orchestration of modular agents
SaferSkills independently audited agents (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This folder contains multiple small, self-contained agents. Each agent follows the same structure and documentation conventions so they are easy to run, extend, and schedule.
agents/<agent_name>/
README.md
agent.py
scripts/
digests/ # Optional output folderShared helpers live in:
agents/_shared/Use the template to bootstrap new agents:
agents/template/Or generate one quickly:
scripts/new_agent.sh <agent_name><agent_name>.py.README.md with purpose, usage, configuration, and scheduling info.scripts/ contains cron-ready helpers.newsDaily news summarizer that pulls from multiple RSS feeds, dedupes, prioritizes by recency/source diversity, and outputs a Markdown digest.
Run:
cd agents/news
python3 agent.pyTopics:
python3 agent.py --list-topics
python3 agent.py --topic techScheduler (cron-ready):
agents/news/scripts/run_daily.shmcpMinimal example of a tool-connected agent using the Model Context Protocol (MCP). Includes a server exposing tools and a client that calls them.
Run server:
cd agents/mcp
python3 server.pyRun client:
python3 agent.py --demo
### `template`
Starter scaffold for creating new agents quickly.If you move this repo, update any absolute paths inside agent scripts (for example in cron-ready scripts).
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.