agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or RAG (that is `building-agents`).
Why this score
This repo hosts 10 skills, so its 230 stars are split between them (about 23 each) for scoring.
Popularity score: 62/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank
Security
Scanned Oct 20, 2026 at commit f5ac957c271b, with Cisco's open-source skill-scanner.
What its code does:
- Runs shell commands Common for dev tools. Read the commands it runs.SKILL.md:49 and 1 more
A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan
Alternatives
Other makers' add-ons that do the same job, next to this one.
| Name | Score | Stars | Context | Updated |
|---|---|---|---|---|
| This oneagent-safety ericrisco/rsc-harness · Skill | 62 | ★ 230 | ≈91 always | 16d ago |
| path-safety microsoft/data-formulator · Skill Both about safety | 84 | ★ 18k | ≈24 always | 16d ago |
| safety-net kenryu42/cc-safety-net · Plugin Both about safety | 81 | ★ 1.9k | not measured | today |
| audit-ui-thread-safety flutter/flutter-intellij · Skill Both about safety | 73 | ★ 2.0k | ≈44 always | 19d ago |
| gate-worktree-git-safety kunchenguid/no-mistakes · Skill Both about safety | 80 | ★ 8.9k | ≈40 always | 17d ago |
| async-safety zakariaf/Flutter-Skills · Skill Both about safety | 53 | ★ 58 | ≈153 always | 1mo ago |