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 Borda/vision-delivery --skill detect-and-analyzegit clone --depth 1 https://github.com/Borda/vision-deliveryWrote 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/borda/vision-delivery/detect-and-analyze)<a href="https://agentmods.dev/skills/borda/vision-delivery/detect-and-analyze"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/detect-and-analyze/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/borda/vision-delivery/detect-and-analyze"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/detect-and-analyze.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00166 | $0.01313 |
| Opus 5 | $0.00083 | $0.00656 |
| Sonnet 5 | $0.00033 | $0.00263 |
| Haiku 4.5 | $0.00017 | $0.00131 |
Grade A, and why
detect-and-analyze 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 10d 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.
Turn an object-level business question into a detector that passes independent acceptance and produces actionable per-instance output. Counts, crops, relative dimensions, class breakdowns, and zone membership may be derived from boxes. Physical units and pixel-precise outlines are outside a box-only claim.
Platform execution boundary. Read ../../resources/roboflow-platform-lookup.md before any provider-specific search, dataset, training, inference, or deployment action. Use installed official Roboflow skills or current MCP resources only for read-only discovery and sourced action-brief inputs; never invoke provider execution. Sentinel owns the problem contract, independent evidence, failure diagnosis, artifact verification, and decision.
Follow ../../resources/fde-methodology.md; the domain-specific requirements below refine its generic sequence.
1. Frame the operational decision
Inspect available images, clips, annotations, code, and camera constraints first. Ask at most three missing business questions:
- Which object instances matter, and what action follows a detection?
- Which is worse: a missed instance or a false alarm?
- Is this per-image inventory, per-frame monitoring, or an identity-linked video event?
Route one verdict for the whole image to classify-or-flag. Route per-person PPE to this skill; whole-image compliance belongs in classification. Route identity-linked counts to track-and-count.
Freeze the acceptance record before any candidate or baseline result:
Acceptance ID: <session/revision>
Business decision: <action enabled by a passing result>
Gold set: <independent label source, split, sample size, adjudicator>
Primary metric and threshold: <recall/precision/count error/etc.>
Secondary guardrails: <latency, false alarms, size or scene slices>
Frozen before baseline: <timestamp and confirmation>
Baseline result (diagnostic only): <not run yet>
2. Define the output contract
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.
- 10d ago First seen · 102 lines · 166 tokens per session scan A 126031a67dbc
detect-and-analyze is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 29d ago), licensed Apache-2.0. It adds 166 tokens to every session and 1,313 once invoked, about $0.0008 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
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
setup
Use when superb's skills need their dependencies installed or checked — "set up superb", "install the dependencies", "why does pipeline say superpowers is missing", after a fresh plugin install, or on a new machine. Also use when a skill fails complaining that a superpowers sub-skill cannot be found.
boundedrelay-adaptive-sdd
Coordinate the optional BoundedRelay Spec Kit workflow with strict independent reviews, deterministic effort routing, bounded proposals, convergence, and handoff.