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 commands/dragoon0x/canon/teachgit clone --depth 1 https://github.com/Dragoon0x/canonWhat 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 | $0.00018 | $0.00345 |
| Opus 5 | $0.00009 | $0.00172 |
| Sonnet 5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
teach 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 3d 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.
What it actually says
/teach
Explain why a design rule exists. Not "here's the rule" — "here's the rule, here's what breaks without it, here's the source."
What this does
- Identify the rule the user is asking about (e.g., "why 4.5:1 contrast", "why ease-out for entrances", "why labels above inputs").
- Find the relevant CANON skill.
- Structure the explanation in four parts:
- The rule: stated plainly, one sentence.
- The why: the underlying perceptual, cognitive, or accessibility reason.
- The evidence: citation to the source (WCAG SC, Material 3 spec, HIG section, Refactoring UI chapter, research paper).
- The failure mode: what happens to real users when the rule is broken.
- Include a before/after code example.
- Include a one-sentence mnemonic when possible.
Format
Rule: [one sentence]
Why: [2–3 sentences of reasoning]
Evidence: [source with link or citation]
Failure mode: [who gets hurt, how]
Before:
[bad code or mockup]
After:
[good code]
Remember: [mnemonic]
Example invocation
"Teach me why line-height should decrease as font size increases."
Success criteria
The reader walks away able to:
- State the rule.
- Explain the rule to someone else.
- Recognize violations in the wild.
- Point at the source without checking.
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.
- 3d ago First seen · 53 lines · 18 tokens per session scan A 232de2f39662
teach is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 345 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
eli5
Say the last answer again in plain words — same facts, in the order the operator needs them. Optional topic argument.
frappe-lms
Treat the task as Frappe LMS work.
dotnet-teach
One-time setup that scans a .NET backend project, learns its conventions and architecture, and writes them to CLAUDE.md for future sessions.
code-explainer
Use when a designer needs to understand code that already works. What a file does, what a line means, which parts are safe to change. Plain language with Figma analogies, no developer jargon.
setup-guide
Use when someone is starting from nothing and the terminal is unfamiliar. Installing Node and Claude Code, creating a first project, and what to do when a command fails.