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.
git clone --depth 1 https://github.com/harness/harness-aiWrote 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/rules/harness/harness-ai/plugin-standards)<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.
<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>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 | $0.01069 | $0.01069 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
plugin-standards scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Template Compliance
This directory (plugins/cursor/) is the Harness Cursor plugin shipped inside the harness-ai monorepo. The repo root lists it via .cursor-plugin/marketplace.json (Cursor multi-plugin layout). See CLAUDE.md / AGENTS.md for the full contribution guide. Canonical spec: https://github.com/cursor/plugin-template.
Structure — hard rules
- Plugin name (
.cursor-plugin/plugin.json→name) matches^[a-z0-9](?:[a-z0-9.-]*[a-z0-9])?$. - MCP server definitions live only in
mcp.jsonat this plugin root. Never rename this file. - Hook definitions live only in
hooks/hooks.json. Hook scripts live inscripts/. - 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 inplugin.json. - Do not add
.cursor-plugin/marketplace.jsonhere — 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 byscripts/validate-plugin.mjs.
Frontmatter — strict
rules/*.mdc— YAML frontmatter withdescription.skills/*/SKILL.md— YAML frontmatter withname+description.namematches the directory.- Agents (
agents/*.md), commands (commands/*.(md|mdc|markdown|txt)) —name+description. - Frontmatter opens with
---\nand 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.
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.
- 2d ago First seen · 70 lines · 1,069 tokens per session scan A b171f62e5432
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.