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/nthnclrk/enablement-skills/certification-program-buildernpx skills add nthnclrk/enablement-skills --skill certification-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/certification-program-builder)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/certification-program-builder"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/certification-program-builder.svg" alt="Measured on agentmods" 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 | $0.00077 | $0.00936 |
| Opus 5 | $0.00039 | $0.00468 |
| Sonnet 5 | $0.00015 | $0.00187 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
certification-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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Certification program builder
Build an observable gate. If a quiz score or a manager vibe could pass someone, rewrite it.
Certification states what a person may do after they pass, and what evidence proves it. The ramp that prepares them is onboarding-program-builder. A practice drill may supply a scenario; it does not set the decision.
Observable gate. "Certified AE may run first-call discovery unsupervised. Pass: independently gets problem, cost, and a mutual next step. Hard fail: invents a customer result."
Quiz. "80% on the product quiz plus manager sign-off."
If two assessors cannot score the same evidence the same way, you do not have a standard yet.
Confirm Inputs First
Ask only for the inputs that change the standard:
- Role, critical tasks, and the failures this gate must catch
- What the result will control, and who owns the job standard
- Authentic evidence already available, plus examples of ready and not-ready work
- Assessor group, cohort size, and evaluation capacity
- Accommodation, retake, and recertification constraints
Do not invent a pass mark from convenience. Course completion, tenure, confidence, and manager familiarity are not readiness evidence.
Read The Right Reference
Read references/certification-scoring-rules.md for anchors, hard fails, and calibration. Skip it if the user already has a governed rubric and only wants retake or recertification rules.
Default Workflow
- Write the readiness claim. What they may do, in which situations, with what independence. Done when a manager can use that sentence to grant or withhold work.
- Derive 4-6 dimensions from the job and its failure risks. Not from training modules.
- Define authentic evidence for each dimension. Type, minimum quantity, allowed support, critical errors. Done when a quiz cannot substitute for the work.
- Write behavior anchors and practical prompts.
Dimension-specific
1through4. Generic labels are not a rubric. - Set the standard at minimally competent independent performance.
Overall threshold, critical-dimension minimums, non-compensable hard fails. Mark it
provisionaluntil the owner and a pilot support it. - Pilot on ready, borderline, and not-ready samples. If known-ready people fail, fix the task or the anchors before moving the number.
- Calibrate assessors. Independent benchmark scoring, variance review, rescore gate. Do not go live while hard-fail calls still disagree.
- Test delivery capacity.
Demand, assessor time, moderation, accommodations, retakes. Return
fits,reduce,sequence, orblocked. - Write decision, appeal, retake, accommodation, recertification, and version rules.
- Ship the pack with owner, version, validation status, and the delivery decision.
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.
- 6d ago First seen · 80 lines · 77 tokens per session scan A 4617c64c1d94
certification-program-builder is a skill published in the GitHub repository nthnclrk/enablement-skills (13 stars, last pushed 16d ago), licensed MIT. It adds 77 tokens to every session and 936 once invoked, about $0.0004 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
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.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
ark-documentation
Guidance for structuring Ark documentation using the Diataxis framework. Use this skill when creating new docs, deciding where content belongs, reviewing documentation PRs, or restructuring existing documentation.