certification-program-builder

certification-program-builder is a skill for Codex from nthnclrk/enablement-skills. It costs 77 tokens per session (936 once invoked), scanned A, original, MIT.

A framework for creating job certifications based on observable work and required evidence. It defines what someone may do after passing and how assessors should make consistent pass or fail decisions.

In plain words
What is it for?
Use it to design practical assessments, assessor guides, scoring rules, retakes, and recertification for sales or other roles.
Why use it?
It replaces vague manager judgement or quiz-only checks with standards tied to real job tasks. It also helps different assessors evaluate the same work in the same way.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Install

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.

agentmods
npx agentmods add skills/nthnclrk/enablement-skills/certification-program-builder
Any agent
npx skills add nthnclrk/enablement-skills --skill certification-program-builder
Clone the repo
git clone --depth 1 https://github.com/nthnclrk/enablement-skills

Made for: Codex.

Wrote 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.

agentmods badge for certification-program-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/certification-program-builder.svg)](https://agentmods.dev/skills/nthnclrk/enablement-skills/certification-program-builder)
Your own site
<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>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 936 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 6d ago against content hash 4617c64c1d94, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

skills/certification-program-builder/SKILL.md · 80 lines

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:

  1. Role, critical tasks, and the failures this gate must catch
  2. What the result will control, and who owns the job standard
  3. Authentic evidence already available, plus examples of ready and not-ready work
  4. Assessor group, cohort size, and evaluation capacity
  5. 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

  1. 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.
  2. Derive 4-6 dimensions from the job and its failure risks. Not from training modules.
  3. Define authentic evidence for each dimension. Type, minimum quantity, allowed support, critical errors. Done when a quiz cannot substitute for the work.
  4. Write behavior anchors and practical prompts. Dimension-specific 1 through 4. Generic labels are not a rubric.
  5. Set the standard at minimally competent independent performance. Overall threshold, critical-dimension minimums, non-compensable hard fails. Mark it provisional until the owner and a pilot support it.
  6. Pilot on ready, borderline, and not-ready samples. If known-ready people fail, fix the task or the anchors before moving the number.
  7. Calibrate assessors. Independent benchmark scoring, variance review, rescore gate. Do not go live while hard-fail calls still disagree.
  8. Test delivery capacity. Demand, assessor time, moderation, accommodations, retakes. Return fits, reduce, sequence, or blocked.
  9. Write decision, appeal, retake, accommodation, recertification, and version rules.
  10. Ship the pack with owner, version, validation status, and the delivery decision.

Read the full file on GitHub · 80 lines

Files

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.

Changes

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.

  1. 6d ago First seen · 80 lines · 77 tokens per session scan A 4617c64c1d94

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories