prd-taskmaster

Why this score

This repo hosts 10 skills, so its 606 stars are split between them (about 61 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 3a9756ad2f0b, with Cisco's open-source skill-scanner.

What its code does:

• Reads environment variables and sends network requests with them API clients do this to send your key to the service. Check which service it talks to.prd_taskmaster/llm_client.py:202 and 2 more
• Runs shell commands Common for dev tools. Read the commands it runs.README.md:1, docs/product/UX-SPEC.md:1, install.sh:1 and 5 more
• Makes network requestsSKILL.md, prd_taskmaster/llm_client.py:201 and 2 more
• Reads environment variables, where API keys usually liveprd_taskmaster/taskmaster.py:14, prd_taskmaster/tournament/goose_backend.py:324
• Uses dependencies without a pinned version A later version of a dependency could change what runs.mcp-server/requirements.txt:1 and 1 more

Web addresses in its code:

• raw.githubusercontent.cominstall.sh:179
• api.anthropic.comprd_taskmaster/llm_client.py:20
• api.github.cominstall.sh:35
• api.openai.comprd_taskmaster/llm_client.py:22
• atlas-ai.auhooks/mode_d_blocker.py:27
• generativelanguage.googleapis.comprd_taskmaster/llm_client.py:69
• task-master.devscripts/setup-taskmaster.sh:67

These are the sites named in the code, so it's where your data could go. It isn't a complete list: code can build addresses while it runs, and a few of these may be links rather than calls. Whatever you send also goes to the AI model you use.

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.