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/coddy-project/coddy-agentWrote 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/coddy-project/coddy-agent/provider-proxy)<a href="https://agentmods.dev/rules/coddy-project/coddy-agent/provider-proxy"><img src="https://agentmods.dev/badge/rules/coddy-project/coddy-agent/provider-proxy/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/coddy-project/coddy-agent/provider-proxy"><img src="https://agentmods.dev/badge/rules/coddy-project/coddy-agent/provider-proxy.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 | $0.00000 | $0.00339 |
| Opus 5.5 | $0.00000 | $0.00136 |
| Sonnet 5.5 | $0.00000 | $0.00068 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
provider-proxy 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 11d 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
Provider transport and proxy boundary
Every outbound request belonging to an LLM provider — completions, streams,
model discovery, account usage, OAuth/device sign-in, token refresh, revoke,
and any provider added later — must follow that row's providers[].proxy
setting.
- Production provider helpers accept the row's proxy setting and build their
client through
llm.HTTPClientForProviderProxy; do not usehttp.DefaultClient,&http.Client{},http.Get,http.Post, orhttp.Headin a provider path. - A helper that needs a custom
*http.Clientonly as a test seam must rejectnil; nil must never silently fall back to a direct/environment client. - Settings sign-in starts before Save. If the form carries an unsaved
proxy, apply it after resolving the row, including when the saved row has another provider type. An absent field retains the row value;""/inheritinherit the process proxy;nonegoes direct; invalid settings return 400. - When changing provider transport, extend
features/provider_proxy.featureandinternal/llm/bdd_provider_proxy_test.gofor every new request class, and keepTestProviderProxyGuardgreen.
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.
- 11d ago Changed · +1 lines · -334 tokens per session dd50c369ef56
- 14d ago First seen · 30 lines · 334 tokens per session scan A ea7b26427c78
provider-proxy is a cursor rule published in the GitHub repository coddy-project/coddy-agent (175 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 339 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 2026-10-02.
Other cursor rules, from other repositories
proxy-auth-transport
Every CLI command or browser UI action that calls a crit-web API must work in both modes.
hatch3r-contract-testing
Consumer-driven and spec-driven contract testing between services — Pact, Schemathesis, Dredd, pact-broker can-i-deploy gate.
api
For creating tests for the backend in bubblelab-api.
use-frontend-api-client
Generated API client usage.
playwright-api-testing
You are an expert QA engineer with deep knowledge of Playwright and TypeScript, tasked with creating API tests for web applications.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.