agent-eval
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
Skill by sakuradairong
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sakuradairong-agent-eval
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-eval
What's inside
- Skill name
agent-eval- Description
- Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
- License
- unknown
- Instructions
- 140 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from sakuradairong/omp-config
- 0.568score
angular-developer
sakuradairong
Generates Angular code and provides architectural guidance.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
canary-watch
sakuradairong
Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
autonomous-agent-harness
sakuradairong
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
blender-motion-state-inspection
sakuradairong
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
browser-qa
sakuradairong
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
astrbot-plugin-development
sakuradairong
Use when developing, debugging, or fixing AstrBot plugins and encountering import errors, async generator issues, plugin loading failures, or configuration…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
agent-architecture-audit
sakuradairong
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: C★ 48Claude Code +9 - 0.562score
benchmark
sakuradairong
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
architecture-decision-records
sakuradairong
Capture architectural decisions made during Claude Code sessions as structured ADRs.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
agentic-os
sakuradairong
Build persistent multi-agent operating systems on Claude Code.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
docker-compose
sakuradairong
Expert guidance on Docker Compose V2 syntax, best practices, and common patterns for writing production-ready compose files.
SkillCFreshness: C★ 48Claude Code +9 - 0.560score
cisco-ios-patterns
sakuradairong
Cisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, interface hygiene, and safe change-window verification.
SkillCFreshness: C★ 48Claude Code +9
Signals
- Stars
- 48
- Forks
- 12
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/sakuradairong/omp-config
- Website
- agisota.github.io/old-one/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.337score
agent-eval
nicolas2601
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillBFreshness: B★ 3Claude Code +9 - 0.313score
agent-eval
KUNDURUHIMANEESHREDDY
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillBFreshness: BClaude Code +9 - 0.307score
agent-eval
krataia
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillBFreshness: BClaude Code +9 - 0.307score
agent-eval
agisota
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillCFreshness: C★ 3Claude Code +9 - 0.280score
agent-eval
jaysonpantollana
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillCFreshness: CClaude Code +9 - 0.280score
agent-eval
LongHuynh712
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillCFreshness: CClaude Code +9 - 0.280score
agent-eval
julio211916
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillCFreshness: CClaude Code +9 - 0.280score
agent-eval
netsecdevio
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillCFreshness: CClaude Code +9 - 0.276score
agent-eval
majiang213
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillDFreshness: D★ 5Claude Code +9 - 0.261score
agent-eval
aayushsoam
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillDFreshness: D★ 2Claude Code +9 - 0.241score
agent-eval
Michae2xl
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
SkillDFreshness: DClaude Code +9
More from sakuradairong
- 0.568score
angular-developer
sakuradairong
Generates Angular code and provides architectural guidance.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
blender-motion-state-inspection
sakuradairong
Use this skill when inspecting Blender characters, rigs, poses, animation retargeting, ground contact, facing direction, or model-vs-motion alignment where…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
agent-architecture-audit
sakuradairong
Full-stack diagnostic for agent and LLM applications.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
astrbot-plugin-development
sakuradairong
Use when developing, debugging, or fixing AstrBot plugins and encountering import errors, async generator issues, plugin loading failures, or configuration…
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
autonomous-agent-harness
sakuradairong
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing.
SkillCFreshness: C★ 48Claude Code +9 - 0.563score
browser-qa
sakuradairong
Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.
SkillCFreshness: C★ 48Claude Code +9
Cite this page
agent-eval skill. Agent Mart. https://agentmart.dev/skills/sakuradairong-agent-eval (last updated 2026-10-24)