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/dotfiles --skill course-developmentgit clone --depth 1 https://github.com/fmind/dotfilesWrote 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/dotfiles/course-development)<a href="https://agentmods.dev/skills/fmind/dotfiles/course-development"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/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/dotfiles/course-development"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/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 | $0.00028 | $0.00558 |
| Opus 5.5 | $0.00011 | $0.00223 |
| Sonnet 5.5 | $0.00006 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
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 1mo 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 — 37 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; use hugo for the site, fmind-visuals for slides, and quality-assurance for the test campaign.
Workflow
- Define the learner: State prerequisites, target capability, available time, delivery platform, and accessibility constraints. Remove content that does not advance the target capability.
- Write observable outcomes: Express what the learner will build, diagnose, explain, or decide. Give each module one primary outcome and a completion signal.
- Sequence the journey: Move from a minimal working example through guided practice to an independent lab. Introduce each concept immediately before it is used.
- Make examples executable: Pin dependencies, include expected commands and outputs, keep fixtures small, and run every code path in a clean environment. Never publish placeholder code or unverified APIs.
- Design practice and feedback: Give labs a concrete starting state, success criteria, likely failure modes, and recovery hints. Keep solutions separate enough that learners can attempt the work first.
- Check the human surface: Verify navigation, reading order, keyboard use, contrast, alt text, captions or transcripts, mobile layout, copy-paste behavior, and platform-specific constraints.
- Validate progressively: Test the changed example first, then its lesson, module, navigation, links, and the repository's full gate. Exercise both the instructor and fresh-learner paths.
- Prepare release acceptance: Record the exact candidate, supported platform, test evidence, known limitations, and rollback or correction path. Publishing remains a separate authorization.
Quality Bar
- Prefer one coherent learning path over a catalog of disconnected features.
- Teach the reason and trade-off before adding abstraction.
- Keep sample output deterministic and redact credentials, personal data, and paid-service responses.
- Distinguish local rendering, platform preview, and publicly released evidence.
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.
- 1mo ago First seen · 37 lines · 28 tokens per session scan A d24e1e493efe
course-development is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 558 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 2026-08-31.
Other skills, from other repositories
documentation-site
Build Zensical docs and course sites: navigation, API docs, Pages, MkDocs/Hugo migration.
course-development
Design technical courses, lessons, exercises, and executable labs.
google-developer
Find official Google developer docs and vendor skills (google/skills): Cloud, Ads, Analytics.
full-review
Full review: read every repo area, apply verified fixes, and prove all checks pass.
duckdb
Query and export CSV, Parquet, JSON, or SQLite data with DuckDB.
observability
Instrument Python services and agents: structlog logs, OpenTelemetry traces and metrics.