What is slop-index AGENTS.md?

Project instructions for reproducing the Slop Index, a study that measures recognizable patterns in AI-written text using token statistics and compares models with pre-AI human writing.

Use them to regenerate human baselines, produce model outputs, calculate the index, and estimate ranking ranges from a completed run.

They document the files, data stages, commands, and optional services needed to rebuild the study's results consistently.

How hgaddipati1118/slop-index configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hgaddipati1118/slop-index. 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/hgaddipati1118/slop-index/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hgaddipati1118/slop-index

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hgaddipati1118/slop-index/agents-md/github.svg)](https://agentmods.dev/instructions/hgaddipati1118/slop-index/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hgaddipati1118/slop-index/agents-md"><img src="https://agentmods.dev/badge/instructions/hgaddipati1118/slop-index/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hgaddipati1118/slop-index/agents-md"><img src="https://agentmods.dev/badge/instructions/hgaddipati1118/slop-index/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,978 This file is loaded in full into every session.

When invoked 1,978 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.

Model	Per session	Once invoked
Fable 5.1	$0.01978	$0.01978
Opus 5	$0.00989	$0.00989
Sonnet 5	$0.00396	$0.00396
Haiku 4.5	$0.00198	$0.00198

Measured 10d ago against content hash a582c2d6f760, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

slop-index 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 10d 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 · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md, reproduce The Slop Index end to end

This file is the machine-readable playbook. An agent (Claude Code, Codex, etc.) should be able to rebuild every result in this repo from it. CLAUDE.md is a symlink to this file, so both tools read the same instructions. Humans want README.md.

The Slop Index ranks frontier LLMs by how much recognizable "AI slop" their writing contains, measured mechanically against pre-AI human baselines (all text provably written before Oct 2022) across four domains: email, social, essay, chat. A companion web app collects a human-preference Elo. No LLM judges score other LLMs, every number is a token statistic.

Repo layout

harness/           the pipeline (pure stdlib + LiteLLM). Run everything from repo root.
  providers.py       model roster (MODELS), prices, LiteLLM adapter. Reads keys from env.
  generate.py        stage 1: scenarios x models x samples -> runs/<id>/outputs.jsonl
  score.py           stage 3: mechanical Slop Index (conciseness/templating/rhythm/tells)
  rank_spread.py     bootstrap rank ranges + tie groups from a run
  detect.py          optional: Pangram AI-detector pass (needs PANGRAM_API_KEY). SATURATES.
  analyze.py         pilot go/no-go gate (works with or without detector scores)
  budget.py          hard $ cap ledger + kill switch (runs/BUDGET.json)
  export_votes.py    dump the live vote log from Redis to jsonl
scenarios/pilot/   the 112 hand-written scenarios (email/social/essay/slack) + per-scenario setups
baselines/         DERIVED human-baseline stats only (stats.json). Raw corpora are NOT shipped
                   (1.4GB, third-party licenses), see baselines/README.md to rebuild them.
runs/full-merged/  outputs.jsonl = the 19,928 real generations behind the published board
runs/full-merged-score.log  = the exact score.py + rank_spread.py output (the results)
site/              the deployed app (Vercel + Upstash Redis + Cloudflare Turnstile)
  public/            index.html (the game), benchmark.html (the report), *.json data
  api/               serverless vote/session/leaderboard/admin endpoints (read secrets from env)
  scripts/           gen_pairs.py, build_bench_data.py, norm_logos.py (rebuild the site data)
docs/              SPEC.md, RUBRICS.md, DATASETS.md, DATASET_SPEC.md, PILOT_FINDINGS.md

Read the full file on GitHub · 134 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.

10d ago First seen · 134 lines · 1,978 tokens per session scan A a582c2d6f760

Subscribe to this mod's changes

slop-index AGENTS.md is an instructions file published in the GitHub repository hgaddipati1118/slop-index (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,978 tokens to every session, about $0.0099 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.

Research Scientific

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

slop-index: Instructions file for Codex