Fix Snyk vulnerabilities and open PRs automatically
A developer built a Claude Code/Cursor workflow that reads vulnerability tickets, updates dependencies and lockfiles, opens PRs and monitors CI, with merging kept manual. ·
Done withClaude CodeCursor
- What they did
- At CertifyOS, the developer built a Claude Code/Cursor workflow for Snyk vulnerability tickets. It reads each ticket, identifies the dependency fix, updates the lockfiles, opens a PR and monitors CI. Merging stays manual, so a person reviews and approves every change.
- How it went
- Weekly remediation effort dropped from 6–7 hours to around 1–1.5 hours, according to the developer. The source is a job-seeking post, so there are no further details on failures or how the workflow is built.
- Worth knowing
- Keeping merges manual left a human check on every automated dependency change, and the time savings came with that check in place.
Try it yourself with Claude Code
Read the open vulnerability tickets in [Snyk project or ticket queue] for the repo at [repo path]. For each one, update the affected dependency and lockfile, run [test command], and open a separate pull request describing the fix, then watch CI and report any failures. Do not merge anything, and show me the list of planned PRs before you push or open the first one.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: HN · Nov 2, 2026
Related use cases
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Build and balance a live Telegram RPG
A non-coding PM had Claude Code write a Telegram RPG bot, deploy it over SSH, and run tens of thousands of test fights to rebalance classes.
Find code faster with a local search agent
A small local agent navigates ColGrep multivector code search and reads files to find things quicker and cheaper, and can be plugged into Claude Code.
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Build a budgeting app from a single prompt
A low-coder used Replit Agent to build a 'Budget Buddy' with category budgets, a spending dashboard and expense log in about 20 minutes, using half their monthly credits.
Build specs through automated multi-agent verification and review loops
A developer writes a spec, then lets an implementation engine build it with review rounds from different agents and models, triaging issues and looping until the code meets spec.
Custom agent
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.