Borrowing it
Nothing to install: this file belongs to coroniumio/coronium-proxy-mcp. 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/coroniumio/coronium-proxy-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/coroniumio/coronium-proxy-mcpWrote 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/instructions/coroniumio/coronium-proxy-mcp/agents-md)<a href="https://agentmods.dev/instructions/coroniumio/coronium-proxy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/coroniumio/coronium-proxy-mcp/agents-md/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/instructions/coroniumio/coronium-proxy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/coroniumio/coronium-proxy-mcp/agents-md.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 | $0.00429 | $0.00429 |
| Opus 5.5 | $0.00172 | $0.00172 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
coronium-proxy-mcp AGENTS.md 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 9d 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
Public MCP maintenance
This repository is the public customer MCP. Work here does not authorize changes to the Coronium backend, reseller API, private OpenClaw support MCP, customer balances, proxy servers or customer proxy assignments.
Use the deployed route/controller contract as evidence for field names and side effects; see docs/backend-contract.md. Keep fixes readable and scoped, following https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md.
Never use production payment, rotation, cancellation, replacement, credential or support-message calls for verification. Contract tests must use loopback fixtures, synthetic credentials and an isolated home directory. Only the explicitly named public catalog smoke script may make unauthenticated production reads.
Preserve structured receipts, native currencies, unknown states, ownership checks, confirmations and idempotency keys. No automatic write retries, alternate-route retries, amount splitting or bypasses of backend refusal. Immediate cancellation must never be described as disabling auto-renew.
Do not expose admin or server repair routes. Capability and connectivity claims must be specific to the modem, provider and tested protocol.
Keep all existing tool names unless a deliberate major migration documents their removal. Regenerate docs/tool-catalog.json and the README catalog when schemas change. Run npm run check, npm run docs:check and npm run test:package before release. Never commit credentials, token caches, private customer evidence or environment files.
Profiles: the directory profile is the explicit DIRECTORY_TOOLS allowlist in src/profiles.ts plus test/profiles/directory.json; change both on purpose. Spending tools must stay behind CORONIUM_TOOL_PROFILE=full and CORONIUM_ENABLE_SPENDING=1. Every tool declares its backend routes; they must exist in test/fixtures/v3-routes.json.
Public repository: never add internal implementation details (backend file paths, server names, hosts, database names, credentials, defect descriptions or revenue terms). The route fixture holds only method, path, auth and public field shapes. Copy uses a short dash, never long dashes. Contact address: [email protected].
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.
- 9d ago Changed · +4 lines · +126 tokens per session 0d2e95e9e78d
- 1mo ago First seen · 14 lines · 303 tokens per session scan A b3d4890dc080
coronium-proxy-mcp AGENTS.md is an instructions file published in the GitHub repository coroniumio/coronium-proxy-mcp (1 stars, last pushed 11d ago), licensed MIT. It adds 429 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-09-11.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.