← ClaudeAtlas

subagent-engineeringlisted

Design and maintain Claude Code subagents: the delegation decision, the frontmatter that governs a run, and the system prompt the agent wakes up with.
xobotyi/cc-foundry · ★ 23 · AI & Automation · score 84
Install: claude install-skill xobotyi/cc-foundry
**A subagent is a separate context with its own system prompt.** It inherits none of the caller's conversation, and everything it reads is discarded when it stops — only what it returns survives. Isolation is the reason to pay for one, and the return value is the entire product. <prerequisite> A subagent definition is a system prompt. Invoke `prompt-engineering` for the wording, instruction budget, and timelessness rules that govern every line written here. This skill covers only what is specific to the subagent artifact — the delegation decision, the frontmatter, and the prompt the agent wakes up with. </prerequisite> ## Delegate only where the isolation pays - **Delegate work whose output is far larger than its conclusion** — a wide search, a long file, a verbose test run. The caller pays for the summary instead of the transcript. - **Delegate to restrict, too.** A tool allowlist or a cheaper model binds the whole run, which no instruction inside the main conversation achieves. - **Keep the work in the main conversation when it needs back-and-forth**, when several phases share the same context, or when the change is small and targeted. A subagent starts cold: it pays in startup latency and in rediscovering what the caller already knows. - **Write a skill instead when the artifact wanted is reusable instruction text** that runs in the caller's own context. A skill carries procedure; a subagent carries a context boundary. - **A subagent runs its own system prompt