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 yolo-detectorgit 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/yolo-detector)<a href="https://agentmods.dev/skills/hipson47/hipson/yolo-detector"><img src="https://agentmods.dev/badge/skills/hipson47/hipson/yolo-detector.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 | $0.00032 | $0.01099 |
| Opus 5 | $0.00016 | $0.00549 |
| Sonnet 5 | $0.00006 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
yolo-detector 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 7d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YOLO Detector
Purpose
Define a reproducible YOLO inference boundary for detection, segmentation, tracking, or pose. Keep model configuration, preprocessing, postprocessing, result serialization, licensing, and verification explicit.
Use When
- The task explicitly selects Ultralytics YOLO or requires its supported modes.
- An image, video, camera, or API workflow needs structured predictions.
- A demo must emit both machine-readable results and optional annotations.
Do Not Use When
- A browser-side MediaPipe landmark task satisfies the requirement.
- The model family is undecided; use
cv-project-routerfirst. - The task is training orchestration, identity recognition, or a medical claim.
Inputs
- Mode: detect, segment, track, or pose.
- Model identifier, exact library/model version, source, license, checksum, and approved cache location.
- Image/frame contract, class allowlist, confidence and IoU thresholds, and device policy.
- Required JSON fields, coordinate space, annotation policy, and latency target.
Default Stack
- Python, Ultralytics, OpenCV, and NumPy in a demo-owned environment.
- CPU baseline and a small pinned model only after explicit download approval.
- Absolute pixel
xyxyboxes in JSON, with source dimensions included. - OpenCV capture delegated to
opencv-realtime-cameraand web boundaries delegated tocv-webapp-starter.
Workflow
- Confirm the selected YOLO task and reject modes not supported by the pinned model. Record Ultralytics AGPL-3.0 or Enterprise licensing implications.
- Require explicit approval before adding the dependency or downloading weights. Never execute model-repository scripts or arbitrary remote code.
- Pin library and model revisions, record source/checksum/cache location, and keep weights outside Git.
- Define image size, color order, confidence, IoU/NMS, class filters, maximum detections, device selection, warm-up, and deterministic seed where relevant.
- Convert library-specific results at one adapter boundary. Validate finite confidence values, class identifiers, source dimensions, and clipped boxes.
- For tracking, state tracker configuration and lifecycle; track IDs are session-local and must not be treated as identity.
- Make annotated media optional and derived from normalized JSON, not a second source of truth.
- End with
vision-verifierusing a licensed static fixture and expected structural assertions rather than brittle exact detections alone.
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.
- 7d ago First seen · 125 lines · 32 tokens per session scan A c39bff981503
yolo-detector is a skill published in the GitHub repository Hipson47/Hipson (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,099 once invoked, about $0.0002 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.