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 skills add ArdurAI/ardur-agent --skill onboard-new-engineergit clone --depth 1 https://github.com/ArdurAI/ardur-agentWrote 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.
[](https://agentmods.dev/skills/ardurai/ardur-agent/onboard-new-engineer)<a href="https://agentmods.dev/skills/ardurai/ardur-agent/onboard-new-engineer"><img src="https://agentmods.dev/badge/skills/ardurai/ardur-agent/onboard-new-engineer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ardurai/ardur-agent/onboard-new-engineer"><img src="https://agentmods.dev/badge/skills/ardurai/ardur-agent/onboard-new-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.01140 |
| Opus 5 | $0.00012 | $0.00570 |
| Sonnet 5 | $0.00005 | $0.00228 |
| Haiku 4.5 | $0.00002 | $0.00114 |
Grade A, and why
onboard-new-engineer 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 10d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding a new engineer
The goal of the first week is not to teach someone everything about the system — that takes months. It is to get them to their first merged change quickly, and to build the map and relationships they will fill in over time. An engineer who has shipped one small thing and knows who to ask is far more productive than one who has read documentation for five days.
This is a generic structure. It is meant to be customized per team — see
@./customize.md for the specific things you must fill in before handing it to a
new hire. A runbook with <placeholder> repo names is worse than none.
Before day one (the host's job)
The new engineer's time is wasted if the basics are not ready. Have these done before they start:
- Accounts and access provisioned: code host, CI, cloud console, observability, chat, ticketing, password manager.
- A named onboarding buddy assigned — one person whose explicit job is to answer "dumb" questions without the new hire feeling they are imposing.
- A starter task picked: a small, real, low-risk change with a clear definition of done. Not a toy; something that actually ships.
Day 1-2: orient and set up
The aim is a working environment and a mental map, not mastery.
- Read the right things, in order. Point at the few documents that give the most context per minute: the architecture overview, the "how we work" doc (branching, review, deploy), and the top-level README. Do not hand over a wiki and say "read everything" — curate three to five documents.
- Set up the dev environment end to end. Clone, build, run the app locally, run the test suite green. This is the highest-value early task: it forces contact with the real toolchain and surfaces setup gaps. Every place the setup docs are wrong, the new hire fixes them — their first contribution.
- Run the app and poke it. Use the product as a user. Trigger the main flows. Nothing builds intuition faster than seeing the thing work.
- Meet the buddy and agree on a check-in rhythm (a short daily sync for the first week works well).
What ships with it
1 file 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.
- 10d ago First seen · 100 lines · 24 tokens per session scan A a1e772bcf6ee
onboard-new-engineer is a skill published in the GitHub repository ArdurAI/ardur-agent (2 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 1,140 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
cli-operations
A guide for coordinating work through the Rovai command-line interface, including messages, group requests, lasting tasks and history lookup. Rovai is a system for communication and task coordination between agents.
oma-recap
Analyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate themed daily/period work summaries. Filter by date or time window.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
cron
A scheduler for tasks that should run automatically at a future time or repeat on a schedule. It uses cron expressions, a text format for describing times such as every day at 9:00.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.