renderer at a site. NEVER use
`mcp__claude-in-chrome__*` tools — they are slow, unreliable, and not what this
project uses.
**Server / sidebar / extension internals:** before editing `browse/src/server.ts`,
`extension
139k24d agoReviewMountCreate a free account to mount
ruff format`
- Pre-commit hooks: `uv run pre-commit run --all-files`
**MCPServer Mode:**
The library can run as an MCPserver for integration with Claude Desktop:
```bash
Steady7 mentions in 2 weeks
1 project uses a version of this
120k5mo agoReviewMountCreate a free account to mount
JuliusBrusseePipes a download into a shellCLAUDE.md
mcp — the Caveman MCPserver (Go core + launcher, Apache-2.0)
A thin **stdio JSON-RPC** adapter exposing the compression [engine](../engine/CLAUDE.md) as
five MCP tools to any host (Claude Code
Steady7 mentions in 2 weeks
No other project uses it yet
115k7mo agoReviewMountCreate a free account to mount
accepted through the raw retry, and a compressed PAYG conversation without MCP recovery that streams (the server-side retrieve tool cannot ride a stream, so the conversation stays raw from
Steady7 mentions in 2 weeks
No other project uses it yet
115k7mo agoReviewMountCreate a free account to mount
subagent stops
- `skills`: List of skill names to preload into agent context
- `mcpServers`: MCPservers for this subagent (server names or inline configs)
- `hooks`: Lifecycle hooks scoped to this subagent
No other project uses it yet
68k6mo agoReviewMountCreate a free account to mount
under 72 characters**
5. **Reference issues** in the footer when applicable (e.g., `Closes #123`)
## MCPServers Available
This project has OpenCode configured with:
1. **Context7** - Documentation search (`use context7
No other project uses it yet
67k10mo agoReviewMountCreate a free account to mount
name --type <fast|slow>` (slow = adds a data-backfill step).
- A read-only Postgres MCPserver is configured in `.mcp.json` for inspecting workspace data, metadata, and migration results. Writes
No other project uses it yet
60k37d agoReviewMountCreate a free account to mount
requiring a running server (live API or docker-compose)
- **hindsight-extensions/**: Server extension slots (tenancy/auth, HTTP endpoints, MCP tools, operation validators, memory defense)
- **hindsight-dev/**: Development tools and benchmarks
### Core
57k13d agoReviewMountCreate a free account to mount
guidelines and style enforcement
### clojure-mcp-lite tools
- **clj-nrepl-eval** - This is another good mechanism for running Clojure code on an nrepl server.
### Application database
- **[app-db-migrations](.claude/skills/app-db-migrations/SKILL.md
No other project uses it yet
50k10d agoReviewMountCreate a free account to mount
Build and test
The MCPserver source lives in `microsoft/playwright`, in `packages/playwright-core/src/tools/`.
This repo ships `@playwright/mcp`: `cli.js` and `index.js` run the server from the `playwright-core`
alpha that `package.json` pins
39k2d agoReviewMountCreate a free account to mount
affected`) instead of using the underlying tooling directly
- You have access to the Nx MCPserver and its tools, use them to help the user
- When answering questions about
No other project uses it yet
38k39d 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.