<feed xmlns='http://www.w3.org/2005/Atom'>
<title>superpowers.git/tests/claude-code, branch opencode-native-skills</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 token usage analysis to subagent-driven-development test</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-30T04:51:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=faa65e7163e2fa6cfdc5b7277b38f2c2b7a8b688'/>
<id>faa65e7163e2fa6cfdc5b7277b38f2c2b7a8b688</id>
<content type='text'>
- Rewrote analyze-token-usage.py to parse main session file correctly
- Extracts usage from toolUseResult fields for each subagent
- Shows breakdown by agent with descriptions
- Integrated into test-subagent-driven-development-integration.sh
- Displays token usage automatically after each test run
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
- Rewrote analyze-token-usage.py to parse main session file correctly
- Extracts usage from toolUseResult fields for each subagent
- Shows breakdown by agent with descriptions
- Integrated into test-subagent-driven-development-integration.sh
- Displays token usage automatically after each test run
</pre>
</div>
</content>
</entry>
<entry>
<title>fix: verify skill usage via session transcript not text output</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-30T03:35:43+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=24ca8cd9d5fd83197ebe60ca45eb87e3476d6aa6'/>
<id>24ca8cd9d5fd83197ebe60ca45eb87e3476d6aa6</id>
<content type='text'>
The skill instructions are internal and don't appear in user-facing
output. Updated verification to parse the session JSONL transcript
and check for actual tool usage:
- Skill tool invocation
- Task tool (subagents)
- TodoWrite (tracking)
- Implementation results
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The skill instructions are internal and don't appear in user-facing
output. Updated verification to parse the session JSONL transcript
and check for actual tool usage:
- Skill tool invocation
- Task tool (subagents)
- TodoWrite (tracking)
- Implementation results
</pre>
</div>
</content>
</entry>
<entry>
<title>test: use bypassPermissions mode for unrestricted testing</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-30T01:15:21+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=8fbeca830a89027f9a40ee7cdcfee54202b9f65a'/>
<id>8fbeca830a89027f9a40ee7cdcfee54202b9f65a</id>
<content type='text'>
dontAsk mode was auto-denying Write tool. Use bypassPermissions
instead to allow full tool access in this controlled test environment.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
dontAsk mode was auto-denying Write tool. Use bypassPermissions
instead to allow full tool access in this controlled test environment.
</pre>
</div>
</content>
</entry>
<entry>
<title>test: auto-approve permissions with --permission-mode dontAsk</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-29T19:47:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=67de772d7f8fc53e426e856571a22dba69d625a1'/>
<id>67de772d7f8fc53e426e856571a22dba69d625a1</id>
<content type='text'>
Headless tests need automatic permission approval to write files.
Using dontAsk mode to auto-approve permissions for test directory.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Headless tests need automatic permission approval to write files.
Using dontAsk mode to auto-approve permissions for test directory.
</pre>
</div>
</content>
</entry>
<entry>
<title>test: add --add-dir flag for temp directory access</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-29T19:39:04+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=cf728637924c664250ab1433b1373fcdf05f9df7'/>
<id>cf728637924c664250ab1433b1373fcdf05f9df7</id>
<content type='text'>
Claude needs explicit permission to access the temp test directory.
Added --add-dir flag to grant access to the test project.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Claude needs explicit permission to access the temp test directory.
Added --add-dir flag to grant access to the test project.
</pre>
</div>
</content>
</entry>
<entry>
<title>test: show Claude output in real-time during integration test</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-29T19:29:12+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=baa23b16bbda52ad7082f3bfb8d68c4d0a3840f4'/>
<id>baa23b16bbda52ad7082f3bfb8d68c4d0a3840f4</id>
<content type='text'>
Use tee instead of redirection so test output is visible during
execution while still being saved to file for analysis.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Use tee instead of redirection so test output is visible during
execution while still being saved to file for analysis.
</pre>
</div>
</content>
</entry>
<entry>
<title>fix: run integration test from superpowers dir to access local dev skills</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-29T18:35:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=0aba33be1c64686a6e1682cce4fa2a0ed040fc33'/>
<id>0aba33be1c64686a6e1682cce4fa2a0ed040fc33</id>
<content type='text'>
The superpowers-dev marketplace makes skills available only when running
from the plugin directory. Updated test to run claude from superpowers
directory while working on the test project.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The superpowers-dev marketplace makes skills available only when running
from the plugin directory. Updated test to run claude from superpowers
directory while working on the test project.
</pre>
</div>
</content>
</entry>
<entry>
<title>Fix tests to use --allowed-tools flag</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-29T06:21:24+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=06310d6f5f960f28f8eec1d8117c0739a42e2163'/>
<id>06310d6f5f960f28f8eec1d8117c0739a42e2163</id>
<content type='text'>
Claude Code headless mode requires --allowed-tools flag to actually
execute tool calls. Without it, Claude only responds as if it's doing
things but doesn't actually use tools.

