{
  "schema_version": "1.0",
  "id": "archive:https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents",
  "slug": "effective-harnesses-for-long-running-agents-0xzfs05",
  "url": "https://feed7.dev/p/effective-harnesses-for-long-running-agents-0xzfs05",
  "title": "Effective harnesses for long-running agents",
  "why_included": "Anthropic's harness pattern for multi-session agents: an initializer sets up the env, a JSON feature list, and progress files; each session then ships one feature, verified end-to-end and committed to git.",
  "summary": "**The gist** Anthropic describes a harness for agents working across context windows on tasks spanning hours or days. A **two-agent split**: an initializer session creates an **init.sh**, a progress file, a first git commit, and a **JSON feature list** (200+ entries in their claude.ai-clone demo); later coding sessions each pick one feature, implement, test, and commit.",
  "practical_implication": "**Why it matters** The failure modes it targets — agents biting off whole features and exhausting context, or declaring a project done early — plague anyone running Claude Code or Codex on long builds. Concrete takeaways: **one feature per session**, JSON over Markdown for tracking files, a fixed startup ritual (read git log and progress, verify the app boots), and end-to-end browser testing via **Puppeteer MCP** rather than unit tests alone.",
  "agent_context": "**The gist** Anthropic describes a harness for agents working across context windows on tasks spanning hours or days. A **two-agent split**: an initializer session creates an **init.sh**, a progress file, a first git commit, and a **JSON feature list** (200+ entries in their claude.ai-clone demo); later coding sessions each pick one feature, implement, test, and commit.\n\n**Why it matters** The failure modes it targets — agents biting off whole features and exhausting context, or declaring a project done early — plague anyone running Claude Code or Codex on long builds. Concrete takeaways: **one feature per session**, JSON over Markdown for tracking files, a fixed startup ritual (read git log and progress, verify the app boots), and end-to-end browser testing via **Puppeteer MCP** rather than unit tests alone.\n\n**Watch out** The recipe is tuned to **full-stack web apps**; the authors say generalization to other domains is unexplored. Claude also can't see **browser-native alert modals** through Puppeteer, and whether one coding agent beats specialized multi-agent setups is an open question.",
  "source": {
    "name": "Anthropic",
    "url": "https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents",
    "published_at": null
  },
  "source_class": "blog_post",
  "content_type": "Engineering Post",
  "layer": "agent",
  "domains": [
    "coding"
  ],
  "topics": [
    "harness-engineering",
    "coding-agents",
    "agent-memory"
  ],
  "verification": {
    "status": "official_source",
    "label": "Official Source",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The recipe is tuned to **full-stack web apps**; the authors say generalization to other domains is unexplored. Claude also can't see **browser-native alert modals** through Puppeteer, and whether one coding agent beats specialized multi-agent setups is an open question."
  ],
  "lifecycle": "Current",
  "published_at": null,
  "modified_at": null,
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/effective-harnesses-for-long-running-agents-0xzfs05",
    "json": "https://feed7.dev/p/effective-harnesses-for-long-running-agents-0xzfs05.json",
    "markdown": "https://feed7.dev/p/effective-harnesses-for-long-running-agents-0xzfs05.md"
  }
}