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 MarcoZorn/agencykit --skill shooting-daygit clone --depth 1 https://github.com/MarcoZorn/agencykitWrote 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/marcozorn/agencykit/shooting-day)<a href="https://agentmods.dev/skills/marcozorn/agencykit/shooting-day"><img src="https://agentmods.dev/badge/skills/marcozorn/agencykit/shooting-day/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/marcozorn/agencykit/shooting-day"><img src="https://agentmods.dev/badge/skills/marcozorn/agencykit/shooting-day.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 | $0.00041 | $0.02711 |
| Opus 5.5 | $0.00016 | $0.01084 |
| Sonnet 5.5 | $0.00008 | $0.00542 |
| Haiku 4.5 | $0.00004 | $0.00271 |
Grade A, and why
shooting-day 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 2mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shooting Day
When to use this skill
English: "shooting", "shot list", "call sheet", "filming day", "production day", "plan the shoot".
Italiano: "shooting", "riprese", "giorno di ripresa", "ODG", "scaletta set", "piano riprese".
What this skill does
Turns a shoot into a plan the whole crew can run from a phone. It produces the order of day with times and locations, a shot list categorised the way a social edit actually needs (hook, body, CTA, B-roll, audio), an equipment checklist you tick as you pack, and a crew briefing formatted to paste straight into WhatsApp. It ends the two universal set problems: "where's the shot list" and "who has the call sheet".
Inputs required
- Project / client and what you are shooting (reels, ad, brand film, product).
- Date, city and location(s) — including call time and wrap target.
- Deliverables — how many pieces, formats and durations come out of the day.
- Crew — who is on set and their role.
- Talent — presenter, model, founder, none.
- Key shots or script beats if they exist. If not, the skill proposes a shot list from the deliverables.
Output format
- ODG (ORDER OF DAY) — timed schedule with locations.
- SHOT LIST — grouped: Hook / Body / CTA / B-roll / Audio.
- EQUIPMENT CHECKLIST — tick-box, grouped by category.
- CREW BRIEFING — WhatsApp-ready block, copy-paste as-is.
- WEATHER NOTE — placeholder with city + date to check the morning of.
Brand voice
If a BRAND.md file exists in this skill's folder (.claude/skills/shooting-day/BRAND.md) or in .claude/brand/BRAND.md (global fallback), read it before generating output and apply its tone, terminology, and examples to all text you produce. A skill-local BRAND.md overrides the global one; if neither exists, use a clean, professional default voice.
Instructions
1. Build the ODG
A timed run of the day from crew call to wrap. Each row: time, activity, location, who's needed. Include the unglamorous but critical blocks — load-in, setup, lighting, lunch, buffer, teardown. Leave real buffer; shoots run long, and a schedule with no slack is a schedule that breaks by 11am. Put the hardest or most talent-dependent setup earliest while energy is high.
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.
- 2mo ago First seen · 203 lines · 41 tokens per session scan A 8f76f1abc8b3
shooting-day is a skill published in the GitHub repository MarcoZorn/agencykit (6 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 2,711 once invoked, about $0.0002 per session on Opus 5.5. 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.
shooting-day compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shooting-dayMarcoZorn/agencykit | Skill | 6 | 4mo ago | MIT | A | 41 | Claude Code |
| create_profile_style_skillFireRedTeam/FireRed-OpenStoryline | Skill | 3.7k | 3mo ago | Apache-2.0 | A | 64 | Claude Code, Codex |
| live-panelseaworld008/Commonly-used-high-value-skills | Skill | 74 | 4d ago | MIT | A | 16 | Claude Code, Codex |
| promo-video-pipelinerexleimo/aios | Skill | 62 | 6d ago | MIT | A | 92 | Claude Code, Codex |
| silicon-stewardlinkerlin/PUAX | Skill | 323 | 1mo ago | MIT | A | 31 | Claude Code, Codex |
| media-expertpersonamanagmentlayer/pcl | Skill | 45 | 18d ago | Apache-2.0 | A | 57 | Claude Code |
| video-directoroyi77/1ai-skills | Skill | 19 | today | MIT | A | 105 | Claude Code |