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/workshopnpx skills add brevdev/workshop-build-an-agent --skill workshopgit 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 | $0.00180 | $0.01477 |
| Opus 5 | $0.00090 | $0.00739 |
| Sonnet 5 | $0.00036 | $0.00295 |
| Haiku 4.5 | $0.00018 | $0.00148 |
Grade A, and why
workshop 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 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.
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.
This is a copy
86% identical to video-copy-analyzer — 410 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build-an-Agent Workshop — Guide & Router
The entry point and map for the Build-an-Agent workshop. Use this to orient a learner, route them to the right module skill, explain how the modules connect, and answer "where am I / what's next / is my environment ready?" — without doing their work for them.
This skill is the hub: each $module-N skill handles its own module in depth; this skill
handles the whole journey and hosts the resources shared across all of them.
Invoking the tutor: the learner reaches these skills by running codex (in a DevX-Lab
JupyterLab terminal, or against a local clone) and typing $workshop for this overview or
$module-N (1–7) for a specific module (or run /skills to pick one from a menu); setup is in the README's Learn with an AI tutor
section. Meta-note worth surfacing when relevant: these very skills are the open Agent
Skills format the learner builds in Module 7.
The learner asked: $ARGUMENTS
The seven-module arc
Each module adds a capability and a matching discipline. Detailed version in references/map.md.
| # | Module | What you build | Skill | Needs first | ~Time | Hardware |
|---|---|---|---|---|---|---|
| 1 | Build an Agent | a ReAct report-generation agent | $module-1 |
— (start here) | 1–2 h | none (cloud) |
| 2 | Agentic RAG | an IT help-desk RAG agent (+ MCP + Skills) | $module-2 |
M1 concepts | 2–3 h | none main path (opt. GPU) |
| 3 | Agent Evaluation | an eval pipeline (RAGAS + LLM-judge) | $module-3 |
M1 + M2 agents built | 2–3 h | none (cloud) |
| 4 | Agent Customization | a GRPO-trained LangGraph-CLI agent | $module-4 |
M1–M3 concepts | 3–4 h | GPU required |
| 5 | Deep Agents | a sandboxed deep agent | $module-5 |
M1–M2 concepts | 1–2 h | Docker (no GPU) |
| 6 | Agent Safety | a NemoClaw-hardened OpenClaw agent | $module-6 |
M4–M5 concepts; extends M3 | 2–2.5 h | Docker + kernel ≥ 5.13 |
| 7 | Harnesses & Skills | a pi-style harness + portable skills | $module-7 |
M1–M6 | 2–3 h | none main; opt. GPU (Ex4) |
What ships with it
5 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 · 71 lines · 180 tokens per session scan A bcbc2ebb3d8f
workshop 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 180 tokens to every session and 1,477 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to video-copy-analyzer, differing in 410 lines, and is treated as a copy.
Other skills, from other repositories
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
pedagogy-review
Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…