Skip to content

fix: use devtrail analyze in devtrail-status skill#42

Merged
montfort merged 1 commit intomainfrom
fix/status-skill-use-analyze
Apr 4, 2026
Merged

fix: use devtrail analyze in devtrail-status skill#42
montfort merged 1 commit intomainfrom
fix/status-skill-use-analyze

Conversation

@montfort
Copy link
Copy Markdown
Contributor

@montfort montfort commented Apr 4, 2026

Summary

  • Replace outdated ">10 lines of changes" heuristic with devtrail analyze --output json (cognitive complexity, threshold 8) as the primary method for AILOG triggers in the devtrail-status skill
  • Add >20 lines fallback when CLI is unavailable, matching the canonical rule in AGENT-RULES.md
  • Update all 3 platform variants: Claude Code, Gemini, and generic agent workflow

Test plan

  • Run /devtrail-status in a project with devtrail CLI installed — verify it runs devtrail analyze and shows cognitive complexity metrics
  • Run /devtrail-status in a project without devtrail CLI — verify it falls back to line count heuristic
  • Verify output format shows (cognitive: N, threshold: 8) instead of (N lines changed)

🤖 Generated with Claude Code

…-status skill

The skill was using an outdated >10 lines rule to trigger AILOG documentation.
Now uses `devtrail analyze --output json` (cognitive complexity, threshold 8)
as the primary method, with >20 lines fallback when CLI is unavailable,
matching the canonical rule in AGENT-RULES.md and the devtrail-new skill.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@montfort montfort merged commit 6f66420 into main Apr 4, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant