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.
git 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/critique)<a href="https://agentmods.dev/commands/austron24/kalshi-trader-plugin/critique"><img src="https://agentmods.dev/badge/commands/austron24/kalshi-trader-plugin/critique.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 5.1 | $0.00015 | $0.01061 |
| Opus 5 | $0.00008 | $0.00531 |
| Sonnet 5 | $0.00003 | $0.00212 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
critique 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 7d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critical Review Scanner
You are initiating critical review on events that were previously researched by /alpha and/or /creative. Your job is to:
- Identify all events that have been researched
- Spawn parallel senior-analyst agents for each event
- Report back with pointers to all generated reviews
Phase 1: Identify Events to Review
Look at the conversation history to find events from previous commands, OR scan the research directory:
ls research/events/
Each folder is an event ticker that should be reviewed.
For each event, verify there's research to review:
ls research/events/<EVENT_TICKER>/
Only include events that have at least one research file (initial-research or creative-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 Senior Analyst Agents
For each event identified, spawn a senior analyst agent 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: "senior-analyst"
- model: opus
- prompt: (see below)
Example prompt for each agent:
Conduct senior analyst review of Kalshi event [EVENT_TICKER].
**CRITICAL: Read ALL files in research/events/[EVENT_TICKER]/ completely. Do not skim. You need full context.**
Your job:
1. Read EVERY research file in the event folder completely
2. Reality check the fundamentals: resolution mechanics, base rates, what actually has to happen
3. Verify the bracket recommendation makes sense (the initial research recommends a specific bracket)
4. Identify fatal flaws, serious concerns, and minor issues
5. Determine if there's genuine alpha or if we're fooling ourselves
6. Provide final recommendation: TRADE [SPECIFIC_TICKER], PASS, or NEEDS MORE WORK
Create your review at: research/events/[EVENT_TICKER]/YYYY-MM-DD-HHMM-senior-review.md
When done, report: file path, files reviewed (confirm ALL read completely), final recommendation (TRADE [ticker]/PASS/NEEDS MORE WORK), one-sentence assessment.
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.
- 7d ago First seen · 124 lines · 15 tokens per session scan A e267b99f04bb
critique is a command published in the GitHub repository austron24/kalshi-trader-plugin (12 stars, last pushed 8mo ago), licensed MIT. It adds 15 tokens to every session and 1,061 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
data-leaderboard
Access leaderboard data, trader rankings, competition stats, and top performer metrics.
gamma-markets
Access detailed market data, filter markets by various criteria, and build market discovery features.
gamma-search
Full-text search across markets and events, plus advanced discovery features.
clob-orders
Create, cancel, and manage orders on Polymarket's Central Limit Order Book.
clob-trades
Access trade execution data, historical trades, and user trade activity.
data-activity
Access user trading activity, transaction history, and order events.