agent-context

agent-context is an Agent instruction files skill for AI agents, published by ThanakritAof in the agent-context-kit repository on GitHub. Skillspace rates agent-context C (71/100) and it passed the safety scan; the rating is based on static analysis only.

Initialize and maintain vendor-neutral repository context under docs/context, including project overview, durable topics, active work, checkpoints, rolling summaries, a backlog of things to do next, resumable handoffs across different agents (Claude Code, Codex, Antigravity), and archives. Use when setting up persistent AI context, starting or resuming non-trivial work, recording decisions or verification, switching agents, approaching context compaction, completing work, noting a backlog item, or when the user asks to initialize, save, checkpoint, summarize, restore, or resume project context.

Grade

C

Quality

71 / 100

Safety

Passed

GitHub stars

66

Unproven: rated by static analysis only, not yet compared head-to-head.

Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it looks like a template or a stub that was never filled in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.