usd-routing-coach-ar: Instructions file for Codex

AGENTS.md

usd-routing-coach-ar AGENTS.md is an instructions file for Codex, OpenCode from Nicopatron/usd-routing-coach-ar. It costs 1,334 tokens per session, scanned A, original, MIT.

A set of operating instructions for an AI coding agent using the USD Routing Coach for Accounts Receivable. Accounts Receivable is the work of tracking money customers owe and handling related invoices and payments.

In plain words
What is it for?
Processing pasted accounts-receivable cases, triaging the right mode, following intake requirements, and producing responses under the project’s runtime rules.
Why use it?
It tells the agent which files and rules to read, how to choose among four working modes, and when to ask for missing information.

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 Nicopatron/usd-routing-coach-ar's own configuration. It tells Codex and OpenCode how to work on usd-routing-coach-ar 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 usd-routing-coach-ar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Nicopatron/usd-routing-coach-ar. 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/Nicopatron/usd-routing-coach-ar/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/Nicopatron/usd-routing-coach-ar

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 usd-routing-coach-ar AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nicopatron/usd-routing-coach-ar/agents-md/github.svg)](https://agentmods.dev/instructions/nicopatron/usd-routing-coach-ar/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nicopatron/usd-routing-coach-ar/agents-md"><img src="https://agentmods.dev/badge/instructions/nicopatron/usd-routing-coach-ar/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 usd-routing-coach-ar AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nicopatron/usd-routing-coach-ar/agents-md"><img src="https://agentmods.dev/badge/instructions/nicopatron/usd-routing-coach-ar/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,334 This file is loaded in full into every session.
When invoked 1,334 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 $0.01334 $0.01334
Opus 5 $0.00667 $0.00667
Sonnet 5 $0.00267 $0.00267
Haiku 4.5 $0.00133 $0.00133

Measured 9d ago against content hash 9d0e6d3c8a10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

usd-routing-coach-ar 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.

AGENTS.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operational primer for AI coding agents (Codex CLI, Cursor, Windsurf, Zed, Roo Code, Aider, Cline, Continue, Claude Code). The README.md is for humans; this file is for you. Folder follows the agents.md open convention.

What the folder does, calibration date, and methodology: see README front-load. Canonical runtime behavior: rules.md.


Files to read on first paste, in this order

  1. rules.md — the output contract: 4 modes, output format per mode, confidence calibration, intake gate, length caps, bilingual policy, refusal discipline, voice. This file is canonical for runtime behavior.
  2. examples.md — 5 worked examples (Marina Routing EN flagship, Diego Routing ES, Federica Audit Response ES, Juan Year-End ES, Refusal triggered by intake gate)
  3. reference/intake-checklist.md — the 5 required intake inputs + refusal protocol + override
  4. reference/mode-triage.md — signal patterns + decision tree for the 4 modes + edge cases (multiple invoices, mid-conversation switching)
  5. reference/glossary.md — Layer-1 (AR domain terms) and Layer-2 (specialist-internal terms: Audit-pack, Intake gate, Mode triage, Pattern Memo, RI transition, Decision Trace, Override, Lane, Headroom, Refusal discipline) definitions. Read first if unsure about any term used in rules.md or examples.md.
  6. reference/monotributo-categorias.md, reference/usd-routing-options.md, reference/afip-audit-signals.md, reference/audit-response-playbook.md — domain reference, read on demand when constraints / lane comparison / audit-trigger flags / audit-response runtime are relevant

Operator perspective and credibility anchor live in README.md § Built by — read it when context about who built the specialist is useful, but it's not part of the runtime contract.

The README.md is fine to skim for context but is optimized for human judges, not for you. Skip it if you want.


Default workflow on every paste

Paste arrives
   │
   ▼
1. Mode detection         (signals from reference/mode-triage.md)
   │
   ▼
2. Intake gate            (5 required inputs from reference/intake-checklist.md)
   │   4 of 5 missing? → REFUSE: list gaps, no synthesis, no preamble
   ▼
3. Mode-specific synthesis
   │   • Routing Mode      → 6 sections + audit-pack shadow artifact
   │   • Audit Response    → defensive playbook (no routing recommendation)
   │   • Year-End          → cat projection + RI transition readiness
   │   • Pattern Memo      → quantitative emergent insight (3+ Routing decisions in convo)
   ▼
4. Decision Trace         (3-5 lines citing input signals that drove major calls)
   │
   ▼
5. audit-pack.md shadow   (Routing Mode only — fixed format, ready to drop in AFIP folder)

Read the full file on GitHub · 98 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. 9d ago First seen · 98 lines · 1,334 tokens per session scan A 9d0e6d3c8a10

Subscribe to this mod's changes

usd-routing-coach-ar AGENTS.md is an instructions file published in the GitHub repository Nicopatron/usd-routing-coach-ar (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,334 tokens to every session, about $0.0067 per session on Opus 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 2026-08-31.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens