course-development

course-development is a skill for Claude Code, Codex from fmind/dot. It costs 39 tokens per session (1,058 once invoked), scanned A, original, MIT.

A method for creating technical courses with lessons, exercises, prerequisites, accessible materials, and checks that show what learners can do.

In plain words
What is it for?
Write or revise courses, chapters, tutorials, and executable labs with structured pages, reference code, and completion exercises.
Why use it?
It turns technical information into guided practice with clear outcomes, so learners can follow the material and finish with usable skills.

Skill for Claude CodeCodex

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/fmind/dot/course-development
Any agent
npx skills add fmind/dot --skill course-development
Clone the repo
git clone --depth 1 https://github.com/fmind/dot

Made for: Claude Code, 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 course-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dot/course-development.svg)](https://agentmods.dev/skills/fmind/dot/course-development)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/course-development"><img src="https://agentmods.dev/badge/skills/fmind/dot/course-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,058 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 $0.00039 $0.01058
Opus 5 $0.00019 $0.00529
Sonnet 5 $0.00008 $0.00212
Haiku 4.5 $0.00004 $0.00106

Measured yesterday against content hash 45319fa17e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

course-development 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 yesterday.

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/course-development/SKILL.md · 41 lines

How it starts

The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Develop a Technical Course

Turn a technical subject into a course that learners can understand, execute, and finish. Own the learning contract: hugo owns the site stack, quality-assurance the test campaign, and playwright browser checks. A course repository's own AGENTS.md overrides this skill wherever they differ.

Workflow

  1. Define the learner: state prerequisites, target capability, available time, delivery platform, and accessibility constraints; cut content that does not advance the capability.
  2. Write observable outcomes: give each page one primary outcome and a completion signal; closing bullets state what the learner can now do, name, or predict, never attendance.
  3. Frame every page: follow page: front matter with an explicit lowercase slug (plus aliases for any previously served URL), an "In one glance" abstract (You will / You need / Time), H2s that name their teaching purpose, ## Your turn with the seven exercise fields, and ## What you can do now ending in a Continue to link.
  4. Mirror the source: quote code with {{< include path="<file>" region="<name>" lang="go" >}} over named regions of the shipped reference implementation; paste command output verbatim in text blocks, and derive every quoted count from a generated manifest (data/captures.yaml via mise run docs:captures in the reference course).
  5. Make labs executable: state a prediction before the exercise, then declare the Mode (inspect, temporary experiment with target-specific preflight and cleanup, or keep), a preflight command, ordered steps, the gate command that proves completion, and the final state; label offline, live-model, container, Kubernetes, cloud, destructive, and paid commands.
  6. Explain diagrams: follow every mermaid diagram with **Diagram in words:** prose; define terms at first use and put the reason beside each command.
  7. Check the human surface: verify navigation, reading order, keyboard use, contrast, alt text, mobile layout, and copy-paste on rendered pages with playwright, then run the course's accessibility gate (mise run check:accessibility in the reference course).
  8. Validate progressively: run the docs and link gates on the changed page first (mise run check:docs and mise run check:links), then the learner gate from a clean clone (mise run install, mise run doctor, mise run check:core, mise run test), then the definition of done in the course's AGENTS.md.
  9. Prepare release acceptance: record the exact candidate, supported platforms, test evidence, known limitations, and correction path, and report the highest proven rung of the proof ladder; publishing remains a separate authorization.

Read the full file on GitHub · 41 lines

Files

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.

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. yesterday First seen · 41 lines · 39 tokens per session scan A 45319fa17e89

Subscribe to this mod's changes

course-development is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,058 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 2026-09-03.