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 danielrosehill/Claude-AI-Video-Producer-Plugin --skill budget-estimatorgit clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-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/danielrosehill/claude-ai-video-producer-plugin/budget-estimator)<a href="https://agentmods.dev/skills/danielrosehill/claude-ai-video-producer-plugin/budget-estimator"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/budget-estimator/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/danielrosehill/claude-ai-video-producer-plugin/budget-estimator"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/budget-estimator.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 | $0.00093 | $0.00653 |
| Opus 5 | $0.00046 | $0.00327 |
| Sonnet 5 | $0.00019 | $0.00131 |
| Haiku 4.5 | $0.00009 | $0.00065 |
Grade A, and why
budget-estimator 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 12d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget estimator
You produce realistic cost projections for an AI video project.
Inputs
- Either a single pipeline (
pipelines/<name>/SPEC.md) or all of them. scripts/storyboards/for shot count and durations.brief/tools-and-models.mdfor model + provider per stage.- Latest pricing — pull from
research/models-*.mdif recent (≤30 days), otherwise re-fetch from provider pages.
Cost model
For each shot, for each pipeline stage:
- Per-call cost — what one generation costs.
- Iteration multiplier — how many takes the user typically runs to get an acceptable result. Defaults if no project history:
- Text-to-image: ×3 (cheap, iterate freely)
- Image-to-video: ×2 (expensive, iterate sparingly)
- Text-to-video direct: ×3 (drifts; expect retries)
- Voice: ×1.5
- Lip-sync: ×1.5
- Upscale / interpolate: ×1
- Typical / low / high = (1 × per-call), (multiplier × per-call), (multiplier × 1.5 × per-call).
If logs/production-log.md has past data on this project, use the actual observed iteration count instead of defaults.
Output
budgets/estimate-<YYYY-MM-DD>.md:
# Cost estimate — <project name>
Date: <YYYY-MM-DD>
Pricing source: <date pulled, provider pages>
## Per-shot breakdown
| Shot | Pipeline | Stages | Low | Typical | High |
|------|----------|--------|-----|---------|------|
## Totals
- Low (everything first-take): $X.XX
- Typical: $Y.YY
- High (heavy iteration): $Z.ZZ
## Sensitivity
- Single biggest cost driver: <stage / model>
- Cheapest substitute that preserves quality: <if any>
## Assumptions
- <list: aspect, duration per shot, iteration multipliers used, currency>
After writing, summarise in 4-6 lines and flag if the typical figure exceeds the user's stated budget.
Discipline
- Always show a range, never a single point estimate.
- Always cite the date the prices came from. Surface explicitly that AI media pricing changes monthly.
- Convert all prices to a single currency (default USD; user can override).
- Don't include human time. This is API spend only.
- If a stage's pricing model is "per second of output", multiply by the storyboard duration for that shot, not the wall-clock generation time.
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.
- 12d ago First seen · 68 lines · 93 tokens per session scan A b8803af02d65
budget-estimator is a skill published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 653 once invoked, about $0.0005 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.