Open-source CLI and MCP server that evaluates AI agent skills by running cold and skilled agent variants on adversarial tasks, comparing artifacts and transcripts to identify ineffective or harmful skills.
Prices and medians update for the tier you select.
Compare at
cold-run · Pro
No Pro plan
—
Pro-MCP server median
—
insufficient comparable pricing
vs Pro MCP servers
No comparison
cold-run doesn't sell Pro
ⓘ Comparisons are same provider type (MCP server) and same buyer tier (Pro). Never across tiers.
Market density
62nd pctile
125 strong substitutes
Price momentum · 31d
Flat
Agents · Pro median
$27/mo
2 priced · $26–$28 mid 50%
MCP servers · Pro median
$15/mo
1 priced · $15–$15 mid 50%
Platforms · Pro median
$24.17/mo
5 priced · $19.99–$29 mid 50%
Agents cost 1.8× MCP servers at the Pro tier.
Price spectrum · Pro plans · 5 of 8 providers priced · log scale · $14.5 → $29/mo
Agents MCP servers Platforms◻ shaded = middle 50% · line = median (all types)cold-run has no comparable Pro price — not plotted
Products in this market
Ranked by how closely each one matches cold-run's job. Prices show each provider's Pro state; entry prices are labelled as such. Unpriced products still belong to the market.
Market = the products most similar to this one by capability; prices are median / quartiles over its priced members, separated by provider type and buyer tier.