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 rules/cosmic-construct/hermes-cursor-harness/hermes-harnessgit clone --depth 1 https://github.com/Cosmic-Construct/hermes-cursor-harnessWrote 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/cosmic-construct/hermes-cursor-harness/hermes-harness)<a href="https://agentmods.dev/rules/cosmic-construct/hermes-cursor-harness/hermes-harness"><img src="https://agentmods.dev/badge/rules/cosmic-construct/hermes-cursor-harness/hermes-harness.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 | $0.00012 | $0.00198 |
| Opus 5 | $0.00006 | $0.00099 |
| Sonnet 5 | $0.00002 | $0.00040 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
hermes-harness 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
When a task is being driven by Hermes, preserve Hermes as the outer runtime: session state, approval policy, high-level intent, memory context, and final transcript belong to Hermes. Use Cursor for repo-local coding work, tool calls, analysis, edits, and shell execution.
If the Hermes Cursor Harness MCP server is available, use its read-only tools to inspect Hermes session status, project context, and recent harness events before making broad repo changes. These tools are context lookups, not approval to edit files.
If hermes_cursor_sdk_status is available, it can confirm whether Hermes is
driving you through the official Cursor SDK bridge.
When Hermes supplied a permission mode, keep your work inside that mode. In plan or ask mode, do not edit files. In edit mode, make focused repo changes and report the exact files touched.
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 · 22 lines · 12 tokens per session scan A b2cce277130a
hermes-harness is a cursor rule published in the GitHub repository Cosmic-Construct/hermes-cursor-harness (5 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 198 once invoked, about $0.0001 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 cursor rules, from other repositories
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.
family-instance-domain-actions
Family instance domain action implementation patterns.