Our verdict
We have not reviewed claw-bench yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About claw-bench
The Definitive AI Agent Benchmark
Best for
Developers seeking a lightweight, open-source benchmark for evaluating AI agent skills.
Use cases
- Benchmarking AI agent capabilities against standardized skills
- Comparing different agent implementations or configurations
- Validating agent performance during development or before release
Notes
180 stars on GitHub. Last updated 2026-06-17. Licensed Apache-2.0.
Indexed from github-skill-md. Verified against the live GitHub repo.
Pros
- Open-source and accessible via GitHub
- Python-based, easy to integrate into existing workflows
- Focuses on skills, providing concrete evaluation criteria
Cons
- Limited community adoption given only 180 stars
- Scope may be narrow, focusing on skills rather than broader agent behaviors
- No evidence of active maintenance or extensive documentation
Key facts
What we have checked
- Days since the last commit
- 150
- GitHub forks
- 21
- GitHub stars
- 180
- Days to a first reply on issues
- 57.4
- Open issues
- 6
- Releases in the last 90 days
- 0
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
Stars and usage
How claw-bench is growing
180 to 180
Health and security
Is claw-bench looked after, and what do its setup files show
Health score
24 out of 100
| Part | Points | What we saw |
|---|---|---|
| Recent activity | 19.3 of 30 | Last push 150 days ago |
| Releases | 0 of 15 | 0 releases in 90 days |
| Issue replies | 0 of 20 | First reply in 57.4 days (median) |
| Maintainer | 0 of 15 | Owned by a single user |
| Official source | Not counted | MCP servers only |
Security check static checks
97 out of 100
- Low Sends data to a host outside the well-known APIs, host clawbench.net: skills/skill.md, line 265.
- Note No dependency list or install command was found in the skill, so there were no packages to look up on OSV.
Sources
Where this comes from
- GitHubRegistry
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
eval-engineering
langchain-ai
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge…
evaluating-llms-harness
Orchestra-Research
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent wi
google-agents-cli-eval
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
principle-explain-the-number
michael-denyer
Antigravity, Claude Code, Codex, Copilot, Gemini, Muse, OpenCode, Pi, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for ot
brain-in-the-fish
fabio-rovai
Score any document. Prove every claim.
eval-engineering
langchain-ai
Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable project World Knowledge…
review
zby
"Extend with llm, stabilise with code" - Prompts when you're exploring, Python when you're certain. Workers and tools form one function space—refactor between them.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.