agent-exporter AGENTS.md

agent-exporter AGENTS.md is an instructions file for Codex, OpenCode from ihatenodejs/agent-exporter. It costs 1,750 tokens per session, scanned A, original, Unlicense.

Project instructions for Agent Exporter, a command-line tool that records and analyzes AI-agent usage costs from several providers.

In plain words
What is it for?
Use them when developing, type-checking, building, linking, or understanding Agent Exporter's provider, database, pricing, exporter, and command-line components.
Why use it?
They explain the project's development commands, data flow, storage, pricing lookup, and export structure so contributors can work consistently.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/ihatenodejs/agent-exporter/agents-md
Clone the repo
git clone --depth 1 https://github.com/ihatenodejs/agent-exporter

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 agent-exporter AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ihatenodejs/agent-exporter/agents-md.svg)](https://agentmods.dev/instructions/ihatenodejs/agent-exporter/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ihatenodejs/agent-exporter/agents-md"><img src="https://agentmods.dev/badge/instructions/ihatenodejs/agent-exporter/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,750 This file is loaded in full into every session.
When invoked 1,750 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01750 $0.01750
Opus 5 $0.00875 $0.00875
Sonnet 5 $0.00350 $0.00350
Haiku 4.5 $0.00175 $0.00175

Measured 4d ago against content hash e60f20c18bdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-exporter 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 4d 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 · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Exporter is a CLI tool for tracking and analyzing LLM usage costs across multiple AI agent providers (Oh My Pi, OpenCode, Claude Code/CCUsage, Codex, Antigravity, Qwen). It uses SQLite for storage, calculates costs using @pydantic/genai-prices with a fallback pricing database, and exports data in various formats.

Development Commands

Run in development:

bun run dev <command> [args]
# Example: bun run dev sync --provider opencode

Build executable:

bun run build
# Creates compiled binary at dist/agent-exporter

Type checking:

bun run typecheck

Link for local testing:

bun link
# Then use: agent-exporter <command>

Architecture

Core Data Flow

  1. Providers (src/providers/) fetch raw usage data from each platform
  2. DatabaseManager (src/database/) stores unified messages in SQLite
  3. Pricing (src/core/pricing.ts) resolves Oh My Pi stored/catalog costs, then genai-prices → fallback database → $0
  4. Exporters (src/exporters/) transform data into output formats
  5. CLI (src/cli.ts) orchestrates everything via Commander.js

Key Patterns

Provider Adapters: Each provider implements one member of the ProviderAdapter union:

  • MessagesProviderAdapter: name, dataType: 'messages', and fetchMessages(): Promise<UnifiedMessage[]>
  • UsageProviderAdapter: name, dataType: 'usage entries', and fetchUsageEntries(): Promise<UsageEntry[]>

Normalized Data: Message providers return UnifiedMessage[] with standardized token counts (input, output, reasoning, cache creation/read), cost, and metadata. Usage providers return UsageEntry[].

Pricing Resolution:

  1. Oh My Pi: preserve non-zero recorded totals; otherwise use the bundled @oh-my-pi/pi-catalog rates
  2. Primary: @pydantic/genai-prices via calcPrice(); Oh My Pi wrapper records search without the wrapper provider ID
  3. Fallback: src/core/database/prices.ts for exact and regex-matched custom prices
  4. Default: $0 for unknown models

Read the full file on GitHub · 201 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. 4d ago First seen · 201 lines · 1,750 tokens per session scan A e60f20c18bdb

Subscribe to this mod's changes

agent-exporter AGENTS.md is an instructions file published in the GitHub repository ihatenodejs/agent-exporter (2 stars, last pushed 10d ago), licensed Unlicense. It adds 1,750 tokens to every session, about $0.0088 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.