Skip to content

Add remaining Claude Code subagent definitions#4060

Merged
ChrisJBurns merged 2 commits intomainfrom
adds-subagents
Mar 9, 2026
Merged

Add remaining Claude Code subagent definitions#4060
ChrisJBurns merged 2 commits intomainfrom
adds-subagents

Conversation

@ChrisJBurns
Copy link
Copy Markdown
Collaborator

@ChrisJBurns ChrisJBurns commented Mar 9, 2026

Summary

The CLAUDE.md file references several specialized subagents that were not yet
defined in .claude/agents/. This adds the five missing agent definitions so
Claude Code can invoke them for domain-specific tasks.

  • golang-code-writer: Go code generation with idiomatic patterns
  • unit-test-writer: Comprehensive Go test writing (Ginkgo/Gomega)
  • tech-lead-orchestrator: Architectural oversight and task delegation
  • security-advisor: Security code review and architecture guidance
  • site-reliability-engineer: OpenTelemetry and observability expertise

Type of change

  • New feature

Test plan

  • Manual testing (describe below)

Verified that Claude Code correctly discovers and invokes the new subagents
when prompted with tasks matching their descriptions.

Does this introduce a user-facing change?

No. These are internal Claude Code agent definitions that improve AI-assisted
development workflows.

🤖 Generated with Claude Code

Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com>
@github-actions github-actions bot added the size/S Small PR: 100-299 lines changed label Mar 9, 2026
@ChrisJBurns ChrisJBurns changed the title adds remaining sub agents Add remaining Claude Code subagent definitions Mar 9, 2026
rdimitrov
rdimitrov previously approved these changes Mar 9, 2026
Signed-off-by: Chris Burns <29541485+ChrisJBurns@users.noreply.github.com>
@github-actions github-actions bot added size/L Large PR: 600-999 lines changed and removed size/S Small PR: 100-299 lines changed labels Mar 9, 2026
@ChrisJBurns
Copy link
Copy Markdown
Collaborator Author

@rdimitrov needs another tick. I had to push up the "Claude" proof version of them

@ChrisJBurns ChrisJBurns merged commit 406cb85 into main Mar 9, 2026
19 checks passed
@ChrisJBurns ChrisJBurns deleted the adds-subagents branch March 9, 2026 22:21
- Separate business logic from transport/protocol concerns
- Keep packages focused on single responsibilities

**Error Handling:**
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should we remove the duplicate stuff from claude.md?

- MCP Protocol: `github.com/mark3labs/mcp-go`
- Web Framework: Chi router (`github.com/go-chi/chi/v5`)
- CLI: Cobra, Configuration: Viper
- Testing: Ginkgo/Gomega, `go.uber.org/mock`
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

just fyi - (no action requested / previous job) I had migrated from uber/mock to mockery https://github.com/vektra/mockery, since uber/mock doesn't seem to be actively maintained, also a few cleaner improvements

{name: "empty input", input: "", wantErr: true},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also I've used the triple-a (arrange-act-assert) pattern which found useful (just something to consider)

@@ -0,0 +1,128 @@
---
name: unit-test-writer
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

one of the things I've noticed is sometimes Claude writing unit tests for private/helper methods, it's generally/mostly advised to not test private/helper methods directly but indirectly through the public/exported methods. Is this something we could consider or what's the current convention?

@codecov
Copy link
Copy Markdown

codecov bot commented Mar 9, 2026

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 68.69%. Comparing base (c25562f) to head (f8f3768).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #4060      +/-   ##
==========================================
+ Coverage   68.61%   68.69%   +0.07%     
==========================================
  Files         446      446              
  Lines       45435    45435              
==========================================
+ Hits        31176    31210      +34     
+ Misses      11850    11818      -32     
+ Partials     2409     2407       -2     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size/L Large PR: 600-999 lines changed

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants