agent-config-test-confirmation

agent-config-test-confirmation is a cursor rule for Cursor from dfirtnt/Huntable-CTI-Studio. It costs 271 tokens per session, scanned A, original, MIT.

A rule requiring explicit user approval for tests that change active agent settings. These settings include prompts, workflows, provider choices, and model configuration.

In plain words
What is it for?
Use it before creating or running tests that persist changes to agent configuration; ask for confirmation before proceeding.
Why use it?
It prevents a test run from changing the live configuration without the user knowing and agreeing to it.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it before creating or running tests that persist changes to agent configuration; ask for confirmation before proceeding.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation
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/dfirtnt/Huntable-CTI-Studio

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 agent-config-test-confirmation

README.md
[![agentmods](https://agentmods.dev/badge/rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation/github.svg)](https://agentmods.dev/rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation)
Your own site
<a href="https://agentmods.dev/rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation"><img src="https://agentmods.dev/badge/rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation/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.

agentmods 80×15 button for agent-config-test-confirmation

Your own site · 80×15
<a href="https://agentmods.dev/rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation"><img src="https://agentmods.dev/badge/rules/dfirtnt/huntable-cti-studio/agent-config-test-confirmation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 271 This file is loaded in full into every session.
When invoked 271 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 $0.00271 $0.00271
Opus 5 $0.00135 $0.00135
Sonnet 5 $0.00054 $0.00054
Haiku 4.5 $0.00027 $0.00027

Measured 10d ago against content hash b428f2a95af7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agent-config-test-confirmation 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 10d 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/rules/agent-config-test-confirmation.mdc · 36 lines

What it actually says

Agent Config — Test Mutation Confirmation

Rule

You MUST double-check and get explicit confirmation from the user before:

  1. Creating new tests that mutate active agent configs (e.g., workflow config, agent prompts, LLM provider settings).
  2. Running existing tests that mutate active agent configs.

What Counts as Mutating Agent Configs

  • Writing to or modifying workflow configuration files
  • Changing agent prompts, presets, or prompt versions
  • Altering LLM provider/model settings used by the running system
  • Tests that call APIs or services that persist config changes to the active environment

Required Behavior

  • Before proposing or implementing such tests: state that they will mutate agent configs and ask for explicit approval.
  • Before running such tests: confirm with the user that they approve the run.
  • Do not assume approval from "go", "implement", or "run tests" unless the user has explicitly confirmed they approve config-mutating tests.

Example

⚠️ These tests will modify active workflow/agent config. Do you approve running them?

Wait for explicit "yes" or equivalent before proceeding.

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. 10d ago First seen · 36 lines · 271 tokens per session scan A b428f2a95af7

Subscribe to this mod's changes

agent-config-test-confirmation is a cursor rule published in the GitHub repository dfirtnt/Huntable-CTI-Studio (11 stars, last pushed 2d ago), licensed MIT. It adds 271 tokens to every session, about $0.0014 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 2026-08-30.