Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Borda/vision-deliverynpx agentmods add skills/borda/vision-delivery/estimate-economicsWrote 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/estimate-economics)<a href="https://agentmods.dev/skills/borda/vision-delivery/estimate-economics"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/estimate-economics/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/estimate-economics"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/estimate-economics.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 | $0.00137 | $0.01258 |
| Opus 5 | $0.00068 | $0.00629 |
| Sonnet 5 | $0.00027 | $0.00252 |
| Haiku 4.5 | $0.00014 | $0.00126 |
Grade A, and why
estimate-economics 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Give a sourced, editable economic view of the CV decision: one-time effort, monthly run-rate, scaling cliffs, uncertainty, and a managed-vs-DIY recommendation only when comparable inputs exist. This is a decision aid, not a provider sales argument.
Platform execution boundary. Read ../../resources/roboflow-platform-lookup.md before any provider-specific plan, credit, quote, deployment, or runtime lookup. Delegate exact current pricing and product capabilities to the installed official Roboflow skill or current MCP resource. Sentinel owns normalization, provenance, sensitivity, and the recommendation.
1. Establish decision readiness
Read the frozen acceptance artifact, its SHA-256 digest, measured evidence, workload, existing hardware/staff, data volume, and deployment constraints. A measured proof is the preferred basis. If it is absent and the user still wants a rough estimate, label every model/runtime figure as an assumption, retain proof.status: unbound, and do not imply technical feasibility or emit go.
Collect only missing inputs:
- cameras/streams, FPS per stream, hours/month, region, and retention;
- measured model/runtime class and throughput on representative hardware;
- existing hardware and staff ownership;
- annotation/review volume and loaded hourly rates;
- managed quote amount, scope, currency, taxes, and quote date;
- cost of downtime, misses, false alarms, and review labor.
Do not infer architecture, parameter count, or throughput from the task description. Ask upstream for current product facts and use user benchmarks for capacity.
2. Separate costs and sources
Report at least:
- one-time: data preparation/annotation, engineering, integration, validation;
- recurring: compute/service, monitoring/on-call, review labor, storage/egress, drift/retraining;
- scaling cliffs: added instance/service tier, operator load, and availability needs;
- excluded costs and uncertainty ranges.
Every price gets a source and as_of date. A user-supplied quote keeps its own quote date; never stamp it with the repository snapshot date. Do not compare a public plan floor or credit bundle to a fully loaded production quote as if scopes were equivalent.
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.
- 11d ago First seen · 98 lines · 137 tokens per session scan A ac575347b1ec
estimate-economics is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 137 tokens to every session and 1,258 once invoked, about $0.0007 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
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…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
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.