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 commands/austron24/kalshi-trader-plugin/creativegit clone --depth 1 https://github.com/austron24/kalshi-trader-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/commands/austron24/kalshi-trader-plugin/creative)<a href="https://agentmods.dev/commands/austron24/kalshi-trader-plugin/creative"><img src="https://agentmods.dev/badge/commands/austron24/kalshi-trader-plugin/creative.svg" alt="Measured on agentmods" 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 | $0.00013 | $0.00858 |
| Opus 5 | $0.00006 | $0.00429 |
| Sonnet 5 | $0.00003 | $0.00172 |
| Haiku 4.5 | $0.00001 | $0.00086 |
Grade A, and why
creative 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Research Scanner
You are initiating creative/unconventional research on events that were previously researched by /alpha. Your job is to:
- Identify all events that were researched in the previous
/alpharun - Spawn parallel creative-researcher agents for each event
- Report back with pointers to all generated research
Phase 1: Identify Events from /alpha
Look at the conversation history to find the output from the previous /alpha command. The /alpha output lists all research files created, like:
research/events/KXCPI-25DEC/YYYY-MM-DD-HHMM-initial-research.md
research/events/KXFED-26JAN/YYYY-MM-DD-HHMM-initial-research.md
...
Extract all the event tickers from these file paths.
Alternatively, if the conversation doesn't have clear /alpha output, scan the research/events/ directory:
ls research/events/
For each event folder, that's an event to research.
Guard: If no events found:
No research found in `research/events/`. Run `/alpha` first to scan for opportunities and generate initial research.
Exit the command if no events exist.
Phase 2: Spawn Creative Research Agents
For each event identified, spawn a creative-researcher subagent using the Task tool.
CRITICAL: Parallel Blocking Execution
To run agents in parallel (concurrent) but blocking (main agent waits for all to complete):
- Make ALL Task calls in a SINGLE message - This triggers parallel execution
- Do NOT use
run_in_background- Omitting this makes calls blocking - The main agent automatically waits for all agents to complete before continuing
For each agent:
- subagent_type: "creative-researcher"
- prompt: "Conduct creative/unconventional research on Kalshi event [EVENT_TICKER]. The event research folder is at research/events/[EVENT_TICKER]/. Read the existing initial research first, then explore non-obvious angles, unusual correlations, contrarian perspectives, and obscure data sources. Create a file named research/events/[EVENT_TICKER]/YYYY-MM-DD-HHMM-creative-research.md with your findings."
- model: opus
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.
- 4d ago First seen · 100 lines · 13 tokens per session scan A 9e6285cd6899
creative is a command published in the GitHub repository austron24/kalshi-trader-plugin (12 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 858 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
gen-video
Generate video output in one of three modes: Remotion (programmatic React-based video), Gen-AI (shot prompt pack for Runway/Kling/Sora/Pika/Luma), or Remotion+Gen-AI (programmatic scaffold with AI footage embedded).
brand-generate
Generate an on-brand document from a saved Brand Profile.
video
WATCH a video and return a structured VISUAL breakdown (not just a transcript) with Antigravity (agy / Gemini 3.x, natively multimodal in video). Scene-by-scene segments with timestamps, on-screen text/OCR (slides, charts, UI, captions), key visual events, and a summary. For screencasts, tutorials, presentations…
illustration-system
Design an illustration style guide, icon system, or SVG asset set for a product or brand.
sip-attest-audio
Attest an audio artifact (music track, voice-over, podcast, soundscape). Generates SIP attestation embedded in ID3 tags + sidecar .sip.json. Refuses decorative use. v7.5+ — scaffold present, full implementation pending.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.