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/fmind/dot/course-developmentnpx skills add fmind/dot --skill course-developmentgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/course-development)<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>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 | $0.00039 | $0.01058 |
| Opus 5 | $0.00019 | $0.00529 |
| Sonnet 5 | $0.00008 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
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.
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
- Define the learner: state prerequisites, target capability, available time, delivery platform, and accessibility constraints; cut content that does not advance the capability.
- 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.
- Frame every page: follow page: front matter with an explicit lowercase
slug(plusaliasesfor any previously served URL), an "In one glance" abstract (You will / You need / Time), H2s that name their teaching purpose,## Your turnwith the seven exercise fields, and## What you can do nowending in aContinue tolink. - 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 intextblocks, and derive every quoted count from a generated manifest (data/captures.yamlviamise run docs:capturesin the reference course). - Make labs executable: state a prediction before the exercise, then declare the Mode (
inspect,temporary experimentwith target-specific preflight and cleanup, orkeep), 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. - Explain diagrams: follow every mermaid diagram with
**Diagram in words:**prose; define terms at first use and put the reason beside each command. - 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:accessibilityin the reference course). - Validate progressively: run the docs and link gates on the changed page first (
mise run check:docsandmise 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'sAGENTS.md. - 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.
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.
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.
- yesterday First seen · 41 lines · 39 tokens per session scan A 45319fa17e89
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.
Other skills, from other repositories
course-development
Design executable technical curricula, lessons, and labs with prerequisites, guided practice, accessibility, platform checks, and course release acceptance.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.