Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From GSD Core
Validates .planning/ directory integrity and reports missing files, invalid configs, and orphaned plans. Optionally repairs issues or checks session context utilization.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gsd-core:gsd-health [--repair] [--context][--repair] [--context]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
<objective>
--context runs an orthogonal check: the running session's context utilization. The workflow asks for the model's tokensUsed + contextWindow, calls gsd-tools query validate.context, and renders one of three states:
| Utilization | State | Action |
|---|---|---|
| < 60% | healthy | no action — context is comfortable |
| 60% – 70% | warning | recommend /gsd-thread to start fresh |
| ≥ 70% | critical | reasoning quality may degrade past the fracture point |
<execution_context> @~/.claude/gsd-core/workflows/health.md </execution_context>
Execute end-to-end. Parse `--repair` and `--context` flags from arguments and pass to workflow.npx claudepluginhub open-gsd/gsd-coreChecks .planning/ directory integrity for files like STATE.md, config.json, ROADMAP.md; reports PASS/FAIL issues and optionally auto-fixes corruption.
Evaluates .claude/ directory token efficiency by scanning files, estimating tokens, categorizing load types, detecting issues like long CLAUDE.md or duplicates, and generating scored report.
Sets up Claude Code projects with config files and audits existing ones for permissions, context quality, MCP coverage, leaked secrets, stale docs, and cruft. Uses sub-agents for analysis.