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/extractgit 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 | $0.00020 | $0.00476 |
| Opus 5 | $0.00010 | $0.00238 |
| Sonnet 5 | $0.00004 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
extract 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 2d 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
/extract
Walk a codebase, find every color, spacing, font, radius, and shadow value, and consolidate them into a single token layer.
What this does
- Scan the codebase (CSS, Tailwind configs, theme files, inline styles).
- Categorize findings:
- Colors: hex, rgb, hsl, oklch. Group by perceptual similarity.
- Spacing: every margin, padding, gap. Map to nearest 4px/8px grid value.
- Typography: font-size, line-height, font-weight, letter-spacing. Map to the nearest modular-scale step.
- Radii: border-radius values.
- Shadows: box-shadow strings.
- Timing: transition durations and easings.
- Detect inconsistencies:
- "We have 7 grays that are perceptually the same" → collapse to 1.
- "Spacing includes 10px, 11px, 13px, 15px — none on the grid" → snap to nearest.
- "5 shades of blue used as 'primary'" → pick canonical, flag rest.
- Apply
canon-color,canon-typography,canon-spatialas the normalization target. - Build the token file in three layers:
- Primitive: raw scale (
--blue-500,--space-4). - Semantic: intent (
--color-brand-primary,--gap-card). - Component: contextual (
--button-primary-bg).
- Primitive: raw scale (
- Output a migration plan: old value → new token, per file.
Output
- Token file (
tokens.cssortokens.js). - Consolidation report: X colors → Y tokens, with rationale.
- Migration map: file-by-file search/replace list.
- Inconsistencies flagged (spacing off-grid, contrast failures introduced).
Success criteria
Every raw value in the codebase either becomes a token or is flagged as off-system. Token count drops significantly (typical result: 40–70% reduction). Nothing visually breaks.
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.
- 2d ago First seen · 41 lines · 20 tokens per session scan A ae061de2a73f
extract is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 476 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
apply-design-md
Consume the project's design contract — a .design file or DESIGN.md — and thread its tokens through UI code (CSS, Tailwind, or design-system components).
agentation-fix
Session-2 fix loop for Agentation — read structured annotations from the dev overlay and apply targeted UI fixes.
motion-audit
Audit animation timing, easing, springs, and transitions — decide first whether motion should exist, then apply the motion cluster.
scan-ai-tells
Scan UI or marketing copy for AI-default tells and content-authenticity misses — deletion list, not a redesign brief.
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.
off
Disable Audio Recap for this Claude Code session.