tokenmaxxing AGENTS.md

Repository instructions for an Effect-based TypeScript project, covering error types, export style, data synchronization, date handling, command-line tokens, and command-line output.

In plain words
What is it for?
Use them when adding Effect errors, exporting code, syncing daily device data, handling date strings, managing command-line tokens, or designing foreground CLI output.
Why use it?
They keep shared code patterns consistent and prevent mistakes such as throwing untyped errors, changing date buckets, or breaking idempotent synchronization.

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/851-labs/tokenmaxxing/agents-md
Clone the repo
git clone --depth 1 https://github.com/851-labs/tokenmaxxing

Made for: Codex, OpenCode.

Per session 438 This file is loaded in full into every session.
When invoked 438 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 $0.00438 $0.00438
Opus 5 $0.00219 $0.00219
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 3d ago against content hash 525f14f2ec16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tokenmaxxing 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 3d 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 · 36 lines

What it actually says

Repository Instructions

Effect Error Style

  • Prefer native Effect errors over plain JavaScript Error subclasses in Effect code.
  • Use Data.TaggedError for internal typed errors that stay inside the Effect error channel.
  • Use Schema.TaggedErrorClass when an error is part of a public schema or wire contract.
  • Avoid throw for expected domain failures; return Effect.fail(...) with a typed error instead.

Export Style

  • Prefer local declarations first and grouped exports at the end of each authored source file.
  • Use export { ... } for runtime values and export type { ... } for type-only exports.
  • Put default exports at the end too, using a named local value before export default name;.
  • Do not hand-edit generated files just to satisfy this style rule.

Conventions

  • Daily usage rows are keyed (deviceId, date, source, model) and upserted; sync must stay idempotent.
  • date columns are opaque YYYY-MM-DD strings (ccusage local-time buckets); never parse them into Date objects for bucketing.
  • CLI tokens (tmx_ prefix) never expire; revocation (revokedAt) is the only kill switch.

CLI Output Style

  • Foreground human CLI commands should wrap async work in humanSpinner inside humanFrame. This includes network calls, filesystem writes, subprocesses, scheduler changes, package-manager updates, browser opens, and other operations that can visibly pause.
  • Keep machine output clean: --json, silent, and scheduled/background service paths must not emit spinners or decorative human logs.
  • Prefer shared output helpers (humanFrame, humanSpinner, humanLog, formatUrl, formatHighlight, writeJson) over raw console output in foreground commands.
  • Spinner rows should resolve into the final success or error row for that operation instead of adding a separate duplicate row.
  • Do not use indefinite spinners while waiting for external user action; show the actionable URL/code/instruction and then wait quietly.
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. 3d ago First seen · 36 lines · 438 tokens per session scan A 525f14f2ec16

Subscribe to this mod's changes

tokenmaxxing AGENTS.md is an instructions file published in the GitHub repository 851-labs/tokenmaxxing (67 stars, last pushed 27d ago), licensed MIT. It adds 438 tokens to every session, about $0.0022 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 2026-08-30.