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/zackiles/deno-kitWrote 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/zackiles/deno-kit/finalize)<a href="https://agentmods.dev/rules/zackiles/deno-kit/finalize"><img src="https://agentmods.dev/badge/rules/zackiles/deno-kit/finalize/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/zackiles/deno-kit/finalize"><img src="https://agentmods.dev/badge/rules/zackiles/deno-kit/finalize.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 | $0.00007 | $0.00347 |
| Opus 5.5 | $0.00003 | $0.00139 |
| Sonnet 5.5 | $0.00001 | $0.00069 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
finalize 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 1mo 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
Steps to Follow at the End of Generating Code or Making Changes
-
Review all changes made in this turn of the message to see if the files or dependent files we modified had bugs, linting errors, or issues introduced from our changes, or if the objective wasn't met, and fix it.
-
Remove old, dead, or otherwise unused code that is clearly related to our change. Otherwise, let the user know if you find unreferenced code that wasn't related to our change that they might want you to clean up.
-
Update project documentation that is clearly related to this work or refers to this work if our changes made information related to the change outdated or innacurate.
-
After you've compelted all steps, at the end of your message confirming to the human the work was done, provide them the following two options if they'd like to continue the conversation: a) ask if they'd like you to run {x} test to validate the thing you did if a test or a way to check if the work was does exists, and b) ask if they'd like you to increase the depth and breadth of your investgiation into validating if the previous changes were applied correctly and didn't introduce any regressions. If they say yes, then repeat these steps by exanding deeper into individual code files, and outward into related files in the graph.
NOTE: If you feel a round of investigation was unable to identify anything concderning ensure you let the user know that and provide them evidence of why you think there is nothing concerning.
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.
- 1mo ago First seen · 15 lines · 7 tokens per session scan A d1cfa1bd4bef
finalize is a cursor rule published in the GitHub repository zackiles/deno-kit (3 stars, last pushed 7mo ago), licensed MIT. It adds 7 tokens to every session and 347 once invoked, about $0.0000 per session on Opus 5.5. 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
orchestrator
Use when coordinating AI agents through a pipeline — orchestrator role instructions.
workspace
Multi-agent workspace context — loaded on every session.
engineering-agent-prompt-engineer
Use when writing, reviewing, or improving prompts for AI agents — agent role design and prompt engineering.
deno-lint
Deno lint error guidance.
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.