patchbot
Skill1 starsChanged 2 months agoMITView on GitHub
Scan for outdated dependencies and update them across Elixir, Rust, Node, Go, and Python ecosystems. TRIGGER when: user asks about outdated dependencies, "update deps", "dependency check", "what needs updating", or invokes "/patchbot". DO NOT TRIGGER when: user is working on patchbot agent code itself.
- Installs packages
Files
Patchbot
Polyglot dependency updater. Detects ecosystems from lockfiles, scans for outdated packages, updates + tests, and optionally creates PRs.
What You Get
- List of outdated dependencies per ecosystem with current/latest versions
- Automated update + test run (dry-run by default)
- Optional PR creation via
ghCLI
CLI Usage
# Detect ecosystems and list outdated deps
patchbot scan
# Filter to one ecosystem
patchbot scan --ecosystem rust
# Update and run tests
patchbot update --ecosystem node
# Update, test, and create a PR
patchbot pr --ecosystem elixir --base-branch main
# Dry run (preview only)
patchbot update --ecosystem python --dry-runSupported Ecosystems
| Ecosystem | Lockfiles | Update command | Test command |
| Elixir | mix.lock, mix.exs | mix deps.update --all | mix test |
| Rust | Cargo.lock, Cargo.toml | cargo update | cargo test |
| Node | package-lock.json, yarn.lock, pnpm-lock.yaml | npm update | npm test |
| Go | go.sum, go.mod | go get -u ./... | go test ./... |
| Python | requirements.txt, pyproject.toml, poetry.lock, uv.lock | pip install --upgrade | pytest |
MCP Server
patchbot serveConfigure MCP
Add to ~/.mcp.json:
{
"mcpServers": {
"patchbot": {
"command": "patchbot",
"args": ["serve"]
}
}
}MCP Tools
| Tool | Description |
patchbot_scan | Detect ecosystems and list all outdated deps |
patchbot_outdated | List outdated deps for a specific ecosystem |
patchbot_update | Run update + tests for an ecosystem (dry_run by default) |
Install
cd agents/patchbot
pip install -e .Requires ecosystem-specific tooling (mix, cargo, npm, go, pip/pytest).
In this repository61 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-reviewerSkill
- agent-designerSkill
- architectSkill
- autoresearchSkill
- blockscoutSkill
- ci-cd-pipeline-builderSkill
- claude-apiSkill
- codebase-onboardingSkill
- code-reviewSkill
- coingeckoSkill
- database-designerSkill
- dependency-auditorSkill
- design-uxSkill
- digestSkill
- droo-stackSkill
- env-secrets-managerSkill
- ethskillsSkill
- ffmpeg-asmSkill
- focused-fixSkill
- frontend-slop-auditSkill
- git-guardrailsSkill
- git-worktree-managerSkill
- humanizerSkill
- interface-designerSkill
- llm-cost-optimizerSkill
- local-browser-inspectorSkill
- mcp-server-builderSkill
- native-codeSkill
- nixSkill
- noirSkill
- observability-designerSkill
- performance-profilerSkill
- playwrightSkill
- polymathSkill
- prd-to-planSkill
- prepperSkill
- property-testingSkill
- qaSkill
- rag-architectSkill
- raxol-paymentsSkill
- raxolSkill
- raxol-symphonySkill
- recallSkill
- refactoring-strategySkill
- regenSkill
- releaseSkill
- security-auditorSkill
- self-improving-agentSkill
- sentinelSkill
- signozSkill
- skill-creatorSkill
- solidity-auditorSkill
- tddSkill
- tech-debt-trackerSkill
- ubiquitous-languageSkill
- watchdogSkill
- web-asset-generatorSkill
- writing-voiceSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

