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/Flower7C3/tune-tanglerWrote 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/flower7c3/tune-tangler/tune-tangler-assistant)<a href="https://agentmods.dev/rules/flower7c3/tune-tangler/tune-tangler-assistant"><img src="https://agentmods.dev/badge/rules/flower7c3/tune-tangler/tune-tangler-assistant/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/flower7c3/tune-tangler/tune-tangler-assistant"><img src="https://agentmods.dev/badge/rules/flower7c3/tune-tangler/tune-tangler-assistant.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 | $0.00203 | $0.00203 |
| Opus 5 | $0.00102 | $0.00102 |
| Sonnet 5 | $0.00041 | $0.00041 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
tune-tangler-assistant 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.
What it actually says
Code changes
- Prefer small, readable diffs; avoid wide refactors without consent.
- Explain what you are doing; for many files or risky changes, propose a plan first, then implement.
How assistants should work
- This is a real environment with shell and network when available: run commands and use tools to investigate; do not only tell the user what to run.
- Do not give up after a single failure—try alternatives, diagnose, and retry when sensible.
- When citing existing code in chat, use the project’s code-reference format (line ranges and file paths) so navigation is one click.
Response style
- Be concise and clear; do not hide tool or build failures.
Do not
- Assume user intent instead of clarifying when requirements are ambiguous.
- Ignore analyzer or build failures you could fix or report accurately.
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.
- 10d ago First seen · 25 lines · 203 tokens per session scan A 67762a11fc17
tune-tangler-assistant is a cursor rule published in the GitHub repository Flower7C3/tune-tangler (6 stars, last pushed 3mo ago), licensed MIT. It adds 203 tokens to every session, about $0.0010 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
compose-accessibility
Compose accessibility rules for TalkBack — icons, headings, Canvas, live regions, focus, modals, and attribute preservation.
compose-coroutines
Compose scroll/coroutine patterns — prevent programmatic scroll from being mistaken for user scroll, cancellation-safe flag resets.
testing-conventions
Testing conventions — JUnit 4, Kotest property tests, instrumented tests, what to test when.
ios-viewmodel
ViewModels conform to ObservableObject and expose state via @Published properties.
compose-ui
Compose UI conventions — Material 3, recomposition optimization, Compose-only UI, theming.
android-viewmodel
Android ViewModel conventions — StateFlow, repository abstraction, coroutines, no LiveData.