffb963fe7c80444fd7bf81ff61ca92'/>
<id>e3d881b7b6ffb963fe7c80444fd7bf81ff61ca92</id>
<content type='text'>
Fixes #55

Added superpowers:code-reviewer agent to plugin's agents/ directory.
Previously, skills referenced a code-reviewer agent that users needed
to configure personally, causing failures for new users.

Changes:
- New: agents/code-reviewer.md - Agent definition with systematic review checklist
- Updated: skills/requesting-code-review/SKILL.md - Use superpowers:code-reviewer
- Updated: skills/subagent-driven-development/SKILL.md - Use superpowers:code-reviewer
- Version bump: 3.2.0 -&gt; 3.2.1
- Added: .claude-plugin/marketplace.json for local development testing
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fixes #55

Added superpowers:code-reviewer agent to plugin's agents/ directory.
Previously, skills referenced a code-reviewer agent that users needed
to configure personally, causing failures for new users.

Changes:
- New: agents/code-reviewer.md - Agent definition with systematic review checklist
- Updated: skills/requesting-code-review/SKILL.md - Use superpowers:code-reviewer
- Updated: skills/subagent-driven-development/SKILL.md - Use superpowers:code-reviewer
- Version bump: 3.2.0 -&gt; 3.2.1
- Added: .claude-plugin/marketplace.json for local development testing
</pre>
</div>
</content>
</entry>
<entry>
<title>bump to 3.2.0</title>
<updated>2025-10-20T15:42:32+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-20T15:42:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=184a4c464e94a15c88a168ace8ebb3746df317cf'/>
<id>184a4c464e94a15c88a168ace8ebb3746df317cf</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Update RELEASE-NOTES.md for v3.2.0 release</title>
<updated>2025-10-18T17:41:29+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-18T17:41:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=7fc125e5e9d864e082de89e3f72ffa4b95d5cc92'/>
<id>7fc125e5e9d864e082de89e3f72ffa4b95d5cc92</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Update all superpowers skill references to use namespace prefix</title>
<updated>2025-10-18T17:38:54+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-18T17:38:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=79436abffa0f5a5b6376df6dc0eeba2c5f0dcf19'/>
<id>79436abffa0f5a5b6376df6dc0eeba2c5f0dcf19</id>
<content type='text'>
Skills are now namespaced as superpowers:&lt;name&gt; when referenced.
Updated all REQUIRED SUB-SKILL, RECOMMENDED SUB-SKILL, and
REQUIRED BACKGROUND references to use the superpowers: prefix.

Also added -design suffix to brainstorming skill's design document
filename to distinguish from implementation plan documents.

Files updated:
- brainstorming: Added -design suffix, updated skill references
- executing-plans: Updated finishing-a-development-branch reference
- subagent-driven-development: Updated finishing-a-development-branch reference
- systematic-debugging: Updated root-cause-tracing and test-driven-development references
- testing-skills-with-subagents: Updated test-driven-development reference
- writing-plans: Updated executing-plans and subagent-driven-development references
- writing-skills: Updated test-driven-development, systematic-debugging, and testing-skills-with-subagents references
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Skills are now namespaced as superpowers:&lt;name&gt; when referenced.
Updated all REQUIRED SUB-SKILL, RECOMMENDED SUB-SKILL, and
REQUIRED BACKGROUND references to use the superpowers: prefix.

Also added -design suffix to brainstorming skill's design document
filename to distinguish from implementation plan documents.

Files updated:
- brainstorming: Added -design suffix, updated skill references
- executing-plans: Updated finishing-a-development-branch reference
- subagent-driven-development: Updated finishing-a-development-branch reference
- systematic-debugging: Updated root-cause-tracing and test-driven-development references
- testing-skills-with-subagents: Updated test-driven-development reference
- writing-plans: Updated executing-plans and subagent-driven-development references
- writing-skills: Updated test-driven-development, systematic-debugging, and testing-skills-with-subagents references
</pre>
</div>
</content>
</entry>
<entry>
<title>Add design documentation phase to brainstorming skill</title>
<updated>2025-10-18T17:19:14+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-10-18T17:19:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=9597f088c43fc77173415f54a81de95e2a8404dc'/>
<id>9597f088c43fc77173415f54a81de95e2a8404dc</id>
<content type='text'>
The old brainstorming command included writing the design document
before handing off to implementation planning. This was lost when
the command was converted to a skill.

Added Phase 4: Design Documentation to write the validated design
to docs/plans/YYYY-MM-DD-&lt;topic&gt;.md before proceeding to worktree
setup and planning.

Tested with subagent to verify design document is written and
committed even under time pressure.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The old brainstorming command included writing the design document
before handing off to implementation planning. This was lost when
the command was converted to a skill.

Added Phase 4: Design Documentation to write the validated design
to docs/plans/YYYY-MM-DD-&lt;topic&gt;.md before proceeding to worktree
setup and planning.

Tested with subagent to verify design document is written and
committed even under time pressure.
</pre>
</div>
</content>
</entry>
</feed>
