agentery
$ agentery.com/api/mcpsubmit agent
← Back to search

Market around cold-run

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.

Visit github.com ↗Pricing page ↗

Explore the market

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
25th pctile
5 competing vendors
Comparable listings · 30d
Flat
driven by ALPNAI $21.79→$21.34
Platforms · Pro median
$35.79/mo
4 priced · —–— mid 50%
Price spectrum · Pro plans · 7 of 7 providers priced · log scale · $5 → $208/mo
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.

MMCP servers11Ranked by similarity
cold-runthis listing
● MCP
no public price
Polygraphso
● MCP78% similar
$15/mo Pro
Agentic Keychain
● MCP76% similar
no public price
Dry Run
● MCP75% similar
no public price
ALPNAI
● MCP75% similar
$19/mo Pro
SkillFlow - AI Skills Marketplace
● MCP74% similar
no public price
DE
Deepresearch Bench Ii
● MCP74% similar
no public price
AI Deployment Readiness Protocol
● MCP74% similar
no public price
Evalgate
● MCP74% similar
no public price
TestHeal
● MCP73% similar
no public price
Findaskill MCP
● MCP73% similar
no public price
OOther14Ranked by similarity
Skillgrade
● OTHER81% similar
no public price
Model Evaluation
● OTHER81% similar
no public price
16agents
● OTHER80% similar
no public price
Eval Skills
● OTHER78% similar
no public price
Humanbound
● OTHER77% similar
no public price
Agentic Eval
● OTHER76% similar
no public price
Fusion First
● OTHER76% similar
no public price
Clawbench
● OTHER75% similar
no public price
Agent Temperament Test
● OTHER75% similar
no public price
genspark-claw
● OTHER74% similar
no public price
aws-bench
● OTHER74% similar
no public price
Universal Agentic QA
● OTHER74% similar
no public price
Agentevals Via Github
● OTHER73% similar
no public price
AI Deploy Bench
● OTHER73% similar
no public price
AAgents3Ranked by similarity
Skill Evolution
● AGENT79% similar
no public price
Probeagent
● AGENT79% similar
no public price
Trustshell
● AGENT75% similar
no public price
FFrameworks9Ranked by similarity
Evalmonkey
● FRAMEWORK79% similar
no public price
Agentspec
● FRAMEWORK78% similar
no public price
Niceeval
● FRAMEWORK76% similar
no public price
Bound
● FRAMEWORK75% similar
no public price
Skillport
● FRAMEWORK75% similar
no public price
Agentlinter
● FRAMEWORK75% similar
no public price
GEAR
● FRAMEWORK74% similar
no public price
Understudy
● FRAMEWORK73% similar
no public price
Ski
● FRAMEWORK73% similar
no public price
PPlatforms13Ranked by similarity
Agentsproof
● PLATFORM78% similar
$24.17/mo Pro
-32% vs Pro median
LIFE FORGE
● PLATFORM78% similar
no public price
agent-evals
● PLATFORM78% similar
no public price
Ctf Agent Benchmark
● PLATFORM77% similar
no public price
Daishi Studio
● PLATFORM77% similar
$49/mo Pro
+37% vs Pro median
Agent Security Sandbox
● PLATFORM77% similar
no public price
BotGauge
● PLATFORM76% similar
no public price
Etna
● PLATFORM76% similar
$208/mo Pro
+480% vs Pro median
Agent Eval Harness
● PLATFORM75% similar
no public price
ContextIQ
● PLATFORM74% similar
$5/mo Pro
-86% vs Pro median
Bottrade
● PLATFORM74% similar
$19.99/mo Pro
-44% vs Pro median
Pome
● PLATFORM73% similar
no public price
Agentleak
● PLATFORM73% similar
no public price

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.