audit

A command for checking an interface against a broad set of design rules. It reviews visual design, interaction, accessibility, forms, responsive layouts, performance, interface states, and wording, then groups problems by severity.

In plain words
What is it for?
Use it to audit a page or codebase, find design and usability violations, and organise fixes by urgency.
Why use it?
It gives developers one structured review instead of requiring separate checks for each part of an interface.

Command

Install

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.

agentmods
npx agentmods add commands/dragoon0x/canon/audit
Clone the repo
git clone --depth 1 https://github.com/Dragoon0x/canon
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 707 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00707
Opus 5 $0.00025 $0.00353
Sonnet 5 $0.00010 $0.00141
Haiku 4.5 $0.00005 $0.00071

Measured 2d ago against content hash ae9a7a084d74, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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.

source/commands/audit.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit

Perform a full CANON audit of the current codebase or selection.

Process

Work through each CANON skill in order. For each, apply its Audit Checklist against the current interface. Record violations.

  1. canon-typography → font count, size scale, line-height, line length, Inter usage
  2. canon-color → contrast ratios, pure black/white, gray-on-color, token system
  3. canon-spatial → off-grid values, spacing scale count, touch targets
  4. canon-motiontransition: all, hardcoded durations, prefers-reduced-motion, banned easings
  5. canon-interaction → focus rings, hover treatment, disabled states, tap targets
  6. canon-responsive → mobile-first, container widths, fluid type, hover-wrapped
  7. canon-accessibility → semantic HTML, ARIA usage, keyboard, contrast, skip link
  8. canon-forms → labels, input types, autocomplete, validation timing, error specificity
  9. canon-depth → shadow construction, elevation tokens, z-index scale, border radius
  10. canon-states → 4 required states per screen, skeletons, error recovery
  11. canon-performance → LCP, INP, CLS, bundle size, image optimization
  12. canon-ux-writing → button labels, error messages, empty states, tone consistency

Output

Group findings by severity:

Critical (ship-blockers)

Accessibility violations (WCAG AA failures), broken interactions, data loss risks.

High (quality issues)

Inconsistent systems, off-scale values, missing states, anti-patterns.

Medium (polish)

Minor inconsistencies, optimization opportunities.

Low (nits)

Style preferences, subjective improvements.

For each finding, include:

  • File and line where the issue lives
  • What's wrong in one sentence
  • Why it's wrong (reference to the CANON skill + cited standard)
  • How to fix with a code diff where possible

Report Format

CANON AUDIT REPORT
==================
Repo:   {name}
Date:   {date}
Files:  {count}
Score:  {X}/100  ({critical} critical, {high} high, {medium} medium, {low} low)

CRITICAL
--------
1. [canon-accessibility] styles.css:42
   Focus ring removed without replacement.
   WCAG 2.4.7 violation.
   Fix:
     - outline: none;
     + &:focus-visible { outline: 2px solid var(--color-focus); outline-offset: 2px; }

2. [canon-color] Header.tsx:18
   Body text #666 on #999 surface fails contrast (2.8:1, need 4.5:1).
   WCAG 1.4.3 violation.
   Fix: use var(--color-text) on var(--color-bg), check pair.

...

Read the full file on GitHub · 77 lines

Changes

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.

  1. 2d ago First seen · 77 lines · 50 tokens per session scan A ae9a7a084d74

Subscribe to this mod's changes

audit is a command published in the GitHub repository Dragoon0x/canon (5 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 707 once invoked, about $0.0003 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.