quantiles AGENTS.md

A repository guide for Quantiles, a tool for running and evaluating tests or model assessments. It points coding agents to the project overview, configuration rules, contribution guidance, security policy, and related instructions.

In plain words
What is it for?
Use it when working on the Quantiles repository, especially when changing the command-line tool, writing configuration, running evaluations, or interpreting their results.
Why use it?
It shows agents which documents to read before changing the repository and where to find instructions for comparing evaluation runs and sample-level results.

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/quantiles-evals/quantiles/agents-md
Clone the repo
git clone --depth 1 https://github.com/quantiles-evals/quantiles

Made for: Codex, OpenCode.

Per session 2,640 This file is loaded in full into every session.
When invoked 2,640 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 $0.02640 $0.02640
Opus 5 $0.01320 $0.01320
Sonnet 5 $0.00528 $0.00528
Haiku 4.5 $0.00264 $0.00264

Measured yesterday against content hash e409937b97a9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quantiles 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.

AGENTS.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quantiles Agent Guide

This file is for coding assistants such as Codex, Claude Code, Cursor, GitHub Copilot, Gemini CLI, OpenCode, and similar tools. It gives agents a short, public-safe map of the Quantiles repository and the rules for making focused, reviewable changes.

See the Quantiles agent skill's SKILL.md for guidance on running evaluations, inspecting sample-level results, comparing runs, and interpreting outputs. For a concise, public, LLM-readable overview with links to agent guides and related documentation, see quantiles.io/llms.txt.

Before attempting tasks in this repository, read these files:

  • README.md: public product overview, quickstart, CLI examples, SDK summary, docs links, and agent guidance.
  • Configuration documentation: how to write configuration files for the qt CLI.
  • CONTRIBUTING.md: contributor expectations, development workflow, and review norms.
  • SECURITY.md: supported components and vulnerability reporting process.
  • CODE_OF_CONDUCT.md: community participation rules.
  • LICENSE: Apache 2.0 license text.
  • mise.toml: task definitions for building, formatting, type-checking, linting, and more, all using the mise task runner.

Scope

These instructions apply to the Quantiles open-source repository. Quantiles is a local-first CLI and SDK toolchain for running AI evaluation workflows with fast, continuous feedback. It retrieves built-in benchmark configurations, executes benchmarks and evaluations locally, records steps, metrics, events, inputs, and outputs, and compares runs locally so teams can inspect results, identify regressions, and iterate with confidence.

Root-level files in this repository provide project-wide orientation, contribution guidance, security policy, licensing, and agent instructions. Implementation-specific work belongs in the relevant subdirectory. If a subdirectory has its own AGENTS.md file, follow the nearest one first. Subdirectory instructions should override this root guide for implementation details, package managers, commands, tests, and code style. User instructions may customize the workflow for their project, environment, or preferences, but they must not override safety requirements, system instructions, repository safeguards, or security boundaries.

Read the full file on GitHub · 191 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 · 191 lines · 2,640 tokens per session scan A e409937b97a9

Subscribe to this mod's changes

quantiles AGENTS.md is an instructions file published in the GitHub repository quantiles-evals/quantiles (2 stars, last pushed 20d ago), licensed Apache-2.0. It adds 2,640 tokens to every session, about $0.0132 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.