CockroachDB Plugin for Claude Code connects Claude Code to CockroachDB clusters, which are distributed databases, so the agent can work with schemas, SQL queries, and database operations. It is intended for developers, database administrators, and operators working with self-hosted or CockroachDB Cloud deployments. The catalogue entries provide its MCP connections, specialized agents, skills, and safety hooks.
Borrowing it
Nothing to install: this file belongs to cockroachdb/claude-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cockroachdb/claude-plugin/main/AGENTS.mdgit clone --depth 1 https://github.com/cockroachdb/claude-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/cockroachdb/claude-plugin/agents-md)<a href="https://agentmods.dev/instructions/cockroachdb/claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/cockroachdb/claude-plugin/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/cockroachdb/claude-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/cockroachdb/claude-plugin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00749 | $0.00749 |
| Opus 5.5 | $0.00300 | $0.00300 |
| Sonnet 5.5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
claude-plugin AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for claude-plugin
Guidance for AI coding assistants (and new contributors) working in this repo. It complements CONTRIBUTING.md; read that first for setup and the full workflow.
What this repo is
The CockroachDB plugin for Claude Code: MCP backends (.mcp.json + tools.yaml), agents (agents/), skills (skills/), and safety hooks (hooks/hooks.json + scripts/).
Rules that prevent breakage
- Never edit
skills/by hand. Skills are synced from the cockroachdb-skills submodule by a weekly workflow that also regenerates theskillsarray in.claude-plugin/plugin.json. Changes there get overwritten. Contribute skills upstream instead. - Never bump versions by hand. Release Please owns
versionin.claude-plugin/plugin.json,.release-please-manifest.json, andCHANGELOG.md. Use conventional commits:fix:/feat:cut a release,chore:/docs:do not (and that is fine, because installs pull from git, not release tarballs). - Keep the hook command pattern. Hook commands load their script through a
runpybootstrap with a\\?\long-path prefix on Windows and a trailing; exit 0. This is load-bearing: it survives plugin cache paths past Windows MAX_PATH (issue #20), hosts that fail to substitute${CLAUDE_PLUGIN_ROOT}(issue #23), and current Claude Code, which exportsCLAUDE_PLUGIN_ROOTinstead of substituting it in shell-form commands, so the bootstrap falls back to the environment variable. A hook must never surface an error on every edit; when the interpreter cannot even open the script, it must fail open. The exact pattern is documented in CONTRIBUTING. - Use
${VAR:-default}in.mcp.json, never a bare${VAR}. An unset bare reference reaches the server as literal text (issue #27). Toolbox uses an empty value as-is instead of its default, so connection settings need non-empty defaults that matchtools.yaml. - Match plugin MCP tools by their scoped name. Claude Code names them
mcp__plugin_cockroachdb_<server>__<tool>, and a hook matcher that lists only the baremcp__<server>__<tool>name never fires for marketplace installs. - Hook scripts are Python 3 stdlib only, read JSON on stdin, write JSON on stdout, and always exit 0 (blocking is signaled via
hookSpecificOutput.permissionDecision, not exit codes). - No counts in descriptions. Do not write "three agents" or "33 skills" anywhere; counts go stale. Name the things instead.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 14d ago Changed · +2 lines · +155 tokens per session 649850c1c566
- 1mo ago First seen · 30 lines · 594 tokens per session scan A a862c9b92ba6
claude-plugin AGENTS.md is an instructions file published in the GitHub repository cockroachdb/claude-plugin (4 stars, last pushed 15d ago), licensed Apache-2.0. It adds 749 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).