Stats
Actions
Tags
From agent-harness-kit
Inspect context usage, token budget, compaction history, and overflow risk. Use when sessions get long, before large changes, after compaction, or when cost/context drift is suspected.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-harness-kit:context-healthThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Shows session context pressure using telemetry, compaction snapshots, and budget settings.
Shows session context pressure using telemetry, compaction snapshots, and budget settings.
/context-health
/context-health --last=7d
node .claude/skills/context-health/context-health.mjs --last=30d
.harness/config.json.contextManagementnpx claudepluginhub tuanle96/agent-harness-kit --plugin agent-harness-kitProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.