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-cli-tools/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-cli-tools)<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-cli-tools"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-cli-tools/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-cli-tools"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-cli-tools.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 | $0.00150 | $0.06726 |
| Opus 5.5 | $0.00060 | $0.02690 |
| Sonnet 5.5 | $0.00030 | $0.01345 |
| Haiku 4.5 | $0.00015 | $0.00673 |
Grade B, and why
openproxy-cli-tools scanned grade B with 2 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| Claude Code | `/api/cli-tools/claude-settings` | `~/.claude/settings.json` | 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 | head -c 200 How it starts
The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openproxy-cli-tools — wire AI coding CLIs into the proxy
Extends §5 of .agents/skills/openproxy/SKILL.md, which shows the one-liner per tool. This skill is the reference version: every route, every settings-file path, the exact POST body each endpoint accepts, and the verification that proves traffic is flowing.
Read the entry skill first if the server isn't running yet. This skill assumes openproxy server start --detach --no-open has already succeeded and $OPENPROXY_API_KEY holds the management key.
The one thing to get right: OpenProxy normalizes the base URL for you. Send http://127.0.0.1:4623 and the server appends /v1 wherever the tool expects a versioned path. Sending .../v1 yourself is fine too — normalize_v1_base_url() is idempotent.
0 · Preflight
# Server is up?
curl -sS http://127.0.0.1:4623/health | head -c 200
# Management key present?
test -n "$OPENPROXY_API_KEY" && echo "key in env" || echo "need openproxy server init"
1 · Auth model for /api/cli-tools/*
Every route below is gated by require_dashboard_or_management_api_key(). Two accepted shapes:
| Method | Header |
|---|---|
| Management key | Authorization: Bearer $OPENPROXY_API_KEY |
| Management key (alt) | x-api-key: $OPENPROXY_API_KEY |
| Browser session | auth_token cookie from POST /api/auth/login |
If a request carries any key header, the dashboard-session path is skipped and the key is validated strictly. A malformed key therefore fails even on a server with requireLogin off — don't debug that as a missing cookie.
export OP=http://127.0.0.1:4623
export AUTH="Authorization: Bearer $OPENPROXY_API_KEY"
curl -sS "$OP/api/cli-tools" -H "$AUTH"
2 · Route map
Every path below was read out of src/server/api/cli_tools.rs and src/server/api/cli_tools/*.rs. Routes that exist on disk but are not mounted into cli_tools::routes() are called out explicitly rather than documented as if they worked.
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 · 410 lines · 150 tokens per session scan B 0b87d53db3df
openproxy-cli-tools is a skill published in the GitHub repository quangdang46/openproxy (29 stars, last pushed 5d ago), licensed MIT. It adds 150 tokens to every session and 6,726 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, 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…