Human-approved GitHub-to-Slack Review Router setup for workflows and AI agents
git clone https://github.com/Patrax/review-router-setup && cp review-router-setup/*.md ~/.claude/agents/Subagents overview
# Review Router Setup
[](https://github.com/Patrax/review-router-setup/actions/workflows/test.yml)
Create a GitHub-to-Slack Review Router connection from a workflow or AI coding session. The Action produces one short-lived browser link. Open it and sign in to Tenpace to claim and lock the exact repository, Slack destination, routing preset, and reviewer mention policy.
The Action never receives GitHub App credentials, Slack OAuth tokens, provider authorization codes, or the human's Tenpace session.
## Use the Action
Create `.github/workflows/review-router-setup.yml`:
```yaml
name: Set up Review Router
on:
workflow_dispatch:
permissions:
contents: read
id-token: write
jobs:
setup:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
- uses: Patrax/review-router-setup@v1
with:
slack-channel: pull-requests
preset: repo-watch
reviewer-mentions: all
```
Run the workflow. The same GitHub user who started it opens the **Continue Review Router setup** link in the job summary, signs in to Tenpace, completes the GitHub and Slack steps, and lets the page reconcile and verify the route with a real Slack delivery.
## Config as code
Instead of inputs, commit `.tenpace/review-router.yml`:
```yaml
version: 1
route:
slack-channel: pull-requests
preset: repo-watch
reviewer-mentions: all
```
You can also set `slack-workspace` when the Tenpace team has more than one connected workspace. Explicit Action inputs override the file.
## Inputs
- `slack-channel`: Slack channel name, with or without `#`. Required unless present in the config file.
- `slack-workspace`: Optional exact workspace name, Slack team ID, or Tenpace workspace ID.
- `preset`: `repo-watch`, `full-coverage`, or `team-activity`. Default: `repo-watch`.
- `reviewer-mentions`: `all`, `connected-only`, or `none`. Default: `all`.
- `config`: Config path. Default: `.tenpace/review-router.yml`.
## Outputs
- `setup-id`: Public setup-session ID.
- `setup-url`: Short-lived human authorization URL.
- `status`: Initial status, normally `awaiting_human`.
The machine setup token is masked and deliberately not exposed as an Action output. The displayed URL contains no claim secret: it is bound to the GitHub actor in the signed OIDC token, and that same GitHub user must open it. The browser flow can finish setup without putting a secret into another workflow step.
## Security model
GitHub Actions OIDC proves the repository and actor for the workflow run. It does not grant provider authority. Tenpace verifies the OIDC issuer, signature, audience, time window, repository and owner IDs, actor ID, subject, and repository binding. Action URLs contain no claim secret and can only be claimed by that GitHub actor.
The server creates an inert intent. A Tenpace user signs in and claims the setup URL, which atomically locks that exact intent version. The machine token cannot edit after claim; the person who claimed the setup can edit it, and saving creates and locks the new version in the same action. Provider OAuth stays in the browser and encrypted credentials stay on Tenpace.
Setup creation and application are idempotent. The final check sends one message through the same Slack delivery path used for pull request notifications.
See [SECURITY.md](SECURITY.md) for reporting and operational details.
## For coding agents
Read [AGENTS.md](AGENTS.md) before automating setup. Canonical machine-readable surfaces:
- [OpenAPI 3.1](https://api.tenpace.com/openapi.json)
- [Remote MCP](https://api.tenpace.com/mcp)
- [MCP Registry metadata](server.json)
- [Agent descriptor](https://api.tenpace.com/.well-known/tenpace-agent.json)
- [Raw Markdown guide](https://review-router.tenpace.com/docs/agent-setup.md)
- [llms.txt](https://review-router.tenpace.com/llms.txt)
No AI-discovery convention is universal, so the same workflow is described in the Action metadata, README, AGENTS.md, linked HTML/Markdown docs, OpenAPI, MCP, and well-known descriptor.
The remote MCP server is also published to the official MCP Registry as
`io.github.Patrax/review-router`
## License
MIT
What people ask about review-router-setup
What is Patrax/review-router-setup?
+
Patrax/review-router-setup is subagents for the Claude AI ecosystem. Human-approved GitHub-to-Slack Review Router setup for workflows and AI agents It has 0 GitHub stars and was last updated today.
How do I install review-router-setup?
+
You can install review-router-setup by cloning the repository (https://github.com/Patrax/review-router-setup) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is Patrax/review-router-setup safe to use?
+
Patrax/review-router-setup has not been audited yet by our security agent. Review the original repository on GitHub before using it in production.
Who maintains Patrax/review-router-setup?
+
Patrax/review-router-setup is maintained by Patrax. The last recorded GitHub activity is from today, with 0 open issues.
Are there alternatives to review-router-setup?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy review-router-setup to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/patrax-review-router-setup)<a href="https://claudewave.com/repo/patrax-review-router-setup"><img src="https://claudewave.com/api/badge/patrax-review-router-setup" alt="Featured on ClaudeWave: Patrax/review-router-setup" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.