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/Intense-Visions/harness-engineeringWrote 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/intense-visions/harness-engineering/use-harness-skills)<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>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 | $0.00478 | $0.00478 |
| Opus 5 | $0.00239 | $0.00239 |
| Sonnet 5 | $0.00096 | $0.00096 |
| Haiku 4.5 | $0.00048 | $0.00048 |
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.
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.mdor 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.
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.
- 4d ago First seen · 39 lines · 478 tokens per session scan A e133d7111d85
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.
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.