gadievron

Greenlight — Development skill for Claude Code

Development community

Refusal handling skill for vulnerability research evals.

How to install Greenlight

This entry records only its repository, not the path inside it, so there is no exact command to give. Open gadievron/greenlight and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Greenlight does

Refusal handling skill for vulnerability research evals.

Alternatives in Development

OpenAI Codex CLI — (Rust implementation) 67.8k ★
Scientific Agent Skills — A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing 18.7k ★
Industry Research — 行业投资研究：产业链全景扫描 + 四大师个股分析框架 15.9k ★

README

greenlight — refusal handling skill for vulnerability research evals

What this is

Using the greenlight skill, you'd be able to autonomously handle Opus 4.7's refusals in security research-type evals. It was created for benchmarking purposes, mapping out where Claude Code's guardrails trigger exploitation-related refusals, and where they can't be relied upon.

While validated only on Opus 4.7, the methodology should generalize to other models, but every model requires its own re-validation. Remember: this is a proof of concept, not rigorous research. Specifically, if your bench distribution differs from this one (different model, different target class, uniform rather than bimodal re-roll), re-validate before considering the retry-cap recommendation.

Author: Gadi Evron (@gadievron)

Who it's for

You are doing authorized AI-safety / security refusal research in cyber security, and are building a harness that runs Claude (via `claude-agent-sdk` or the Claude Code CLI), for purposes such as CVE reproductions, hardened-service testing, vulnerability-class benchmarks, exploitation capability measurements, and similar, and you are hitting one of these:

Sessions fail with Exception("Command failed with exit code 1") and you can't tell if it was a transport flake, a rate-limit, or a content-policy refusal.
Your bench retries refused sessions blindly and wastes tokens on identical re-runs.

Where to start

If you are…	Start at…
A researcher / harness author wanting the validated minimal skill (high evidence bar)	`SKILL.md` (v3 canonical)
A researcher / harness author wanting a richer skill at lower evidence bar (varied capabilities)	`SKILL-v5.md`
A researcher wanting to build your own skill section-by-section (template)	`SKILL-modular.md`

Installation

# Drop into another research harness:
cp -r refusal-handling /path/to/your/harness/skills/

# Or make available in every Claude Code session on your machine:
c