create-repo-agent
create-repo-agent is an Agent security & guardrails skill for AI agents, published by langfuse in the langfuse repository on GitHub. Skillspace rates create-repo-agent C (70/100) and it passed the safety scan; a judge model has also reviewed it.
Use when designing, implementing, reviewing, or hardening Langfuse repo-owned autonomous agents, especially GitHub Actions that invoke Claude, Codex, or another LLM agent on a schedule or workflow_dispatch, create pull requests, update workflow prompts or allowlists, handle GitHub tokens/secrets, use untrusted web content, or self-improve repo agent instructions.
- Grade
- C
- Quality
- 70 / 100
- Safety
- Passed
- GitHub stars
- 31,215
Placed #1 of 6 in the judged category final for Agent security & guardrails.
Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Repo-internal: written for the repository it lives in. Explicitly about Langfuse repo-owned agents and workflows
Judge review
Placed #1 of 6 in the judged category final for Agent security & guardrails.
- Trigger
92 92 - Instructions
95 95 - Specificity
92 92 - Safety
96 96 - Disclosure
85 85 - Maintenance
88 88
The strongest security design in the batch: a least-privilege split between a read-only audit job and a separate publisher, plus explicit non-negotiables including never trusting prompt instructions as the sole security boundary.
What the scanner flagged
- mentions secrets in text
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.