aura-courier-mcp: Instructions file for Codex

AGENTS.md

aura-courier-mcp AGENTS.md is an instructions file for Codex, OpenCode from auraajenticai/aura-courier-mcp. It costs 3,833 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for coding agents working on the aura-courier-mcp project. They describe required investigation, response formats, authentication work, and safety limits such as not using real shipment or payment services.

In plain words
What is it for?
Use them to guide an agent through hardening the MCP server, checking its tools and webhooks, running tests, and using mocked courier and payment calls.
Why use it?
They give an agent project-specific rules and verification steps instead of leaving it to guess how the repository works or which actions are safe.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is auraajenticai/aura-courier-mcp's own configuration. It tells Codex and OpenCode how to work on aura-courier-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything aura-courier-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to auraajenticai/aura-courier-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.

Copy the file
curl -O https://raw.githubusercontent.com/auraajenticai/aura-courier-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/auraajenticai/aura-courier-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for aura-courier-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/auraajenticai/aura-courier-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/auraajenticai/aura-courier-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/auraajenticai/aura-courier-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/auraajenticai/aura-courier-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.

agentmods 80×15 button for aura-courier-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/auraajenticai/aura-courier-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/auraajenticai/aura-courier-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,833 This file is loaded in full into every session.
When invoked 3,833 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03833 $0.03833
Opus 5.5 $0.01533 $0.01533
Sonnet 5.5 $0.00767 $0.00767
Haiku 4.5 $0.00383 $0.00383

Measured yesterday against content hash e29a25e49e06, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aura-courier-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 yesterday.

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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

AGENTS.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — aura-courier-mcp v2.5.4 → v2.6.0 hardening

Works for any coding agent (Claude Code, Codex, Antigravity/Gemini, Cursor). Save as AGENTS.md in the repo root (Claude Code: also copy/symlink to CLAUDE.md; Antigravity/Gemini: GEMINI.md if it does not read AGENTS.md). Then prompt: "Read AGENTS.md and execute it end to end."

Repo: https://github.com/auraajenticai/aura-courier-mcp (Apache-2.0, Node, Streamable-HTTP MCP, protocol 2024-11-05)


0. Ground rules (read first, obey always)

  1. Discover before editing. Read the repo (entrypoint, tool registry, courier adapters, webhook handlers, config, existing tests, package.json) and write a 10-line "repo map" at the start of your report. Do not assume file names; the ones used below are placeholders.
  2. Never invent facts. Anything marked OBSERVED below was seen in live behavior. Anything marked UNVERIFIED you must confirm from code or by running it, then state the result. If you cannot confirm, say so; do not guess.
  3. Never create real shipments or move money. Do not call real courier booking, cancel, or payout endpoints. Use mocks/nock/fixtures for upstream APIs. No real customer phone numbers in tests; use 01700000000-style synthetic values only.
  4. No secrets in code, logs, tests, or the report. Redact API keys, tokens, and merchant IDs.
  5. Backward compatibility. Do not rename or remove existing tools or existing response fields. Add new fields. Deprecate loudly in descriptions.
  6. Small, reviewable commits (one per task ID). Run the full test suite before each commit.
  7. Stop and ask (end your turn with a question) only if a decision cannot be derived from code or this file, e.g. choosing a hosting secret store. Otherwise decide, document in the report, and continue.
  8. Honest reporting. If a task is partly done, say exactly which acceptance tests pass and which fail.

1. Global response envelope (all tools)

{
  "ok": true,
  "data": {},
  "error": null,
  "meta": {
    "request_id": "uuid",
    "source": "live_api | static_tariff | cache | validator",
    "as_of": "ISO-8601"
  }
}

Read the full file on GitHub · 216 lines

Changes

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.

  1. yesterday First seen · 216 lines · 3,833 tokens per session scan A e29a25e49e06

Subscribe to this mod's changes

aura-courier-mcp AGENTS.md is an instructions file published in the GitHub repository auraajenticai/aura-courier-mcp (0 stars, last pushed today), licensed Apache-2.0. It adds 3,833 tokens to every session, about $0.0153 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 2026-11-10.

Related

aura-courier-mcp AGENTS.md compared with instructions from other repositories

aura-courier-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
aura-courier-mcp AGENTS.mdauraajenticai/aura-courier-mcpInstructions file0todayApache-2.0A3,833Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot