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.
git 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/polish)<a href="https://agentmods.dev/commands/dragoon0x/canon/polish"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/polish/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/commands/dragoon0x/canon/polish"><img src="https://agentmods.dev/badge/commands/dragoon0x/canon/polish.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 | $0.00044 | $0.00702 |
| Opus 5.5 | $0.00018 | $0.00281 |
| Sonnet 5.5 | $0.00009 | $0.00140 |
| Haiku 4.5 | $0.00004 | $0.00070 |
Grade A, and why
polish 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polish
The 80/20 move for existing interfaces. Don't redesign. Refine.
Polish Pass (in order)
1. Typography refinement
- Tighten display headings:
letter-spacing: -0.02emon anything above 40px - Enable OpenType:
font-feature-settings: "kern", "liga", "calt"; font-variant-numeric: tabular-nums - Cap line length:
max-width: 65chon all prose - Check line-height inverse: larger text = tighter leading
2. Color tuning
- Replace every
#000withoklch(20% 0.02 <primaryHue>) - Replace every
#fffwithoklch(99% 0.005 <primaryHue>) - Tint all neutrals toward the primary hue (0.005–0.02 chroma)
- Check focus ring contrast against adjacent surfaces: must hit 3:1
3. Spacing snap
- Every margin/padding snaps to the 4px or 8px grid
- Consolidate duplicate values
- Section-to-section gap >= 2× heading-to-content gap (hierarchy)
4. Motion polish
- Replace CSS default
easewith tokenized--ease-outand--ease-in - Set durations from tokens:
--duration-fast: 150ms,--duration-normal: 250ms - Cap hover transitions at 200ms
- Exits faster than entrances by 20–30%
- Add
@media (prefers-reduced-motion: reduce)if missing
5. Interaction states
- Every interactive element has all 6 states defined
- Focus ring is 2–3px solid, 2px offset, hits 3:1 contrast
- Active state: 2% scale-down + 100ms transition
- Disabled: 50% opacity,
cursor: not-allowed,pointer-events: none
6. Depth refinement
- Replace single-layer shadows with multi-layer from the elevation token scale
- Shadow color tinted, not pure black
- Border-radius consolidated to a 3–4 step scale
- No belt-and-suspenders (don't combine border + shadow unless intentional)
7. Microcopy tune
- Every button label is a verb + object ("Save changes", not "Submit")
- Every error message is specific and actionable
- Replace "Click here" with descriptive link text
- Sentence case on buttons and headings (not Title Case)
8. Edge details
- Images have
width,height,loading,decodingattributes fetchpriority="high"on LCP image; noloading="lazy"on it- Fonts use
font-display: swap - Icons are 3:1 contrast if they carry meaning
- Skip link present and works
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 · 64 lines · 44 tokens per session scan A 98d9feb89c08
polish is a command published in the GitHub repository Dragoon0x/canon (6 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 702 once invoked, about $0.0002 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 commands, from other repositories
agentation-fix
Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.
scan-ai-tells
Scan UI or marketing copy for AI-default tells and content-authenticity misses — deletion list, not a redesign brief.
ccc-theme
List, preview or switch the Commander terminal color theme (Claude, OLED Black, Matrix, or a random palette) used by hooks and terminal art. Use when the user asks to change the theme, colors or skin.
extract-foundations-from-screens
Extract canonical foundations docs (color, typography, spacing, radii) from a batch of existing SCREENSPECs. Re-runs only add new tokens and route conflicts to a Review queue. Use when SCREENSPECs already document raw values and need converging into role tokens. Do not use when foundations are already curated and…
screen-spec
Generate a screen specification from a Figma frame using MCP tools (getdesigncontext, getscreenshot), matching the SCREENSPEC.md template (layout, states). Use when documenting a specific screen. Do not use when the screen has no Figma frame or the spec already exists, for 6 or more screens (use screen-spec-fleet), or…
design-critic
Use when you want an honest read on a design instead of encouragement. What is wrong, ranked by severity, with the reason attached. Works on a screenshot, a mockup, or a described screen.