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/brettdavies/sounding-webmcp-demoWrote 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/brettdavies/sounding-webmcp-demo/competition-details)<a href="https://agentmods.dev/rules/brettdavies/sounding-webmcp-demo/competition-details"><img src="https://agentmods.dev/badge/rules/brettdavies/sounding-webmcp-demo/competition-details/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/brettdavies/sounding-webmcp-demo/competition-details"><img src="https://agentmods.dev/badge/rules/brettdavies/sounding-webmcp-demo/competition-details.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 | $0.00040 | $0.00040 |
| Opus 5 | $0.00020 | $0.00020 |
| Sonnet 5 | $0.00008 | $0.00008 |
| Haiku 4.5 | $0.00004 | $0.00004 |
Grade A, and why
competition-details 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 6d 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
Do not open, read, reference, quote, summarize, index, or use COMPETITION_DETAILS.md.
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.
- 6d ago First seen · 7 lines · 40 tokens per session scan A c04ba9e4047d
competition-details is a cursor rule published in the GitHub repository brettdavies/sounding-webmcp-demo (1 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session, about $0.0002 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 2026-09-04.
Other cursor rules, from other repositories
second-brain-memory
Always recall at session start and remember important context via Second Brain (MCP or brain CLI).
tailwind
Tailwind CSS v4 - CSS-first config, @source detection, @theme tokens, semantic dark-mode tokens, static-string classes, and the enforced better-tailwindcss lint set.
hono-gateway
Hono gateway Worker rules - middleware order, observability, zValidator, thin handlers, service bindings.
workers-config
Wrangler config rules - secrets vs vars, generated types, RPC typing, fail-closed expectations.
typescript-config
Shared TSConfig presets - inheritance, the strict flags that change how you write code, deliberate omissions, editing rules, in-app #/ imports.
ci
CI parity with pnpm ci, expression-context rules for env blocks, affected vs full graph by event, frozen lockfile, SHA pins, deny-by-default permissions.