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 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/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/fmind/dot/course-development"><img src="https://agentmods.dev/badge/skills/fmind/dot/course-development.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 | $0.00015 | $0.00646 |
| Opus 5.5 | $0.00006 | $0.00258 |
| Sonnet 5.5 | $0.00003 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00065 |
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 12d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop a Technical Course
Build a course learners can understand, execute, and finish. Use documentation-site as the default course publisher; an existing course repository owns its platform, page schema, and task names. Use quality-assurance for a broader test campaign.
Workflow
- Define the learner: prerequisites, target capability, time, delivery format, and accessibility needs; keep only content that advances the outcome.
- Make outcomes observable: give each lesson a primary capability and a completion signal; introduce terms before using them.
- Ground examples: derive code and counts from shipped source or generated evidence; explain the reason beside a command and distinguish captured output from illustration.
- Record terminal examples when useful: follow the VHS workflow for reproducible demos with synthetic inputs; retain the command transcript and a static equivalent for accessibility.
- Make practice executable: state the goal, starting state, a prediction, ordered work, verification, and what remains afterward; label temporary changes and external access/cost.
- Validate progressively: run the changed lesson's checks and examples, then the repository's learner gate from a clean environment; record unexercised platforms or live services.
- Prepare acceptance: connect outcomes to evidence, known limitations, and a correction path; publication follows the user's authorized scope.
Optional Reference Profile
Read reference-course.md only for a course that adopts the conventions, exercise fields, and task names of the reference course (~/mlops-courses/agentops-open-course, whose AGENTS.md owns the page frame, gates, and authoring rules). Otherwise use the course's own authoring contract.
Gotchas
- Define prerequisites by state: state the required machine or knowledge state, not merely a previous chapter number.
- Never break published routes: preserve URLs or provide tested redirects/aliases when changing them.
- Prefer local exercises: use meaningful local work by default; live models, cloud resources, and destructive cleanup need their declared authority and limits.
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.
- 12d ago Changed · -2 lines 0559f6c830ca
- 14d ago Changed 3fe424ac0887
- 15d ago Changed · -1 lines · -3 tokens per session e625af272d66
- 17d ago Changed 8371e737e38b
- 29d ago Changed d7f02ef3f3e8
- 1mo ago Changed · +1 lines · -21 tokens per session 4c4d1e6b4f2e
- 1mo ago Changed · +1 lines 78b480ed9c0e
- 1mo ago Changed d3ba6eadecdc
- 1mo ago First seen · 41 lines · 39 tokens per session scan A 45319fa17e89
course-development is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 646 once invoked, about $0.0001 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 2026-09-03.
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.
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
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.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.