context-engineering

Agent Skills is an open standard for packaging reusable agent capabilities (instructions + resources) in a folder that tools can discover and load on demand. The format was originally developed by Anthropic and released publicly as an open specification in October 2025 (announcement, engineering blog). Treat the spec as actively evolving: implementations and best practices may change as more clients adopt it. Canonical definition: A simple, open format for giving agents new capabilities and expertise. ...

An agentic harness is the wrapper around an LLM that turns it into an agent by running it in a loop, giving it tools, and managing state. Working Definition Agentic harness = controller loop + tool runtime + context/state management + guardrails + (optional) evaluation. In practice, the harness is the part that: Calls the model repeatedly (plan -> act -> observe -> update -> repeat) Executes tools (shell, files, web, APIs, repo ops) on the model’s behalf Manages context (what to include, summarize, persist, retrieve) Enforces constraints (step limits, timeouts, budgets, sandboxing, policy checks) Optionally adds evaluation (tests, graders, benchmarks, self-checks) Two Common Meanings Runtime harness - used to build/operate real agents (coding agents, research agents, ops agents). Evaluation harness - used to run task suites and measure performance across models/variants. Why It Matters Most “agent capability” comes from the harness: ...