building-agents

building-agents is a skill for Claude Code, Codex from ericrisco/rsc-harness. It costs 85 tokens per session (4,898 once invoked), scanned A, original, MIT.

A guide for building AI agents that can call tools, retrieve information, return structured results, and be evaluated and traced. It keeps the application code independent of a particular AI model provider.

In plain words
What is it for?
Use it when creating provider adapters, agent loops, tool schemas, retrieval-augmented generation, evaluation checks, cost routing, tracing, or an MCP server.
Why use it?
It reduces rewrites when changing providers and gives the agent a consistent structure for tool use, retrieval, testing, and monitoring.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it when creating provider adapters, agent loops, tool schemas, retrieval-augmented generation, evaluation checks, cost routing, tracing, or an MCP server.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ericrisco/rsc-harness/building-agents
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ericrisco/rsc-harness --skill building-agents
Clone the repo
git clone --depth 1 https://github.com/ericrisco/rsc-harness

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for building-agents

README.md
[![agentmods](https://agentmods.dev/badge/skills/ericrisco/rsc-harness/building-agents.svg)](https://agentmods.dev/skills/ericrisco/rsc-harness/building-agents)
Your own site
<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/building-agents"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/building-agents.svg" alt="Measured on agentmods" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,898 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00085 $0.04898
Opus 5 $0.00043 $0.02449
Sonnet 5 $0.00017 $0.00980
Haiku 4.5 $0.00009 $0.00490

Measured 8d ago against content hash 5ec1322e94e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

building-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/verify.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/building-agents/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Building production LLM agents (model-agnostic)

A thin provider adapter, a disciplined agent loop, schema-validated tools, provider-neutral RAG, eval gates, OTel tracing, and optionally an MCP server — so swapping OpenAI ↔ Anthropic ↔ Gemini ↔ OSS is a config change, not a rewrite.

The one rule

Program against a capability interface, never a vendor SDK. Vendor specifics (model id, tool-schema shape, JSON mode, caching, token limits) live behind one adapter resolved from config. Model names and prices rot — if one appears in business logic it's a bug, and re-verify the dated tables before quoting a number.

Hand off instead when: a new non-trivial feature has no approved spec + plan under 02-DOCS/wiki/sdd/ → stop and run specify first (method: sdd), which routes back here once the plan is approved; one-line/low-risk changes go straight through. Anthropic-SDK internals (caching, thinking, batch) in a file that only imports anthropicclaude-api if your environment has it, since this skill stays multi-provider. Workspace scaffolding → harness. Choosing which coding agent to use → agent-eval territory. Pure prompt-wording tuning with no architecture change → prompt engineering, not this. A one-shot throwaway prompt, or no retrieval/tools/loop/evals at all → you don't need an agent; call the SDK directly and say so.

Decision rules (read before writing code)

  1. Adapter first — define the LLMProvider Protocol before any provider call.
  2. Smallest loop that works — single-agent before multi-agent; ReAct only when the path is uncertain; plan-execute when steps are knowable. Multi-agent means orchestrator-worker with a semaphore-bounded parallel fan-out, never a free-for-all.
  3. Tools are typed contracts — schema + validation + idempotency key on every side-effecting tool; no catch-all tools.
  4. Retrieve, don't stuff — RAG when ground truth lives in data; cite or refuse.
  5. Eval before ship — a golden set + regression gate in CI, or it's not production.
  6. Cheapest model that passes the eval — route/cascade up, never default to flagship.

Read the full file on GitHub · 387 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 387 lines · 85 tokens per session scan A 5ec1322e94e3

Subscribe to this mod's changes

building-agents is a skill published in the GitHub repository ericrisco/rsc-harness (70 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 4,898 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…

raphaelmansuy/edgecrab · 63 tokens

qdrant

Manage Qdrant vector database via REST API. Use when the user asks to create or delete collections, upsert or search vectors, inspect points, filter by payload fields, manage snapshots, check cluster status, or debug semantic search issues. Covers collection CRUD, point upsert/search/scroll/count, payload indexes…

bug-ops/zeph · 88 tokens

attach-receipts

Attaches sourcedoc/extractionrunid/schemaversion receipts to every edge at write time, and refuses to write any edge missing one of the three.

ayeshakhalid192007-dev/graph-engineering-crash-course · 34 tokens

Vector Databases

Guides retrieval-store design, indexing, and query behavior for embedding-backed systems without confusing storage with application truth.

agentic-in/elephant-agent · 26 tokens

qdrant-vector-search

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

raphaelmansuy/edgecrab · 46 tokens

pinecone

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.

raphaelmansuy/edgecrab · 63 tokens