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 Hipson47/Hipson --skill vision-demo-buildergit clone --depth 1 https://github.com/Hipson47/HipsonWrote 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/hipson47/hipson/vision-demo-builder)<a href="https://agentmods.dev/skills/hipson47/hipson/vision-demo-builder"><img src="https://agentmods.dev/badge/skills/hipson47/hipson/vision-demo-builder.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00934 |
| Opus 5 | $0.00014 | $0.00467 |
| Sonnet 5 | $0.00005 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
vision-demo-builder 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 8d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vision Demo Builder
Purpose
Package an already selected CV pipeline into a small, reproducible demo. Own the demo entry point, configuration, sample invocation, artifact layout, operator README, and acceptance checklist without redefining the model or web trust boundary.
Use When
- A working CV pipeline needs a local CLI, bounded preview, or lightweight demo.
- The deliverable needs run commands, sample configuration, JSON, annotations, screenshots, FPS logs, or a demo README.
- A prerecorded fixture must make the demo usable without camera hardware.
Do Not Use When
- The model/task is undecided; use
cv-project-routerfirst. - The primary deliverable is a Next.js/FastAPI application; pair with
cv-webapp-starterfor its HTTP and browser boundaries. - The request is production deployment, training infrastructure, or a broad application rewrite.
Inputs
- Existing inference/capture adapter and its input/output contracts.
- Target audience, platform, run mode, acceptance criteria, and time budget.
- Approved dependencies/model assets and deterministic fixture.
- Required JSON, annotated media, screenshot, video, metrics, and retention rules.
Default Stack
- Existing project stack first; otherwise a small Python CLI around the pipeline.
- OpenCV preview only for an explicitly local GUI demo.
- Static image/prerecorded video mode available alongside any camera mode.
- Environment variables or config files for non-secret options; no credentials required for the baseline demo.
Workflow
- Inspect the repository and reuse its CLI, configuration, logging, output, testing, and packaging conventions. Avoid new frameworks for a small demo.
- Freeze the upstream frame and prediction contracts before adding presentation code. Keep inference logic out of UI callbacks.
- Define one clear entry point with bounded inputs, output directory, overwrite policy, timeout/frame limit, CPU default, and optional device selection.
- Provide a deterministic fixture path. Make camera, GPU, hosted API, and model download modes explicit options rather than startup side effects.
- Emit machine-readable JSON as the source of truth. Derive annotations, screenshots, or video from that result and make media retention opt-in.
- Write copy-pasteable setup/run commands, expected outputs, stop behavior, privacy notes, license gates, and troubleshooting for missing model/camera.
- Keep generated artifacts under a bounded ignored directory with collision-safe names. Never overwrite source media by default.
- End with
vision-verifier; record which local, camera, browser, GPU, and live checks actually ran.
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.
- 8d ago First seen · 102 lines · 27 tokens per session scan A 3fc383db8bcf
vision-demo-builder is a skill published in the GitHub repository Hipson47/Hipson (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 934 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.
Other skills, from other repositories
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
agent-support-matrix
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests.
kirby-collections-and-navigation
Builds Kirby listings, pagination, search, filtering/sorting/grouping, and navigation menus. Use when implementing collection logic in templates/controllers/snippets.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.
kirby-forms-and-frontend-actions
Implements frontend forms and actions in Kirby (contact forms, file uploads, email with attachments, creating pages from frontend). Use when handling user input or building submission flows.