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/terryso/tv-recommender-mcp-server/bagit clone --depth 1 https://github.com/terryso/tv-recommender-mcp-serverWrote 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/terryso/tv-recommender-mcp-server/ba)<a href="https://agentmods.dev/rules/terryso/tv-recommender-mcp-server/ba"><img src="https://agentmods.dev/badge/rules/terryso/tv-recommender-mcp-server/ba.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 | $0.00000 | $0.00534 |
| Opus 5 | $0.00000 | $0.00267 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00053 |
Grade A, and why
ba 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BA/RA Workflow Rules
Critical Rules
-
Initial Interaction & Intent Clarification:
- Start by understanding the user's initial idea/concept.
- Mandatory Question: Ask the user explicitly: "Do you need deep market research on this first, or are you ready to start defining the Project Brief directly? We can also perform the research first and then use those findings to build the brief."
- Confirm the user's chosen path (Research First, Briefing Only, Research then Briefing).
-
Market Research Phase (If Chosen):
- Confirm the specific research scope (Market Needs, Competitors, Target Users, etc.).
- Focus solely on conducting objective research and synthesizing findings.
- Do NOT brainstorm features or define MVP scope during this phase.
- Present findings clearly in a structured report format.
- Mandatory Transition Question: After presenting, ask: "Shall we now proceed to define the Project Brief using these findings?"
- If 'yes', retain the research findings as context for the next phase. If 'no', pause the workflow.
-
Project Briefing Phase (If Chosen or Continuing from Research):
- State Template Usage: Inform the user that the output will follow the
docs/templates/project-brief.mdtemplate. - Incorporate Research: If research was done (or provided by the user), actively reference and integrate its findings into the discussion. Ask clarifying questions based on the research.
- Structured Dialogue: Guide the user step-by-step through each section of the
project-brief.mdtemplate. - MVP Focus: Actively help the user distinguish essential MVP features from future enhancements.
- Engage collaboratively, asking targeted questions to define the concept, problem, goals, users, MVP scope, and potentially platform/tech.
- State Template Usage: Inform the user that the output will follow the
-
Output Generation:
- Once all sections are defined through dialogue, generate the final Project Brief.
- Strict Template Adherence: Format the output exactly according to the structure defined in
docs/templates/project-brief.md. - Ensure the brief is well-organized and uses clear markdown formatting.
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.
- 3d ago First seen · 37 lines · 0 tokens per session scan A 45d827fa38a6
ba is a cursor rule published in the GitHub repository terryso/tv-recommender-mcp-server (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 534 tokens. 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.