agentmods.dev

inspect-weshop-canvas

inspect-weshop-canvas is a skill for Claude Code, Codex from weshopai/weshop-dsh-plugin. It costs 81 tokens per session (1,309 once invoked), scanned A, original, MIT.

A tool for working with the current WeShop canvas, a shared workspace for image, video, audio, and text materials. It can inspect canvas content and handle requested generation or image-editing workflows.

In plain words
What is it for?
Use it to inspect canvas results, create or transform images, upscale them, derive prompts from them, edit them locally, and publish generated media or text to the canvas.
Why use it?
It keeps generated or edited materials connected to the canvas and requires completed outputs to be published there before the task is considered finished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 13repo 22d ago A scan 81 tokens original MIT

Good fit Use it to inspect canvas results, create or transform images, upscale them, derive prompts from them, edit them locally, and publish generated media or text to the canvas.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas
View source ↗ weshopai/weshop-dsh-plugin weshop.ai
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.

Any agent
npx skills add weshopai/weshop-dsh-plugin --skill inspect-weshop-canvas
Clone the repo
git clone --depth 1 https://github.com/weshopai/weshop-dsh-plugin

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for inspect-weshop-canvas

README.md
[![agentmods](https://agentmods.dev/badge/skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas/github.svg)](https://agentmods.dev/skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas)
Your own site
<a href="https://agentmods.dev/skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas"><img src="https://agentmods.dev/badge/skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas/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.

agentmods 80×15 button for inspect-weshop-canvas

Your own site · 80×15
<a href="https://agentmods.dev/skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas"><img src="https://agentmods.dev/badge/skills/weshopai/weshop-dsh-plugin/inspect-weshop-canvas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,309 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00081 $0.01309
Opus 5 $0.00041 $0.00655
Sonnet 5 $0.00016 $0.00262
Haiku 4.5 $0.00008 $0.00131

Measured 11d ago against content hash d032185c36c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

inspect-weshop-canvas 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 11d 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.

skills/inspect-weshop-canvas/SKILL.md · 64 lines

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.

Inspect weshop Canvas

Non-negotiable insertion rule

  • Add in the canvas is exclusively a human-facing material importer. Never use browser automation to insert a generated output through it.
  • Every successful image MUST be inserted with weshop_canvas_publish_result. Publish generated video, audio, or text with weshop_canvas_publish_asset and the matching mediaType before replying that the task is complete.
  • Publishing the result is part of generation completion, not an optional follow-up step. Do not ask the user to add it manually.
  • If publishing fails, report the failure and retry the canvas tool; do not fall back to the webpage Add button.

Visible execution progress

Use weshop_canvas_report_progress at meaningful transitions so the canvas exposes concise, verifiable status — not private chain-of-thought. Set one stable startedAt timestamp for the task and include a monotonic percent:

  1. interpreting (~8%): one-sentence understanding plus outputPlan.
  2. researching (~12–20%, only when required): report the platform/market/source focus.
  3. planning (~22%): selected WeShop commercial workflow or model and why it fits.
  4. prompt-ready (~32%): set promptStatus to "已完成"; summarize the prompt constraints.
  5. generating (35–85%): report the active model and expected output count.
  6. publishing (~92%): report that completed files are being added automatically.
  7. complete (100%) or error: report the concrete outcome.

Do not emit updates for every API poll. Keep progress useful and sparse.

  • Call weshop_canvas_get_state before reasoning about the full canvas.
  • Call weshop_canvas_get_selection when the user says "this", "these", "selected", or otherwise refers to the active selection. Always inspect selectedItemIds and selectedItems; they contain the complete multi-selection. The singular fields are compatibility aliases for the primary/last-selected item only.
  • Treat kind: material as source/reference input and kind: result as generated output.
  • Use each item's provenance to explain how it entered the canvas. Do not infer missing provenance.
  • If connected is false, ask the user to open WeShop for DeepSeek Harness first.
  • Call weshop_canvas_get_requests when the user asks to handle an operation submitted from the canvas right-click menu.

Read the full file on GitHub · 64 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. 11d ago First seen · 64 lines · 81 tokens per session scan A d032185c36c7

Subscribe to this mod's changes

inspect-weshop-canvas is a skill published in the GitHub repository weshopai/weshop-dsh-plugin (13 stars, last pushed 22d ago), licensed MIT. It adds 81 tokens to every session and 1,309 once invoked, about $0.0004 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 2026-08-30.

Creative and mediaagentagent-skillsagentic-aiagentic-workflowagentscanvas
Related

Other skills, from other repositories

feature-demo-recording

Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…

kirodotdev/KiroCrew · 90 tokens

image-authoring

Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.

kirodotdev/KiroCrew · 45 tokens

pptx-maker

Generate or restyle a PowerPoint deck. Use when the user wants to create or edit a .pptx presentation, build slides from text or a URL, or design a reusable slide style.

kirodotdev/KiroCrew · 43 tokens

artifacts

Persist, version, and iterate on LLM-generated UI (widgets, HTML, markdown). Load when the user wants to save, find, update, or iterate on a previously-rendered widget — anything that should outlive the chat scrollback.

kirodotdev/KiroCrew · 52 tokens

artistic

High-contrast, expressive style with creative typography and bold color choices for visually striking interfaces.

bergside/awesome-design-skills · 21 tokens

vigilante-create-issue

Help a human author write an implementation-ready GitHub issue that Vigilante can execute reliably.

aliengiraffe/vigilante · 25 tokens