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 nthnclrk/enablement-skills --skill onboarding-program-buildergit clone --depth 1 https://github.com/nthnclrk/enablement-skillsWrote 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/nthnclrk/enablement-skills/onboarding-program-builder)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/onboarding-program-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/onboarding-program-builder/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/nthnclrk/enablement-skills/onboarding-program-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/onboarding-program-builder.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 | $0.00085 | $0.01012 |
| Opus 5.5 | $0.00034 | $0.00405 |
| Sonnet 5.5 | $0.00017 | $0.00202 |
| Haiku 4.5 | $0.00009 | $0.00101 |
Grade A, and why
onboarding-program-builder 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 24d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboarding program builder
Help new hires learn, practise, and demonstrate the work their role requires, with support matched to their starting proficiency.
Onboarding teaches the job and collects diagnostic evidence. A pass/fail gate is certification-program-builder. A customer time-to-value journey is onboarding-to-value-playbook.
Performance checkpoint. "Before independent discovery, observe a live call: the rep clarifies the buyer's problem and its impact, then agrees a useful next step. If no live opportunity is available, continue practice and leave the checkpoint pending."
Calendar. "Days 1-30: complete product training. Days 31-60: shadow. Days 61-90: carry a full pipeline."
Each phase should give the hire a useful work task and the manager a clear way to judge what support is needed.
Inputs
Reuse supplied context first. If a missing company fact would change the result, check the relevant sections of .enablement/context.md when available. Preserve source dates and approval limits.
Ask only for the inputs that change the plan:
- Role, segment, and experience mix: new hire, internal transfer, experienced external
- Job-critical tasks, expected outcomes, and costly failure risks
- Target time to supervised and independent work
- Starting-proficiency evidence, if any exists
- Learner, facilitator, SME, and manager capacity
- Whether a formal certification exists that onboarding should prepare for, not score
Keep role standards, ramp targets, and capacity unknown until verified. Missing baseline is unknown ability, not low ability.
Supporting material
Read references/onboarding-framework.md for phase gates, evidence checkpoints, and the certification boundary. Skip it if the user already has competencies and only wants a focused checkpoint revision.
Procedure
- Start from the job, not the catalog. Critical tasks, outcomes, failure risks. Done when each competency is a thing someone does at work.
- Take a short starting baseline. Knowledge check, work sample, roleplay, or observed task. Use it to compress or add support by profile.
- Gate phases on evidence, not dates. Foundation, supervised application, independent execution. Add a 30-60-90 view only when asked or useful. Dates do not prove progression.
- Map each competency to practice, live-work evidence, and a manager check. Done when this week's proof is observable without a quiz score.
- Space learning, practice, application, and review across realistic work opportunities. Use feedback and retries before increasing difficulty or independence. Where live work is unavailable, use a representative simulation and state which evidence still needs to come from live work.
- Build a capacity ledger first.
Learners, facilitators, SMEs, managers, systems, timezones. Return
fits,reduce,sequence, orblockedbefore assigning work that overflows. - Give managers checks they can actually run. Lightweight, scheduled inside available coaching time.
- Name ramp-risk triggers and the evidence that returns someone to the path.
- If a certification exists, show where onboarding gathers evidence for it.
Leave the standard and the decision to
certification-program-builder.
What ships with it
2 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.
- 24d ago Changed · +2 lines b1337df69c7f
- 2mo ago First seen · 80 lines · 85 tokens per session scan A 95939509397a
onboarding-program-builder is a skill published in the GitHub repository nthnclrk/enablement-skills (16 stars, last pushed 25d ago), licensed MIT. It adds 85 tokens to every session and 1,012 once invoked, about $0.0003 per session on Opus 5.5. 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.
onboarding-program-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onboarding-program-buildernthnclrk/enablement-skills | Skill | 16 | 25d ago | MIT | A | 85 | Codex |
| hr-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| book-mirrorgarrytan/gbrain | Skill | 32k | yesterday | MIT | A | 138 | Claude Code |
| exam-forecastanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 73 | Claude Code |
| lean-formalizewanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 81 | Claude Code |
| eli5companion-inc/feynman | Skill | 10k | 6d ago | MIT | A | 63 | Claude Code, Codex |
| deck-course-modulenexu-io/html-anything | Skill | 9.4k | 25d ago | Apache-2.0 | A | 25 | Claude Code, Codex |