plugin-standards

plugin-standards is a cursor rule for Cursor from harness/harness-ai. It costs 1,069 tokens per session, scanned A, original, Apache-2.0.

A set of contribution rules for the Harness Cursor plugin, which adds Harness-related tools to the Cursor coding editor. It checks that plugin files, metadata, hooks, paths, and marketplace structure follow the required format.

In plain words
What is it for?
Use it when adding or editing plugin files, MCP server definitions, hooks, assets, or marketplace metadata in the Harness monorepo.
Why use it?
It prevents changes from breaking the plugin layout or failing the repository's validation checks.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc). Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it when adding or editing plugin files, MCP server definitions, hooks, assets, or marketplace metadata in the Harness monorepo.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/harness/harness-ai/plugin-standards
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.

Clone the repo
git clone --depth 1 https://github.com/harness/harness-ai

Made for: Cursor.

Wrote 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.

agentmods badge for plugin-standards

README.md
[![agentmods](https://agentmods.dev/badge/rules/harness/harness-ai/plugin-standards/github.svg)](https://agentmods.dev/rules/harness/harness-ai/plugin-standards)
Your own site
<a href="https://agentmods.dev/rules/harness/harness-ai/plugin-standards"><img src="https://agentmods.dev/badge/rules/harness/harness-ai/plugin-standards/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.

agentmods 80×15 button for plugin-standards

Your own site · 80×15
<a href="https://agentmods.dev/rules/harness/harness-ai/plugin-standards"><img src="https://agentmods.dev/badge/rules/harness/harness-ai/plugin-standards.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,069 This file is loaded in full into every session.
When invoked 1,069 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01069 $0.01069
Opus 5 $0.00535 $0.00535
Sonnet 5 $0.00214 $0.00214
Haiku 4.5 $0.00107 $0.00107

Measured 2d ago against content hash b171f62e5432, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

plugin-standards 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 2d 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.

plugins/cursor/rules/plugin-standards.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plugin Template Compliance

This directory (plugins/cursor/) is the Harness Cursor plugin shipped inside the harness-ai monorepo. The repo root lists it via .cursor-plugin/marketplace.json (Cursor multi-plugin layout). See CLAUDE.md / AGENTS.md for the full contribution guide. Canonical spec: https://github.com/cursor/plugin-template.

Structure — hard rules

  • Plugin name (.cursor-plugin/plugin.jsonname) matches ^[a-z0-9](?:[a-z0-9.-]*[a-z0-9])?$.
  • MCP server definitions live only in mcp.json at this plugin root. Never rename this file.
  • Hook definitions live only in hooks/hooks.json. Hook scripts live in scripts/.
  • Every referenced path (logo, hook command, skill assets) is a safe relative path — no .., no absolute paths.
  • Logo is committed to assets/ and referenced by relative path in plugin.json.
  • Do not add .cursor-plugin/marketplace.json here — the marketplace manifest lives only at the harness-ai repository root.
  • Do not add a plugins/ subdirectory inside this folder — it breaks the single-plugin subtree layout expected by scripts/validate-plugin.mjs.

Frontmatter — strict

  • rules/*.mdc — YAML frontmatter with description.
  • skills/*/SKILL.md — YAML frontmatter with name + description. name matches the directory.
  • Agents (agents/*.md), commands (commands/*.(md|mdc|markdown|txt)) — name + description.
  • Frontmatter opens with ---\n and closes with \n---\n. Missing keys fail the validator.

Skills

  • Path: skills/<kebab-case>/SKILL.md.
  • Use only the Harness MCP consolidated tools: harness_list, harness_get, harness_create, harness_update, harness_delete, harness_execute, harness_search, harness_describe, harness_schema, harness_diagnose, harness_status.
  • Required sections: ## Instructions, ## Examples, ## Performance Notes, ## Troubleshooting.
  • Every new skill gets a row in the README skill table.

Read the full file on GitHub · 70 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. 2d ago First seen · 70 lines · 1,069 tokens per session scan A b171f62e5432

Subscribe to this mod's changes

plugin-standards is a cursor rule published in the GitHub repository harness/harness-ai (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,069 tokens to every session, about $0.0053 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 2026-09-11.