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/distillgit clone --depth 1 https://github.com/Dragoon0x/canonWrote 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/commands/dragoon0x/canon/distill)<a href="https://agentmods.dev/commands/dragoon0x/canon/distill"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/distill.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 | $0.00040 | $0.00613 |
| Opus 5 | $0.00020 | $0.00307 |
| Sonnet 5 | $0.00008 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
distill 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 4d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/distill
The most underrated design move is subtraction.
Remove first, redesign second
For each screen, list everything on it. Ask of each element:
- What does this communicate? If the answer is vague, it doesn't belong.
- What happens if I remove it? If nothing, remove.
- What happens if I halve it? Try that before full removal.
- Is this serving the user or the stakeholder? Be honest.
Targets for removal
Visual noise
- Borders that whitespace could replace
- Shadows on elements that aren't actually elevated
- Dividers between sections that already have adequate spacing
- Backgrounds on cards that live on a neutral page
- Icon + text duplicates where one would do
Copy fat
- "Click here to..." (just link the relevant word)
- "Please" before every verb
- "In order to" (use "to")
- "At this time" (use "now" or delete)
- "Utilize" (use "use")
- "We are pleased to..." (delete the preamble)
- Empty microcopy that fills space without informing
Color promiscuity
- Multiple primary colors (pick one)
- Saturated accents on every card (reserve for the primary action)
- Distinct hues where lightness variation would work
Weight inflation
- Every label bold (reserve bold for emphasis)
- Uppercase + bold + color + large size on the same thing (pick one)
Interactive overload
- Multiple primary buttons competing (one per screen)
- Tooltips on everything (only on ambiguous elements)
- Animation on every state change (motion = meaning)
Consolidation targets
Count distinct values of each:
- Font sizes → should match modular scale (8–10 stops)
- Spacing values → should match scale (12–14 stops)
- Colors → should match token system (12–20 semantic)
- Border radii → 3–4 values max
- Shadow depths → 5 levels max
- Font weights per family → 4 max
- Typefaces → 3 max
Anything exceeding these counts is a candidate for consolidation.
Output
A reduction plan, ordered by impact:
- Single biggest subtraction — the one change that most improves the page by removal.
- Consolidation pass — which scales (color, spacing, type) collapse into fewer values, and the diff.
- Copy cut — words and phrases to delete, with replacements.
- Before / after — the page or component at the start vs. after the pass.
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.
- 4d ago First seen · 73 lines · 40 tokens per session scan A 491647e7a7ed
distill is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 613 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 2026-08-31.
Other commands, from other repositories
ui-audit
Comprehensive UI audit for accessibility, consistency, and usability.
theme
Switch between visual theme skins — OLED Black, Matrix, Claude Anthropic, Surprise Me.
a11y
You are a WCAG 2.1 Level AA accessibility specialist. You audit user interfaces for perceivable, operable, understandable, and robust compliance. You have zero tolerance for "we'll add a11y later" — accessibility is a launch requirement, not a polish step.
motion-designer
Use when animation feels wrong. Transitions too slow or too bouncy, motion with no purpose, blanket transitions on every property, no reduced-motion support, or animation that drops frames.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
extract-foundations-from-screens
Extract canonical foundations docs (foundations/color.md, foundations/typography.md, foundations/spacing.md, foundations/radii.md) from a batch of existing SCREENSPECs. Idempotent: re-runs only add new tokens, never overwrite existing role mappings, and route conflicts to a Review queue. Use when SCREENSPECs already…