authoring-adept-agentslisted

# Authoring a good adept agent An agent is a single file `.adeptability/agents/<id>.md` (YAML frontmatter + a markdown body that becomes the agent's **entire system prompt**). `adept sync` renders it into every enabled harness that supports agents — Claude Code, OpenCode, Cursor, Copilot, and Codex — so write it **once, well, and harness-neutral**. ## Canonical agent format ```markdown --- id: pr-reviewer # ^[a-z0-9](?:[a-z0-9-]{0,48}[a-z0-9])?$ — matches the filename description: Adversarially reviews drafted changes. Use proactively before every commit. mode: subagent # subagent | primary | all (OpenCode; default subagent) tools: [Read, Grep, Bash] # allowlist; OMITTED = inherit every tool disallowed-tools: [Write] # denylist (Claude Code) model: inherit # verbatim pass-through; grammars differ per harness targets: [] # empty = every enabled harness harness: # per-harness knobs (permissionMode, readonly, sandbox_mode, …) cursor: { readonly: true } --- You are an adversarial reviewer. ... ``` `adept agent check <id>` runs a safety scan plus a best-practice lint over all of this — let it catch your mistakes. ## The description is the delegation trigger — write it like one Every harness decides *whether to hand work to your agent* from the description alone. - State **what it does AND when to invoke it**: *"Reviews Go changes for error-handling bugs. Use after editing i