use-harness-skills

use-harness-skills is a cursor rule for Cursor from Intense-Visions/harness-engineering. It costs 478 tokens per session, scanned A, original, MIT.

A project rule that tells the agent to use predefined harness skills and workflows when they match the task.

In plain words
What is it for?
It is for routing feature work, code reviews, architecture checks, project setup, cleanup, and mechanical verification through named skills.
Why use it?
It reduces improvised work that could skip established steps for planning, reviews, cleanup, documentation, or verification.

Cursor rule for Cursor

Written for Cursor: a Cursor plugin manifest. Also seen: mentions AGENTS.md.

Good fit It is for routing feature work, code reviews, architecture checks, project setup, cleanup, and mechanical verification through named skills.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/intense-visions/harness-engineering/use-harness-skills
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/Intense-Visions/harness-engineering

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 use-harness-skills

README.md
[![agentmods](https://agentmods.dev/badge/rules/intense-visions/harness-engineering/use-harness-skills.svg)](https://agentmods.dev/rules/intense-visions/harness-engineering/use-harness-skills)
Your own site
<a href="https://agentmods.dev/rules/intense-visions/harness-engineering/use-harness-skills"><img src="https://agentmods.dev/badge/rules/intense-visions/harness-engineering/use-harness-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 478 This file is loaded in full into every session.
When invoked 478 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 $0.00478 $0.00478
Opus 5 $0.00239 $0.00239
Sonnet 5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 4d ago against content hash e133d7111d85, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

use-harness-skills 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 4d 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.

.cursor-plugin/rules/use-harness-skills.mdc · 39 lines

What it actually says

Use harness skills, don't freelance

When a task matches a harness skill, invoke the skill instead of improvising. Skills capture workflows that survived prior incidents — bypassing them often re-introduces the same bugs.

Common matches

Task Skill / command
Implementing a new feature /harness:planning then /harness:execution
Reviewing changes /harness:code-review
Detecting structural risk /harness:hotspot-detector or /harness:dependency-health
Bootstrapping or instrumenting a project /harness:initialize-project
Cleaning dead code or fixing patterns /harness:cleanup-dead-code or /harness:codebase-cleanup
Verifying changes mechanically /harness:verify
Doc drift detection /harness:detect-doc-drift
Architecture decisions /harness:architecture-advisor
Performance enforcement /harness:perf

For a complete list, run npx @harness-engineering/cli skills list or check the marketplace plugin's commands/ directory.

When to skip a skill

  • The task is genuinely outside the skill's scope (e.g., the skill doesn't cover your stack).
  • The human explicitly asked for a different approach.
  • The skill's flow has been overridden in this repo's AGENTS.md or skill calibration files.

In all three cases, state the skip explicitly: "Skipping /harness:code-review because the change is documentation-only — running just format:check instead." Then proceed.

What you must not do

  • Never assume "I know what code review is, I don't need the skill." Skills carry calibration data (per-repo learnings, false-positive history, severity rules) you don't have in context.
  • Never replace a skill's structured output with prose. The skill's output format is what downstream automation expects.
  • Never invoke the skill and then ignore its findings. If the finding is wrong, push back with evidence; don't silently drop it.
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. 4d ago First seen · 39 lines · 478 tokens per session scan A e133d7111d85

Subscribe to this mod's changes

use-harness-skills is a cursor rule published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 478 tokens to every session, about $0.0024 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 2026-09-03.