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 instructions/brevdev/workshop-build-an-agent/agents-mdgit 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 | $0.00832 | $0.00832 |
| Opus 5 | $0.00416 | $0.00416 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
workshop-build-an-agent AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents (Codex, Claude Code, …) working in this repository.
This is the Build-an-Agent workshop (a.k.a. DevX / DevX-Lab): a seven-module,
hands-on course that runs on NVIDIA AI Workbench. Learners work through Jupyter
notebooks under code/ and lessons under .devx/.
The workshop tutor (Agent Skills)
This repo ships its tutor as Agent Skills — the cross-harness SKILL.md format.
They auto-load when an agent runs from the project root and trigger by description, or can
be invoked explicitly. In Codex, invoke a skill with $name (e.g. $workshop); in
Claude Code use /name (e.g. /workshop):
$workshop— overview + router across the 7 modules$module-1…$module-7— one tutor per module$setup-workshop— local install helper$nvwb,$nvwb-project— NVIDIA AI Workbench CLI + in-container project awareness
(In Codex you can also run /skills to pick a skill from a menu. The /name slash form is
Claude Code only — typing /module-1 in Codex returns "unrecognized command".)
The skills exist in two parallel trees so either harness works identically:
.claude/skills/— read by Claude Code.agents/skills/— read by Codex (auto-discovered from<repo>/.agents/skills/)
When acting as the tutor (i.e. a learner invokes a $module-N or $workshop skill — /module-N in Claude Code),
follow the skill's own rules: guide, don't solve — give graduated hints, never
complete a learner's exercise, and never reveal or open answer-key files
(*answer*, answer_key/, *.answers/). The canonical tutoring policy lives in
.agents/skills/workshop/references/tutor-policy.md. These rules apply to tutoring
sessions only — they do not restrict normal development work on the repo itself.
Contributor convention: skills are a synced pair
.claude/skills/ is the canonical source. .agents/skills/ is generated from
it by .agents/sync-codex-skills.sh, which applies a small set of harness-specific
substitutions (invocation phrases like "run claude" → "run codex", and the path
.claude/skills/ → .agents/skills/) and preserves a few hand-authored Codex files
(see the HAND_AUTHORED list in that script and .agents/skills/VENDORED.md).
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 · 55 lines · 832 tokens per session scan A a77937a885d2
workshop-build-an-agent AGENTS.md is an instructions file published in the GitHub repository brevdev/workshop-build-an-agent (133 stars, last pushed 14d ago), licensed Apache-2.0. It adds 832 tokens to every session, about $0.0042 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.
Other instructions, from other repositories
ai-agents-for-beginners AGENTS.md
Instructions for microsoft/ai-agents-for-beginners, covering agents.md, project overview, setup commands, prerequisites and initial setup.
deep-agents-from-scratch CLAUDE.md
Instructions for langchain-ai/deep-agents-from-scratch, covering claude.md, project overview, development commands, environment setup and install dependencies using uv (preferred package manager).
building-a-coding-agent-from-scratch-course AGENTS.md
Instructions for decodingai-magazine/building-a-coding-agent-from-scratch-course, covering decode, project structure, tech stack, docs & external services and running commands.
claude-code-from-scratch CLAUDE.md
Instructions for Windy3f3f3f3f/claude-code-from-scratch, a project described as: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 5000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓.
agentic-ai-system-course AGENTS.md
Instructions for bryanyzhu/agentic-ai-system-course, covering claude.md — ai mentor's guideline, the design you are working inside, your role, the curriculum and reference systems: optional, triggered, not required.
MindTrain AGENTS.md
Instructions for shigella520/MindTrain, covering repository instructions, mindtrain target architecture, training and content integrity, safety and integrity and fast release workflow.