Borrowing it
Nothing to install: this file belongs to quangdang46/openproxy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/quangdang46/openproxy/main/.agents/skills/openproxy-chat/SKILL.mdgit clone --depth 1 https://github.com/quangdang46/openproxyWrote 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/skills/quangdang46/openproxy/openproxy-chat)<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-chat"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-chat/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/skills/quangdang46/openproxy/openproxy-chat"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-chat.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 | $0.06665 |
| Opus 5.5 | $0.00000 | $0.02666 |
| Sonnet 5.5 | $0.00000 | $0.01333 |
| Haiku 4.5 | $0.00000 | $0.00666 |
Grade A, and why
openproxy-chat scanned grade A with 1 finding 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 29d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS http://127.0.0.1:4623/health How it starts
The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openproxy-chat — chat completions through /v1/chat/completions
OpenProxy exposes an OpenAI-compatible chat surface on 127.0.0.1:4623. One endpoint —
POST /v1/chat/completions — fronts 40+ providers, with model-level account fallback, combos,
and request/response format translation underneath.
This skill is about getting a chat call right: addressing a model, streaming it, using tools, and reading back what the router actually did.
0 · Preconditions
The server must already be running. Check before anything else:
curl -sS http://127.0.0.1:4623/health
/health needs no auth and returns {"status":"ok", …}. If it is not ok, start the server first
— see the openproxy skill (.agents/skills/openproxy/SKILL.md) for install and start.
Two different credentials, and this trips people up:
| Surface | Credential | Notes |
|---|---|---|
/v1/* (/v1/chat/completions, /v1/models) |
Proxy API key | Authorization: Bearer $OPENPROXY_API_KEY. Mint with openproxy key add <name> --auto. |
/api/* (dashboard, settings, combos, usage, logs) |
Admin / management key | The key printed once by openproxy server init. A proxy key gets 401 invalid_api_key here. |
For the curl examples in this skill you need the proxy key:
export BASE=http://127.0.0.1:4623
export OPENPROXY_API_KEY="$(openproxy key list --robot | jq -r '.data.keys[0].key')"
openproxy key list masks secrets in human output; --robot emits the full key value (handle it
as a secret — do not paste it into a commit, a log, or a shared transcript). To mint a fresh one
instead: openproxy key add my-agent --auto. The admin key from server init also authenticates
/v1/*, so one credential can cover both surfaces.
Sections that touch /api/* — the openproxy chat send|stream, openproxy usage …, and
openproxy logs … commands — need the admin key specifically.
If /v1/* answers an unauthenticated request with 404 instead of 401, the install has
requireApiKey off — /v1 is open on loopback. That is a settings choice, not a bug; see
"Auth" in §8.
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.
- 29d ago First seen · 508 lines · 0 tokens per session scan A beb794f1f667
openproxy-chat is a skill published in the GitHub repository quangdang46/openproxy (29 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,665 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
Other skills, from other repositories
implementing-api-schema-validation-security
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
keirouter-chat
Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through KeiRouter.
keirouter-embeddings
Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Mistral / Cohere / Voyage / NVIDIA / AWS Bedrock and other embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
10router
Entry point for 10Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 10Router, TENROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
post-processing
Extract, analyze, and summarize simulation output data — pull spatial fields at specific timesteps, compute time-series trends and detect steady state, extract line profiles through the domain, generate statistical summaries and distributions, calculate derived quantities (gradients, fluxes, volume fractions…
linear-solvers
Select and configure linear solvers for Ax=b systems arising in numerical simulations — choose between direct (LU, Cholesky) and iterative (CG, GMRES, BiCGSTAB, MINRES) methods, analyze sparsity patterns and matrix conditioning, recommend preconditioners (AMG, ILU, IC), apply row/column scaling, and diagnose…