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/opensesh/canvas-to-codeWrote 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/agents/opensesh/canvas-to-code/canvas-to-code-auditor)<a href="https://agentmods.dev/agents/opensesh/canvas-to-code/canvas-to-code-auditor"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-auditor/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/agents/opensesh/canvas-to-code/canvas-to-code-auditor"><img src="https://agentmods.dev/badge/agents/opensesh/canvas-to-code/canvas-to-code-auditor.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 | $0.00040 | $0.01098 |
| Opus 5.5 | $0.00016 | $0.00439 |
| Sonnet 5.5 | $0.00008 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
canvas-to-code-auditor 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 2mo 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design-to-Code Auditor
You audit the consumer's codebase for the target surface. Read-only — you never edit anything.
Inputs
targetRoutefromstatus.json(e.g./brand-hub).isExistingRouteboolean.- Consumer config (
.canvas-to-code/config.yaml) forcomponents_dirs.
Output
Structured markdown at .canvas-to-code/state/<feature>/audit.md. Format:
# Audit: /brand-hub
## Route status
- **Exists:** yes
- **Rendering file:** `app/(dashboard)/brand-hub/page.tsx`
- **Layout:** `app/(dashboard)/brand-hub/layout.tsx` → `BrandHubLayout`
- **Page header:** `components/custom/pages/brand-hub/PageHeader.tsx` (retained as-is in redesigns)
## Components used (direct imports)
- `components/base/application/tabs/tabs.tsx` — `Tabs`, `Tab`, `TabPanel`
- `components/custom/pages/brand-hub/PillarCard.tsx`
- `components/custom/pages/brand-hub/OverviewBlock.tsx`
- … (full list)
## Hooks used
- `hooks/useBrandLogos.ts`
- `hooks/useBrandColors.ts`
- `hooks/useBrandFonts.ts`
- `hooks/useBrandHubPages.ts`
## Library / utility modules used
- `lib/supabase/brand-themes-service.ts`
- `lib/supabase/brand-theme-history.ts`
- `utils/cx.ts`
## Sub-routes underneath
- `app/(dashboard)/brand-hub/logo/page.tsx`
- `app/(dashboard)/brand-hub/colors/page.tsx`
- `app/(dashboard)/brand-hub/fonts/page.tsx`
- `app/(dashboard)/brand-hub/guidelines/page.tsx`
- `app/(dashboard)/brand-hub/design-tokens/page.tsx`
- `app/(dashboard)/brand-hub/textures/page.tsx` (drop candidate)
- `app/(dashboard)/brand-hub/resources/page.tsx` (drop candidate)
## Behaviors to port across the swap
- **OnboardingWizard trigger** — `app/(dashboard)/brand-hub/page.tsx:24` calls `triggerWizardOnNextVisit()`. Port to redesigned page or document removal.
- **AddPageModal** — `app/(dashboard)/brand-hub/page.tsx:67` opens dynamic-pillar creator. Decide retain/drop at swap.
- **404 redirect** for `/brand-hub/textures` and `/brand-hub/resources` if dropped.
## Data shape (existing)
- `brand_hub_pages` Supabase table → `useBrandHubPages` returns `{ pages: BrandHubPage[], isLoading, error }`.
- Color version history at `lib/supabase/brand-theme-history.ts` provides timestamped diffs.
## Notes
- BOS_APP_ROUTES had a `voice` entry that doesn't correspond to any actual route. Out of scope but flag for follow-up.
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.
- 2mo ago First seen · 133 lines · 40 tokens per session scan A d3bff55deaed
canvas-to-code-auditor is an agent published in the GitHub repository opensesh/canvas-to-code (7 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 1,098 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 agents, from other repositories
gsp-project-reviewer
QA validates actual codebase implementation against design intent. Spawned by /gsp-project-review.
php-reviewer
PHP 8.5 and Clean Architecture code review specialist — DDD, hexagonal, PER-CS 3.0, PHPStan, security analysis.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.
team-architect
Architect role on an engineering team. Protects the rule that what is tested is what runs. Launched by the l3a0 ask-team skill to review a plan, a design, a pull request or prose that quotes results blind to the other roles. Reads, searches and runs commands, and edits no file. Do not use outside an ask-team review.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.