A read-only inventory command for files in .claude-design and related state folders. It groups files by type, shows counts and sizes, and checks whether expected project artifacts exist.

Use it to inspect design assets, screenshots, metadata, notes, review files, plans, audits, and saved source snapshots across features.

It gives a quick view of what design files and tracked artifacts are available without manually searching through folders. It can also show whether key files are missing.

assets — Command by opensesh

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/opensesh/canvas-to-code/assets

Clone the repo

git clone --depth 1 https://github.com/opensesh/canvas-to-code

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,473 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.

Model	Per session	Once invoked
Fable 5	$0.00016	$0.01473
Opus 5	$0.00008	$0.00737
Sonnet 5	$0.00003	$0.00295
Haiku 4.5	$0.00002	$0.00147

Measured yesterday against content hash 93868148b352, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

assets 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 yesterday.

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.

commands/assets.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/canvas-to-code:assets — File inventory

Read-only walk of .claude-design/ (and, for state-tracked features, the matching .canvas-to-code/state/<feature>/ directory). Reports what's on disk, grouped by type, so you can see what's available to import or audit without running ls and find.

What it shows

All features (no args) — one block per feature subfolder under .claude-design/:

Feature name + path
Source shape: iter (with subpage + iter path) or flat. Read from status.json.sourceShape.
Counts by extension: *.html, *.png, *.yaml, *.md, *.tsx, *.json, other
Total size on disk
Whether each standard artifact is present:
- review.html (flat) or iter folder path with source-meta.yaml v2 (iter)
- screenshots/ (count of PNGs)
- source-meta.yaml (flat root) or <iter>/source-meta.yaml (iter)
- notes.md
- .canvas-to-code/state/<feature>/status.json (yes/no)
- .canvas-to-code/state/<feature>/source-snapshot/ (iter-shape features only — verifies the Gate 1 snapshot landed)
- .canvas-to-code/state/<feature>/plan.md (yes/no)
- .canvas-to-code/state/<feature>/audit.md (yes/no)
- Plan doc at docs/spikes/design-system/<YYYY-MM>/<YYYY-MM-DD>-<feature>-bridge.md (yes/no, with path)
- Extracted JSX in /tmp/<feature>-template.tsx (yes/no — ephemeral)

Single feature (--feature <name>) — adds:

Full file tree under .claude-design/<feature>/ with absolute paths + byte sizes
Component-mapping excerpt from status.json.componentMap.byTier (counts only)
Slice file allocations from status.json.slices[].files

Sample (all features)

Canvas-to-Code — assets
=======================
Root: .claude-design/  (3 features · 14.2 MB total)

brand-hub-hifi
  .claude-design/brand-hub-hifi/                    9.1 MB
  ├─ review.html               ✓     1.4 MB
  ├─ screenshots/              ✓     7.6 MB  (12 PNGs)
  ├─ source-meta.yaml          ✓     412 B
  ├─ notes.md                  ✓     1.8 KB
  ├─ status.json               ✓     12.4 KB  (.canvas-to-code/state/)
  ├─ plan.md                   ✓     8.2 KB
  ├─ audit.md                  ✓     3.1 KB
  └─ spike                     ✓     docs/spikes/design-system/2026-05/2026-05-12-brand-hub-hifi-bridge.md
  Counts:  .html 1 · .png 12 · .yaml 1 · .md 3 · .json 1

spaces-redesign
  .claude-design/spaces-redesign/                   3.9 MB
  ├─ review.html               ✓     780 KB
  ├─ screenshots/              ✓     2.9 MB  (5 PNGs)
  ├─ source-meta.yaml          ✓     398 B
  ├─ notes.md                  ✓     2.1 KB
  ├─ status.json               ✓     9.7 KB
  ├─ plan.md                   ✓     6.4 KB
  ├─ audit.md                  ✓     2.8 KB
  ├─ spike                     ✓     docs/spikes/design-system/2026-06/2026-06-04-spaces-redesign-bridge.md
  └─ template.tsx              ✓     /tmp/spaces-redesign-template.tsx  (78 KB, ephemeral)
  Source: flat
  Counts:  .html 1 · .png 5 · .yaml 1 · .md 3 · .json 1 · .tsx 1

brain (iter source)
  .claude-design/brain/home/paper/iter-01-baseline/  860 KB
  ├─ source-meta.yaml          ✓     420 B   (metaVersion: 2, source: paper)
  ├─ notes.md                  ✓     1.2 KB
  ├─ jsx/brain-home.tsx        ✓     14.8 KB
  └─ screenshots/              ✓     844 KB  (1 PNG)
  Snapshot:                   ✓     .canvas-to-code/state/brain/source-snapshot/  (mirrors the iter at Gate 1)
  Source: iter · subpage: home · iter path: .claude-design/brain/home/paper/iter-01-baseline/
  Counts:  .yaml 1 · .md 1 · .tsx 1 · .png 1

account-shell
  .claude-design/account-shell/                     1.2 MB
  ├─ review.html               ✓     410 KB
  ├─ screenshots/              ✓     820 KB  (4 PNGs)
  ├─ source-meta.yaml          ✓     386 B
  ├─ notes.md                  ✓     1.4 KB
  ├─ status.json               ✓     7.1 KB
  ├─ plan.md                   ✓     5.2 KB
  ├─ audit.md                  —     (Gate 3 not yet run)
  └─ spike                     ✓     docs/spikes/design-system/2026-06/2026-06-10-account-shell-bridge.md
  Counts:  .html 1 · .png 4 · .yaml 1 · .md 3 · .json 1

Read the full file on GitHub · 111 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.

yesterday First seen · 111 lines · 16 tokens per session scan A 93868148b352

Subscribe to this mod's changes

assets is a command published in the GitHub repository opensesh/canvas-to-code (6 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 1,473 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.

Code review Productivity ai-tools claude-code claude-design claude-plugin design handoff design-systems

assets

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/canvas-to-code:assets — File inventory

What it shows

Sample (all features)

What this file has done since we first saw it

Other commands, from other repositories

od-contribute

style-guide

design-audit

brand-identity

create

resume