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.
npx skills add NoesisVision/nasde-toolkit --skill nasde-benchmark-from-public-reposgit clone --depth 1 https://github.com/NoesisVision/nasde-toolkitWrote 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/skills/noesisvision/nasde-toolkit/nasde-benchmark-from-public-repos)<a href="https://agentmods.dev/skills/noesisvision/nasde-toolkit/nasde-benchmark-from-public-repos"><img src="https://agentmods.dev/badge/skills/noesisvision/nasde-toolkit/nasde-benchmark-from-public-repos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/noesisvision/nasde-toolkit/nasde-benchmark-from-public-repos"><img src="https://agentmods.dev/badge/skills/noesisvision/nasde-toolkit/nasde-benchmark-from-public-repos.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00131 | $0.03206 |
| Opus 5 | $0.00066 | $0.01603 |
| Sonnet 5 | $0.00026 | $0.00641 |
| Haiku 4.5 | $0.00013 | $0.00321 |
Grade C, and why
nasde-benchmark-from-public-repos scanned grade C with 2 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
RUN apt-get update && apt-get install -y git curl wget ca-certificates && rm -rf /var/lib/apt/lists/* Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
RUN apt-get update && apt-get install -y git curl wget ca-certificates && rm -rf /var/lib/apt/lists/* How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NASDE Benchmark from Public Repos
Build a diverse NASDE benchmark by curating tasks from multiple public GitHub repositories. Designed for validating universal skills — skills that should work across different languages, frameworks, project sizes, and architectural styles.
Prerequisites
- An existing NASDE benchmark project (run
nasde initfirst, or use thenasde-benchmark-creatorskill) - A clear description of the skill being evaluated (what it does, what kinds of tasks it helps with)
- Internet access (to browse and clone public repositories)
Critical: line endings on Windows (read this first)
When generating tests/test.sh, solution/solve.sh, or environment/Dockerfile on a Windows host, write them with LF line endings or every trial fails with bash: required file not found (the kernel reads #!/bin/bash\r as the shebang). See the full explanation and .gitattributes template in the nasde-benchmark-creator skill.
Quick rules:
- The benchmark project MUST have a
.gitattributesenforcing*.sh text eol=lfandDockerfile text eol=lf.nasde initcreates this. If the existing project lacks it, create.gitattributesbefore generating any task files. - When writing files programmatically, use
path.write_text(content, encoding="utf-8", newline="")— never the bare default which translates\n→\r\non Windows. - Sanity-check after generation:
find tasks/<new-task> -name '*.sh' -o -name 'Dockerfile' | xargs file | grep CRLFshould print nothing.
Step 1: Understand the skill under test
Ask the user:
- What does the skill do? (e.g., "helps agents refactor code", "guides test writing", "enforces DDD patterns")
- What languages/frameworks should it support? (e.g., "Python, TypeScript, and Go" or "any language")
- What task types exercise the skill? (e.g., "extract method, rename module, split class" for a refactoring skill)
- Are there known weak spots? (e.g., "seems to struggle with large files" or "not sure about Rust")
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.
- 11d ago First seen · 313 lines · 131 tokens per session scan C dd8dec2fd1f1
nasde-benchmark-from-public-repos is a skill published in the GitHub repository NoesisVision/nasde-toolkit (13 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 3,206 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
generate-tests
Generate EvalView test cases — either from a SKILL.md file using LLM-powered generation, or by capturing real agent interactions through a proxy.
run-eval
Run EvalView regression checks against golden baselines to detect regressions in AI agent behavior after code, prompt, or model changes.
watch
Start EvalView watch mode to automatically re-run regression checks whenever project files change.
api-testing
REST/GraphQL API testing with automated validation — test endpoints, validate responses, check status codes, and ensure API contracts.
agent-eval-coverage
Use when the user wants to know whether their AI/agent repo has the evals and tests needed to trust changes — checking for golden/regression test sets, prompt regression tests, LLM-as-judge, behavioral & tool-use tests, hallucination/safety checks, CI gating, and metrics. Triggers on "do I have enough evals", "how do…
checkup
Give your AI agent a professional health checkup (AgentVitals). Use when the user asks the agent to run a checkup / test itself / benchmark itself ("run a checkup", "check your vitals", "test yourself", "how stable are you", "/checkup"), or an advanced personality checkup (backbone, proactivity, creativity). 给 AI…