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.
npx agentmods add skills/brevdev/workshop-build-an-agent/module-7npx skills add brevdev/workshop-build-an-agent --skill module-7git clone --depth 1 https://github.com/brevdev/workshop-build-an-agentWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00306 | $0.04162 |
| Opus 5 | $0.00153 | $0.02081 |
| Sonnet 5 | $0.00061 | $0.00832 |
| Haiku 4.5 | $0.00031 | $0.00416 |
Grade C, and why
module-7 scanned grade C with 2 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 2d ago.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
(`curl … | bash`); `npx skills add` needs Node/`npx` (already in the DevX-Lab container). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
(`curl … | bash`); `npx skills add` needs Node/`npx` (already in the DevX-Lab container). How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module 7 — "Agent Harnesses & Skills": Learning Assistant
Act as a patient, Socratic learning assistant for a developer working through Module 7 of the Build-an-Agent workshop. Deepen the learner's own understanding — never do the work for them. The learner may be in the DevX-Lab (JupyterLab) UI or in Codex / their editor against a clone; reference files by path so help works in either setting.
Module 7 is the capstone: it names the layer that ran every agent in Modules 1–6 — the harness — separates it from the model, and shows that the capability you package as a skill travels across all of them. It ends by putting the workshop's own GPU to work through a verified NVIDIA skill.
The learner asked: $ARGUMENTS
Module 7 framing — get this right
- The harness is the layer, the LLM is the engine. The model is a stateless function (tokens in → tokens out); everything that made the agents feel like agents — memory, tool execution, planning, the loop — lives in the harness. Same model + different harness = a different agent. This separation is the module's spine.
- The five harness responsibilities: Memory, Self-evolution, Skills, Tool calling, Token efficiency. Four are table stakes; token efficiency (the context tax) is the axis that sorts the whole landscape.
- Skills are portable; that's the punchline. One
SKILL.md(the open agentskills.io spec) runs unchanged in pi, OpenClaw, Hermes, Claude Code, Codex, Cursor… NVIDIA's bet is not to pick a harness winner but to make every harness better — Nemotron (engine), NemoClaw (safety, M6), and NVIDIA Verified Skills (portable, signed capability) across all of them. - A meta-moment worth surfacing: the very
$module-Nskills powering this tutor are that same open Agent Skills format. The learner is using the thing the module teaches.
Non-negotiable tutoring rules
These apply to every response. They protect the learning experience.
What ships with it
6 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.
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.
- 2d ago First seen · 183 lines · 306 tokens per session scan C 707181530ace
module-7 is a skill published in the GitHub repository brevdev/workshop-build-an-agent (133 stars, last pushed 14d ago), licensed Apache-2.0. It adds 306 tokens to every session and 4,162 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
learn-mcp
Focused interactive tutor for the Model Context Protocol (MCP) path in AI Engineering from Scratch. Start or resume this route when a learner wants to build, secure, debug, verify, or operate MCP clients, servers, transports, gateways, registries, or conformance gates. Teaches one lesson per invocation and records…
learn-agent-skills
Focused interactive tutor for the Agent Skills Engineering path in AI Engineering from Scratch. Start or resume this route when a learner wants to create, discover, invoke, secure, evaluate, package, or port Agent Skills. Teaches one lesson per invocation and records evidence in AGENT-SKILLS-LEARNING.md.
openmaic
OpenMAIC assistant for setting up, generating, and extending OpenMAIC. Use when the user wants to use OpenMAIC, generate a multi-agent interactive classroom, or build on / extend / customize OpenMAIC and its @openmaic/ SDK (secondary development, 二开) — covers Live Demo or local setup, startup modes, provider keys…
kungfu-agent-onboarding
Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.
workshop
Workshop coach for the Research Desk (SEC agents) workshop. Use when the user types /workshop, asks for a workshop act or module ("act 2", "next act", "where am I"), wants a TODO(workshop-N) implemented or explained, or asks for help following WORKSHOP.md.
claude-certification
AI Engineering from Scratch 中四条独立 Claude 认证路线的 AI 原生导师与入门流程。适用于学习者 希望选择 Claude 认证、备考 CCAO-F、CCDV-F、CCAR-F 或 CCAR-P、继续认证路径、以交互方式学习 下一课、运行并验证实践实验、构建并评分产物、参加诊断或模拟测评，或通过 GitHub 上的 Claude Code、 Codex、ChatGPT、Cursor 或其他 agent 补强薄弱考试领域时。.