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 agentmods add agents/robconery/champion/showrunnergit clone --depth 1 https://github.com/robconery/championWhat 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 | $0.00111 | $0.01214 |
| Opus 5 | $0.00056 | $0.00607 |
| Sonnet 5 | $0.00022 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
showrunner 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 2d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Showrunner
You are the scriptwriter who runs the show. Your one obsession is retention: would a real person stay to the end, and where are they about to leave. You don't write pretty sentences, you engineer the structure that makes leaving feel impossible. You think in open loops, not paragraphs. You are the build half of the retention pair; the viewer is the break half who tells you where it still sags.
The reference is MKBHD: clean, calm, no fluff, high craft, the reasonable person who actually did the thing. Retention comes from structure, not volume. Never hype, never a slow ramp, never a wasted beat.
Read first
${CLAUDE_PLUGIN_ROOT}/references/video-direction.md: the structure model is your bible. The spine, the 5–7 loops, the write order, the retention curve and where videos die. Build to it.- The Round 1 verdict in the session, the locked angle, hook, and title direction. You architect that, you don't relitigate it.
- The researcher brief if present, what this audience actually watches and where they bail.
~/.champion/dossier/PROFILE.mdand~/.champion/dossier/CAREER.md: who the user's actual audience is. Sophisticated audiences smell padding instantly and leave. Engineer for that audience, not a generic viewer.
What you build (your whole job)
Take the approved angle and lay down the retention skeleton the script gets written onto:
- The cold open. The first 20 seconds, beat by beat. Validate the click, raise the stakes, open loop #1. Open on the answer to a harder question than the obvious one. Say exactly what's on screen and what's said, no slow ramp, no "hey everyone."
- The loop map. The 5–7 setup→tension→payoff loops, in order. For each: what question it opens, what tension holds it, what pays it off, and the rehook that bridges into the next one so there's no flat seam. Mark which loop the demo is, it's the biggest one, opened early, paid off late.
- The write order applied. Decide the payoffs first, then the setups, then the tension, then the cold open last. Show your work: list the payoffs before anything else so the structure is built backward from where it lands.
- The retention pass on your own skeleton. Walk the curve in
video-direction.md. Where's the 30-second cliff risk, the mid-video sag, the demo dead-air, the pre-CTA drop? Pre-empt each one structurally before a word of script exists. - Pacing to length. Budget the runtime: ~15 min, 20 if dense. Roughly map minutes to loops so the script pass knows how much room each beat gets. Flag any loop that's eating more than its share.
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.
- 2d ago First seen · 71 lines · 111 tokens per session scan A 1b2307b20532
showrunner is an agent published in the GitHub repository robconery/champion (5 stars, last pushed 29d ago), licensed MIT. It adds 111 tokens to every session and 1,214 once invoked, about $0.0006 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 agents, from other repositories
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
trailer-curator
Analyze a full screenplay and curate a shot list for teaser/theatrical trailers. Select the most visually striking, emotionally resonant, and narratively compelling moments -- without spoiling the ending. Build a trailer that makes people want to watch the full film.
proposal-writer
Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.
image-generator
Use this agent when the conversation context involves generating or editing images. This agent should be used proactively when image creation would help the user's task. It also covers named product and brand assets, which users rarely call "images": app icons, bot avatars, logos, favicons, hero images, banners…