Loading pattern preview
BlocksAgent Patterns
Just Bash Skills Agent
Just Bash Skills Agent
Minimal ToolLoopAgent chat demo: on-call-style skills (incident triage + stakeholder comms) on disk, skill tool loads SKILL.md + paths, readFile pulls reference checklists and templates from the sandbox.
Use this when an ops or on-call assistant should load markdown runbooks and checklists from disk as skills, using only a skill tool and readFile.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Discover on-disk skill packs with a skill tool
- Pull checklists and templates via sandboxed readFile
- Keep the demo minimal with skill and readFile only
- Stream an ops-style ToolLoopAgent chat UI
Use cases
Products and workflows this pattern is designed to support.
- Incident triage runbook copilots
- Stakeholder communication assistants
- Internal ops agents backed by markdown skills
- Teaching skill loading without full bash access
Compare with
Similar patterns, and when each one is the better fit.
Marketing agent with skills + readFileChat UI wired to a ToolLoopAgent that loads filesystem skills and exposes readFile on the skill sandbox—demo includes ad-creative, copywriting, and paid-ads sk…
Tool ExecutionUse this when your chat app calls tools and you want each call's input, output, and status rendered inline as it streams.
Human in the Loop Plan Builder AgentUses ToolLoopAgent pattern to gather requirements and generate plans. Generates markdown plans with structured todo lists.
Call Options: prepareCallUse this when you need to inject per-user context, such as retrieved documents, into an agent's instructions at call time using typed call options.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
AI_GATEWAY_API_KEYGet key
Capabilities
AI SDK APIs
ToolLoopAgentcreateAgentUIStreamResponsegatewaystepCountIsProviders
Claude
Files added
9 files
app/page.tsxapp/layout.tsxapp/api/chat/route.tsapp/api/chat/skills-directory.tscomponents/chat-form.tsxapp/skills/incident-triage/SKILL.mdapp/skills/incident-triage/references/first-30-minutes.mdapp/skills/stakeholder-comms/SKILL.mdapp/skills/stakeholder-comms/references/update-template.md
Dependencies
8 total
npm packages
5AISDKbash-toollucide-reactNext.jsReact
Registry components
emptyscroll-areatooltip
Critical files
1 file
chat/route.tsToolLoopAgent with createSkillTool + createBashTool (readFile only): expose skill + readFile, stream with createAgentUIStreamResponse.
Requirements
- Complexity
- Intermediate
- Setup time
- ~15 minutes
- Node
- 24+
- Memory
- 512MB
bash-tool runtime
