typecheck # tsc --noEmit (npm run lint is an alias)
# Running the server
npm start # MCPserver in stdio mode
npm run start:http # MCPserver in HTTP mode
Steady19 mentions in 2 weeks
No other project uses it yet
23k2mo agoReviewMountCreate a free account to mount
access gates above.
- On Claude Code 2.1.x, `Claude Code-credentials` may contain only MCPserver OAuth state (`mcpOAuth`) with no `claudeAiOauth`. CodexBar treats that as an OAuth configuration error
23k5mo agoReviewMountCreate a free account to mount
repo.
Use `~/.config/ruler/` for personal preferences, local workflow shortcuts, API keys, and personal MCPservers:
```bash
ruler init --global
```
If it helps everyone working in this repo
Steady8 mentions in 2 weeks
No other project uses it yet
22k17mo agoReviewMountCreate a free account to mount
sync"
- "This module uses pattern Z for all API calls"
- "Tests require the dev server running on PORT 3000"
- "Field names must match the template exactly"
**Do NOT add:**
- Story
2 projects use a version of this
22k10mo agoReviewMountCreate a free account to mount
Stage 3 (高级开发工程师)**: Cross-platform development (WeChat mini-programs, Android apps, MCP)
## Development Commands
### Start Local Documentation Server
```bash
npm install # Install dependencies (first time only)
npm run dev # Start
No other project uses it yet
20k14d agoReviewMountCreate a free account to mount
requires auth)
uv run notebooklm --help # CLI
```
Always install the full extras set (`mcp`, `server`, `impersonate`); omitting them causes adapter suites to skip silently, masking errors and failing
No other project uses it yet
20k2mo agoReviewMountCreate a free account to mount
create so the analyst remembers per-dataset conventions across chats.
- **MCP connector**: add an `mcp_servers` entry plus an `mcp_toolset`. MCP tools default to `always_ask`, so they light
19k40d agoReviewMountCreate a free account to mount
repo from the inside (`resources: [{type: "github_repository", ...}]`)
- **MCP tools**: wire an external data MCPserver (`mcp_servers` + `mcp_toolset` on the agent, credentials via a vault, `vault
19k40d agoReviewMountCreate a free account to mount
with `curl` and a vault-substituted `$SLACK_BOT_TOKEN`, and reads GitHub through the MCPserver with a read-only token from the same vault.
```
cron (deployment.md) ──▶ session ──▶ agent.md
19k40d agoReviewMountCreate a free account to mount
tools**: e.g. Linear or GitHub MCP so the agent can act, not only reply (`mcp_servers` + `mcp_toolset` in `agents/linear-assistant.md`, a `vaults/ .yaml` for the credential, which `ant apply` manages
19k40d agoReviewMountCreate a free account to mount
MCPserver (TypeScript) × Claude Managed Agents
MCPserver that exposes Managed Agents session primitives as tools. Two entrypoints sharing one tool set: `src/server.ts` (stdio → Claude Desktop and Claude Code
Steady3 mentions in 2 weeks
No other project uses it yet
19k40d agoReviewMountCreate a free account to mount
dedupe key → the agent reads the issue and Seer's analysis through the Sentry MCPserver, reproduces, fixes, pushes `autofix/ ` → it calls the `open_pull_request` custom tool, which this
19k40d agoReviewMountCreate a free account to mount
checklist in order. It has the gotchas (vault always sends `Authorization: Bearer`, `allow_mcp_servers` vs `allowed_hosts`, archive-to-reauthorize, deployment pins an agent version, DST cron semantics, auto
19k40d agoReviewMountCreate a free account to mount
tools**: e.g. Slack or GitHub MCP so the agent can act, not only reply (`mcp_servers` + `mcp_toolset` in `agents/slack-assistant.md`, a `vaults/ .yaml` for the credential, which `ant apply` manages
19k40d agoReviewMountCreate a free account to mount
GitHub repository into an interactive Mermaid architecture diagram, plus narrated explainer videos, a public MCPserver and sponsor ad slots. It is **one Next.js 16 App Router application** (React
Steady5 mentions in 2 weeks
No other project uses it yet
18k25d agoReviewMountCreate a free account to mount
agentic.config.{ts,js,json}` files to define:
- Project name and metadata
- Origin adapter (MCPserver or OpenAPI spec)
- Tool configurations and permissions
- Pricing plans and rate limits
- Authentication requirements
18k17mo agoReviewMountCreate a free account to mount
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
CLAUDE.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.