open-gsd/gsd-core

gsd-health

Diagnose planning directory health and optionally repair issues

First seen Jun 23, 2026

Installation

$ npx skills add open-gsd/gsd-core --skill gsd-health

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from open-gsd/gsd-core · top by installs.

npx skills add open-gsd/gsd-core

Browse all from open-gsd/gsd-core

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 9.2K
License LICENSE
Default branch next
Open issues 129
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsRead, Bash, Write, AskUserQuestion
Declared agents claude-code

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,236 B
  • docs SUMMARY.md 81 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 254 installs

SKILL.md

<objective> Validate .planning/ directory integrity and report actionable issues. Checks for missing files, invalid configurations, inconsistent state, and orphaned plans.

--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

</objective>

<executioncontext> @~/.claude/gsd-core/workflows/health.md </executioncontext>

<process> Execute end-to-end. Parse --repair and --context flags from arguments and pass to workflow. </process>