agentmods.dev

claude-plugin AGENTS.md

Repository instructions for working on CockroachDB’s Claude Code plugin, which connects coding assistants to tools, skills, agents, and safety hooks. It explains the project structure and rules that prevent changes from being overwritten or releases from breaking.

In plain words
What is it for?
Use it when changing the plugin, its tools, agents, skills, hooks, tests, or documentation. It also explains how to follow the repository’s testing and writing conventions.
Why use it?
It gives contributors and coding agents the project-specific rules they need before editing code. This avoids losing synced changes, mishandling versions, or breaking required hook behavior.

Instructions file for CodexOpenCode

4 1mo ago A scan 594 tokens original Apache-2.0
View the source file cockroachdb/claude-plugin
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cockroachdb/claude-plugin/agents-md
Clone the repo
git clone --depth 1 https://github.com/cockroachdb/claude-plugin

Made for: Codex, OpenCode.

Per session 594 This file is loaded in full into every session.
When invoked 594 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00594 $0.00594
Opus 5 $0.00297 $0.00297
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00059 $0.00059

Measured yesterday against content hash a862c9b92ba6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

AGENTS.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 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 the skills array in .claude-plugin/plugin.json. Changes there get overwritten. Contribute skills upstream instead.
  • Never bump versions by hand. Release Please owns version in .claude-plugin/plugin.json, .release-please-manifest.json, and CHANGELOG.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 runpy bootstrap 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) and hosts that fail to substitute ${CLAUDE_PLUGIN_ROOT} (issue #23). 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.
  • 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.

Testing

Run the hook regression suite before touching anything under hooks/ or scripts/:

bash scripts/test-hooks.sh

Read the full file on GitHub · 30 lines

Changes

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.

  1. yesterday First seen · 30 lines · 594 tokens per session scan A a862c9b92ba6

Subscribe to this mod's changes

claude-plugin AGENTS.md is an instructions file published in the GitHub repository cockroachdb/claude-plugin (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 594 tokens to every session, about $0.0030 per session on Opus 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.

TestingWriting and docsclaudecockroach-cloudcockroachdbdeveloper-tools
Related

Other instructions, from other repositories

cursor-plugin AGENTS.md

AGENTS.md instructions for cockroachdb/cursor-plugin, covering agent instructions for cursor-plugin, what this repo is, rules that prevent breakage and writing style.

cockroachdb/cursor-plugin · 360 tokens

cursor-plugin CLAUDE.md

Claude Code instructions for cockroachdb/cursor-plugin, a project described as: CockroachDB development plugin for Cursor.

cockroachdb/cursor-plugin · 5 tokens

mcp-toolbox GEMINI.md

Gemini CLI instructions for googleapis/mcp-toolbox, covering mcp toolbox context & style guide, project overview, tech stack, key directories and development workflow.

googleapis/mcp-toolbox · 3,611 tokens

mcp-toolbox AGENTS.md

AGENTS.md instructions for googleapis/mcp-toolbox, a project described as: MCP Toolbox for Databases is an open source MCP server for databases.

googleapis/mcp-toolbox · 4 tokens

cockroach CLAUDE.md

Claude Code instructions for cockroachdb/cockroach, covering claude.md, cockroachdb development environment, essential commands, build package ./pkg/util/log and build the tests in package ./pkg/util/log.

cockroachdb/cockroach · 1,292 tokens

mcp-toolbox CLAUDE.md

Claude Code instructions for googleapis/mcp-toolbox, a project described as: MCP Toolbox for Databases is an open source MCP server for databases.

googleapis/mcp-toolbox · 4 tokens