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 skills add weshopai/weshop-dsh-plugin --skill weshop-openapigit clone --depth 1 https://github.com/weshopai/weshop-dsh-pluginWrote 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/skills/weshopai/weshop-dsh-plugin/weshop-openapi)<a href="https://agentmods.dev/skills/weshopai/weshop-dsh-plugin/weshop-openapi"><img src="https://agentmods.dev/badge/skills/weshopai/weshop-dsh-plugin/weshop-openapi/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/skills/weshopai/weshop-dsh-plugin/weshop-openapi"><img src="https://agentmods.dev/badge/skills/weshopai/weshop-dsh-plugin/weshop-openapi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.01649 |
| Opus 5.5 | $0.00020 | $0.00660 |
| Sonnet 5.5 | $0.00010 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
weshop-openapi 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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WeShop OpenAPI
Mandatory per-turn gate
For every new user turn that asks to generate, edit, transform, upscale, or animate content, this Skill must be invoked through the Skill tool before any WeShop generation call. Invoke it again even if it was already used earlier in the conversation, and again after context compaction, retry, or handoff. Reading this file or the package README with filesystem/Bash does not replace invoking the Skill.
Use the recipes in this Skill as the source of truth. Do not search the package source or the web for parameters already documented here.
WeShop generation runs server-side through the native Cordis tools (weshop_generate_run / weshop_get_run). The WESHOP_API_KEY lives in the Harness host process — never echo it, never put it in a tool argument or a canvas provenance record, and never send it anywhere other than https://openapi.weshop.ai/openapi/*. If the key is missing, stop before any API request and tell the user to open the WeShop canvas and click Configure API Key in its top bar, then retry; alternatively they may set WESHOP_API_KEY before starting Harness. Direct them to https://www.weshop.ai/apiKey only to obtain a key.
Workflow
- Read the canvas (
weshop_canvas_get_state) and use the selectedmaterialitem as the source. Use itsasset.localPathwhen available, else itsasset.url. - Choose the agent and version from the table below; read that agent's parameter notes.
- Call
weshop_generate_runwith{ agent, originalImage?, referenceImages?, taskName?, params, wait: true }. UseoriginalImagefor agents documented with one legacy source image. UsereferenceImagesfor agents documented withimages; local paths are uploaded and copied to bothinput.imagesandparams.imagesautomatically. Result URLs come back indata.executions[*].result[*].image(image agents) or*.video/*.videoPoster(video agents). - On success, publish each returned remote URL directly with
weshop_canvas_publish_result(images) orweshop_canvas_publish_asset(video/audio). Do not download the generated file first. Include complete provenance (method,agent,version,executionId,prompt/taskName,sourceItemIds, returned URL, completion time). A local path is supported only when the generating tool genuinely returns a local-only file. Never overwrite or reclassify the source material item. - If the run fails or times out, report the API error and offer to retry (the error envelope's
retryableflag signals whether a retry is worthwhile).
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.
- 1mo ago First seen · 66 lines · 51 tokens per session scan A c34861b42774
weshop-openapi is a skill published in the GitHub repository weshopai/weshop-dsh-plugin (12 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 1,649 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 2026-08-30.
Other skills, from other repositories
vigilante-create-issue
Help a human author write an implementation-ready GitHub issue that Vigilante can execute reliably.
rn-device-control
This skill should be used when the user asks to "control the simulator", "take a screenshot", "boot the emulator", "install the app", "read UI hierarchy", "manage device state", "open a deep link", "grant permissions", "stream native logs", "disable animations", "change device locale", or needs guidance on xcrun…
rn-feature-development
This skill should be used when building any new feature in a React Native or Expo app, or when the $rn-dev-agent:rn-feature-dev command runs. Triggers on "build a feature", "add X to the app", "implement Y", "create a new screen", "rn-feature-dev", "feature development", "build me X", "add a screen", "wire up this…
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…
rn-workflow
Validate and establish the proven rn-dev-agent operating sequence before a real React Native journey — read project instructions and the declared package manager, inventory sessions/Metro/devices read-only, establish one exclusive simulator/emulator via typed session actions, apply and verify package integration and…
using-rn-dev-agent
Entry point for the rn-dev-agent plugin. Maps user intent to the right command, agent, or skill. Use at the START of any React Native development conversation. Triggers on "I want to build", "build a feature", "add a feature to the app", "test this", "something is broken", "fix the crash", "help with my React Native…