chat-sdk-deploy-bot
AGENTS.md1 starsChanged 8 months agoApache-2.0View on GitHub
A deploy orchestrator built with Chat SDK and Vercel Workflow. Trigger deploys from Slack, gate production with approval, dispatch GitHub Actions, and notify GitHub and Linear when the run finishes. Use these skills when working on this project:
- Reads credentials
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- chat-sdkSkill
- slack-agentSkill
- workflowSkill
- chat-sdkSkill
- slack-agentSkill
- workflowSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 47
Use these skills when working on this project:
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Chat SDK Deploy Bot
A deploy orchestrator built with Chat SDK and Vercel Workflow. Trigger deploys from Slack, gate production with approval, dispatch GitHub Actions, and notify GitHub and Linear when the run finishes.
Stack
- Chat SDK (
chat+@chat-adapter/slack+@chat-adapter/github+@chat-adapter/linear+@chat-adapter/state-redis) — Multi-platform bot framework - Next.js (App Router) — Server and routing
- Vercel Workflow — Durable deploy orchestration
- Octokit — GitHub Actions dispatch and polling
- Linear SDK — Issue commenting and state transitions
- Vitest — Testing
- Ultracite — Linting and formatting
Project Structure
app/
api/
webhooks/
[platform]/
route.ts Dynamic webhook handler for Slack, GitHub, etc.
lib/
bot.ts Chat SDK bot instance with Slack, GitHub, and Linear adapters
deploy-card.ts Card builders for deploy status, approval, and summary
deploy-handlers.ts Slash command, action, and modal handlers
env.ts Environment variable validation
github.ts GitHub Actions dispatch, polling, and PR commenting
linear.ts Linear issue detection, commenting, and state transitions
permissions.ts Deploy permission checks (allowed users, approvers)Commands
pnpm dev # Start Next.js dev server
pnpm build # Production build
pnpm test # Run tests with coverage
pnpm type-check # Type-check without emitting
pnpm check # Lint and format check (ultracite)
pnpm fix # Auto-fix lint and format issues
pnpm validate # Run check + type-check + testSkills
Use these skills when working on this project:
- chat-sdk — Chat SDK API, event handlers, cards, modals, streaming, and adapters
- slack-agent — Slack-specific development patterns, testing, and deployment
- workflow — Vercel Workflow for durable, resumable execution
Key Patterns
- The bot registers Slack, GitHub, and (optionally) Linear adapters. Linear is conditionally enabled via
LINEAR_API_KEY. - Webhook route at
app/api/webhooks/[platform]/route.tshandles all platforms dynamically viabot.webhooks. - Chat SDK card components use JSX (
<Card>,<Button>, etc.) — the tsconfig setsjsxImportSource: "chat". - Deploy orchestration uses Vercel Workflow for durable, resumable execution (approval gates, polling).
- The bot uses
bot.onSlashCommand(),bot.onAction(), andbot.onModalSubmit()for interactivity.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

