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.
npx agentmods add instructions/cockroachdb/cursor-plugin/agents-mdgit clone --depth 1 https://github.com/cockroachdb/cursor-pluginWhat 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 | $0.00360 | $0.00360 |
| Opus 5 | $0.00180 | $0.00180 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
cursor-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.
What it actually says
Agent instructions for cursor-plugin
Guidance for AI coding assistants (and new contributors) working in this repo. It complements CONTRIBUTING.md.
What this repo is
The CockroachDB plugin for Cursor: MCP backends (mcp.json + tools.yaml), best-practice rules (rules/*.mdc), and skills (skills/).
Rules that prevent breakage
- This plugin has no hooks. Cursor does not run the PreToolUse/PostToolUse hook mechanism that the Claude Code plugin uses; safety and best-practice guidance ships as Cursor rules in
rules/. Never describe this plugin as having "safety hooks" (the description says "safety and best-practice rules" on purpose), and do not porthooks.jsonhere. - Never edit
skills/by hand. Skills are synced from the cockroachdb-skills submodule by a weekly workflow that also regenerates theskillsarray in.cursor-plugin/plugin.json. Contribute skills upstream instead. - Never bump versions by hand. Release Please owns
versionin.cursor-plugin/plugin.json,.release-please-manifest.json, andCHANGELOG.md. Conventional commits:fix:/feat:cut a release,chore:/docs:do not. - No counts in descriptions. Do not write "three agents" or "N skills" anywhere; counts go stale. Name the things instead.
Writing style
Commit messages and PR bodies in a plain human voice: conventional-commit prefixes, no AI attribution trailers, plain punctuation.
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.
- yesterday First seen · 19 lines · 360 tokens per session scan A 3b0d95bd2d02
cursor-plugin AGENTS.md is an instructions file published in the GitHub repository cockroachdb/cursor-plugin (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 360 tokens to every session, about $0.0018 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 2026-08-31.
Other instructions, from other repositories
claude-plugin AGENTS.md
Instructions for cockroachdb/claude-plugin, covering agent instructions for claude-plugin, what this repo is, rules that prevent breakage, testing and writing style.
claude-plugin CLAUDE.md
Instructions for cockroachdb/claude-plugin, a project described as: CockroachDB development plugin for Claude.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.