{"slug": "agent-stdlib-a-standard-library-for-building-agents", "title": "Agent-stdlib: A standard library for building agents", "summary": "Anthropic released agent-stdlib, a standard library for building AI agents that packages Claude Code skills, MCP servers, and a tool-gating hook derived from its engineering blog. The library includes components for evaluation, sandboxing, multi-agent orchestration, and parallel autonomous agents, with most parts being model-agnostic and portable across platforms like OpenCode and Cursor.", "body_md": "A standard library for building agents.\n\nAnthropic's engineering blog documents how to build, evaluate, and run agents in production. Most of that knowledge never ships as something you can install; it stays prose you reopen when you hit the problem it solves. `agent-stdlib`\n\npackages the parts nobody else has: Claude Code skills, a few MCP servers, and a tool-gating hook.\n\nEach component names the article it comes from and says how it differs from any skill that already covers similar ground. The pack ships only what was missing. Topics that strong community skills already handle stay out, with pointers below.\n\n| Skill | What it gives you | Source article |\n|---|---|---|\n`build-agent-evals` |\nBuild automated evals for an agent: pick a grader, choose pass@k vs pass^k, run the zero-to-one roadmap |\n|\n\n`calibrate-eval-infrastructure`\n\n[Quantifying infrastructure noise in agentic coding evals](https://www.anthropic.com/engineering/infrastructure-noise)`coding-agent-scaffold`\n\n[Raising the bar on SWE-bench Verified](https://www.anthropic.com/engineering/swe-bench-sonnet)`durable-agent-architecture`\n\n[Scaling Managed Agents](https://www.anthropic.com/engineering/managed-agents)`sandboxing-agentic-systems`\n\n[How we contain Claude](https://www.anthropic.com/engineering/how-we-contain-claude)`using-the-think-step`\n\n[The \"think\" tool](https://www.anthropic.com/engineering/claude-think-tool)`multi-agent-orchestration`\n\n[How we built our multi-agent research system](https://www.anthropic.com/engineering/multi-agent-research-system)`parallel-autonomous-agents`\n\n[Building a C compiler with parallel Claudes](https://www.anthropic.com/engineering/building-c-compiler)Add the marketplace and install the plugin:\n\n```\n/plugin marketplace add pebeto/agent-stdlib\n/plugin install agent-stdlib@agent-stdlib\n```\n\nSkills trigger themselves when a task matches their description. You can also load one explicitly with the `Skill`\n\ntool.\n\nThree servers live under `mcp-servers/`\n\n, each paired with a skill. They need [ uv](https://docs.astral.sh/uv/), which installs each server's one dependency from the script header on first run.\n\n**think**(enabled). The no-op`think`\n\ntool, paired with`using-the-think-step`\n\n.**tool-gateway**(enabled).`search_tools`\n\nand`call_tool`\n\nover a larger catalog, so the agent reaches many tools through two. Paired with the tool-scaling guidance in`advanced-tool-use`\n\n.**code-execution**(opt-in). Presents tools as importable code and runs composed Python in a subprocess. It executes model-written code, so it is not enabled by default. Turn it on once you have wrapped it in real isolation; see`mcp-servers/code-execution/README.md`\n\nand the`sandboxing-agentic-systems`\n\nskill.\n\n`think`\n\nand `tool-gateway`\n\nare wired into the plugin's `.mcp.json`\n\n. To enable `code-execution`\n\n, point your client's MCP config at `uv run .../mcp-servers/code-execution/server.py`\n\n.\n\nruns the orchestrator-worker flow: it decomposes the question, dispatches`/research <question>`\n\n`research-worker`\n\nsubagents in parallel, and synthesizes a cited answer. Paired with`multi-agent-orchestration`\n\n.sets up lock-file coordination for unsupervised agents on one repo, using`/autonomous-loop`\n\n`scripts/locks.py`\n\nand`scripts/autonomy_loop.sh`\n\n. Paired with`parallel-autonomous-agents`\n\n.**action-gating** is a`PreToolUse`\n\nhook that tiers Bash commands by risk and denies or asks on the dangerous ones. It stays off until you set`AGENT_STDLIB_GATING=warn`\n\nor`enforce`\n\n, and it only ever adds friction. See`hooks/README.md`\n\n.\n\nMost of this pack is not Claude-specific. The MCP servers speak the open MCP protocol, the scripts are plain Python and Bash, and the skill content is harness-neutral procedural knowledge. To use it in OpenCode, Cursor, Cline, or a custom agent on any model, see [AGENTS.md](/pebeto/agent-stdlib/blob/main/AGENTS.md), which maps each component to its portable form.\n\nThese topics from the same blog have solid community skills, so they stay out of this pack. Reach for these instead:\n\n**Choosing an agent pattern**(prompt chaining, routing, orchestrator-workers):`markpitt/claude-skills`\n\n→`agent-patterns`\n\n**Context engineering**(compaction, note-taking, just-in-time retrieval):`muratcankoylan/agent-skills-for-context-engineering`\n\n**Designing agent or MCP tools**(consolidation, namespacing, token-efficient responses): the same pack's`tool-design`\n\n**Long-running build harness**(initializer + coding agent, git-tracked state):`eddiearc/long-running-harness`\n\n**GAN-style generator/evaluator harness**:`affaan-m/everything-claude-code`\n\n→`gan-style-harness`\n\n**Contextual retrieval RAG**: packaged versions exist on mcpmarket\n\nThis pack distills public writing on the Anthropic engineering blog. It is an independent project with no endorsement from Anthropic, and it ships no Anthropic code.\n\nSee [CONTRIBUTING.md](/pebeto/agent-stdlib/blob/main/CONTRIBUTING.md). Each skill stands alone in `skills/<name>/SKILL.md`\n\nand opens with the article it distills.\n\nMIT. See [LICENSE](/pebeto/agent-stdlib/blob/main/LICENSE).", "url": "https://wpnews.pro/news/agent-stdlib-a-standard-library-for-building-agents", "canonical_source": "https://github.com/pebeto/agent-stdlib", "published_at": "2026-06-16 16:44:39+00:00", "updated_at": "2026-06-16 16:52:37.282834+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-infrastructure", "developer-tools", "ai-research"], "entities": ["Anthropic", "Claude Code", "MCP", "OpenCode", "Cursor", "Cline", "Claude", "agent-stdlib"], "alternates": {"html": "https://wpnews.pro/news/agent-stdlib-a-standard-library-for-building-agents", "markdown": "https://wpnews.pro/news/agent-stdlib-a-standard-library-for-building-agents.md", "text": "https://wpnews.pro/news/agent-stdlib-a-standard-library-for-building-agents.txt", "jsonld": "https://wpnews.pro/news/agent-stdlib-a-standard-library-for-building-agents.jsonld"}}