Changes:
- Updated run_claude helper to accept allowed_tools parameter
- Updated integration test to use --allowed-tools=all
- This enables actual tool execution (Write, Task, Bash, etc.)

Now the integration test should actually execute the workflow instead
of just talking about it.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Claude Code headless mode requires --allowed-tools flag to actually
execute tool calls. Without it, Claude only responds as if it's doing
things but doesn't actually use tools.

Changes:
- Updated run_claude helper to accept allowed_tools parameter
- Updated integration test to use --allowed-tools=all
- This enables actual tool execution (Write, Task, Bash, etc.)

Now the integration test should actually execute the workflow instead
of just talking about it.
</pre>
</div>
</content>
</entry>
<entry>
<title>Fix syntax error in integration test</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-28T23:22:01+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=dc11a093c326d947f9ac8e416f1cd4b17887bb9a'/>
<id>dc11a093c326d947f9ac8e416f1cd4b17887bb9a</id>
<content type='text'>
Simplified command substitution to avoid shell parsing issues.
Instead of nested heredoc in command substitution, write prompt
to file first then read it.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Simplified command substitution to avoid shell parsing issues.
Instead of nested heredoc in command substitution, write prompt
to file first then read it.
</pre>
</div>
</content>
</entry>
<entry>
<title>Add integration test for subagent-driven-development</title>
<updated>2025-12-18T00:44:50+00:00</updated>
<author>
<name>Jesse Vincent</name>
<email>jesse@fsck.com</email>
</author>
<published>2025-11-28T23:06:10+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/superpowers.git/commit/?id=fa946ae4652745318c3de3526f98c0e074cbdda3'/>
<id>fa946ae4652745318c3de3526f98c0e074cbdda3</id>
<content type='text'>
Created full end-to-end integration test that executes a real plan
and verifies the new workflow improvements actually work.

New test: test-subagent-driven-development-integration.sh
- Creates real Node.js test project
- Generates implementation plan (2 tasks)
- Executes using subagent-driven-development skill
- Verifies 8 key behaviors:
  1. Plan read once at beginning (not per task)
  2. Full task text provided to subagents (not file reading)
  3. Subagents perform self-review
  4. Spec compliance review before code quality
  5. Spec reviewer reads code independently
  6. Working implementation produced
  7. Tests pass
  8. No extra features added (spec compliance)

Integration tests are opt-in (--integration flag) due to 10-30 min runtime.

Updated run-skill-tests.sh:
- Added --integration flag
- Separates fast tests from integration tests
- Shows note when integration tests skipped

Updated README with integration test documentation.

Run with:
  ./run-skill-tests.sh                # Fast tests only
  ./run-skill-tests.sh --integration  # Include integration tests
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Created full end-to-end integration test that executes a real plan
and verifies the new workflow improvements actually work.

New test: test-subagent-driven-development-integration.sh
- Creates real Node.js test project
- Generates implementation plan (2 tasks)
- Executes using subagent-driven-development skill
- Verifies 8 key behaviors:
  1. Plan read once at beginning (not per task)
  2. Full task text provided to subagents (not file reading)
  3. Subagents perform self-review
  4. Spec compliance review before code quality
  5. Spec reviewer reads code independently
  6. Working implementation produced
  7. Tests pass
  8. No extra features added (spec compliance)

Integration tests are opt-in (--integration flag) due to 10-30 min runtime.

Updated run-skill-tests.sh:
- Added --integration flag
- Separates fast tests from integration tests
- Shows note when integration tests skipped

Updated README with integration test documentation.

Run with:
  ./run-skill-tests.sh                # Fast tests only
  ./run-skill-tests.sh --integration  # Include integration tests
</pre>
</div>
</content>
</entry>
</feed>
