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 event4u-app/agent-config --skill onboarding-programgit clone --depth 1 https://github.com/event4u-app/agent-configWrote 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/event4u-app/agent-config/onboarding-program)<a href="https://agentmods.dev/skills/event4u-app/agent-config/onboarding-program"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/onboarding-program/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/event4u-app/agent-config/onboarding-program"><img src="https://agentmods.dev/badge/skills/event4u-app/agent-config/onboarding-program.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 | $0.00047 | $0.02697 |
| Opus 5 | $0.00023 | $0.01349 |
| Sonnet 5 | $0.00009 | $0.00539 |
| Haiku 4.5 | $0.00005 | $0.00270 |
Grade A, and why
onboarding-program 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.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
onboarding-program
When to use
- A first onboarding program is needed because hires are arriving and ramping is ad-hoc, expensive, and slow.
- An existing program is producing inconsistent ramp times across roles or cohorts and the question is where the program leaks productivity.
- A new role family (first sales hire, first designer, first SRE) is being added and the question is what role-shaped onboarding looks like for this function.
Do NOT use as a customer-onboarding surface (route to Wing-3 onboarding-design (H11); this skill is internal-employee, that one is external-customer), as a performance-feedback skill (route to Q4 perf-feedback-craft), or for HRIS-onboarding-module configuration.
Cognition cluster
- Mental model 1 — First principles. Strip onboarding to: what does this person need to know, do, and decide alone before being net-positive? Most onboarding programs over-index on what's easy to teach (history, slides) and under-index on what's hard (decision rights, who-knows-what, codebase / domain context). See
mental-models.md§ 1. - Mental model 21 — Second-order thinking. Onboarding is paid for in mentor time. A 4-hour-per-week mentor commitment from a senior person costs more than people realise; mentor capacity is the binding constraint on hiring velocity. Read mentor cost as part of the program, not a free input.
- Mental model 28 — Inversion. "What would make this hire fail in their first 90 days?" Inversion surfaces the load-bearing risks (unclear scope, no early win, missing tools, no peer relationship). Most onboarding failures trace to one of these four, not to skill gaps.
- Mental model 26 — Optionality. A heavy template onboarding preserves consistency optionality but forecloses role-specific optionality. A pure free-form onboarding preserves customization but forecloses scalability. Pick the trade explicitly per role family.
- Context-spine — org-stage + product + customer-segment. Read org-stage for what's affordable (10-person co: founder onboards; 50-person co: managers + buddies; 150+: dedicated onboarding owner). Read product for domain complexity (deep regulated domain = longer ramp). Read customer-segment for which roles need customer-context immersion early.
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.
- 8d ago First seen · 166 lines · 47 tokens per session scan A f91b9987b696
onboarding-program is a skill published in the GitHub repository event4u-app/agent-config (10 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 2,697 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
cron
A scheduling tool for running tasks at a future time or repeating them on a set schedule. It manages scheduled jobs such as reminders, checks, and reports.
lov-rename-project
A project-renaming workflow that updates a product or repository name across source files, configuration, and documentation. It produces a reviewable plan and preserves compatibility-sensitive names and references where needed.
pm-arch
Skill "pm-arch" from wei63w/pm-manager, covering user input, outline, done when and shared workflow (all /pm- commands).
purpose-driven-leadership
Helps leaders connect their work and their teams' work to authentic meaning, rethink outdated notions of dedication, anchor in purpose over perception, and lead with integrity as a continuous practice. Use when experiencing career malaise or questioning professional direction, noticing disengagement on a team…