Mcp Attribution Worktree

Use this one when you're working through a backlog of MCP or skills attribution issues from the local report API and want each fix to stay auditable. It pulls tool and skills-related issues, reads a representative run's result and trace before deciding anything, and routes actionable problems to either `mcp/src` or `config/source/skills`. Each repair goes into its own Worktrunk worktree with a GitHub issue and PR, and attribution gets stamped `owner=codex` with short evidence notes. The part I like is the closure sweep: it refuses to mark anything resolved until it has re-read the latest PR and review comments. The tradeoff is ceremony. It is heavy for a one-off bug, but for a steady stream of attribution noise it keeps the paper trail honest.

GitHub stars: 1.1K
last updated: Aug 3, 2026

View on GitHub

Install

$ npx -y skills add TencentCloudBase/CloudBase-AI-Toolkit --skill mcp-attribution-worktree --agent claude-code

Installs into .claude/skills of the current project.

Files

MCP Attribution Worktree

Process MCP and skills-related attribution issues as an auditable maintenance workflow instead of ad-hoc debugging.

What this skill does

Use this skill to:

fetch pending MCP and skills-related attribution issues from the local report API
inspect issue detail plus representative runs before making any status decision
map failures back to concrete mcp/src tools, config/source/skills, or classify them as environment / grader / duplicate noise
update attribution issues with concise evidence, owner=codex, and links to external GitHub work
isolate each actionable repair in its own Worktrunk worktree and branch
carry actionable issues through repo repair and PR creation instead of stopping at issue state updates
continue from existing GitHub issues or PRs when later review or evaluation feedback shows the first direction was incomplete or wrong
run a real post-PR evaluation when an evaluation interface is available, and use that result to decide whether another repair loop is needed