retentioneering-tools AGENTS.md

retentioneering-tools AGENTS.md is an instructions file for Codex, OpenCode from retentioneering/retentioneering-tools. It costs 3,200 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for coding agents working on the retentioneering-tools project, including its background, architecture references, and common commands.

In plain words
What is it for?
Use them when working on retentioneering, especially when reading project guidance, consulting architecture decisions, or running installation and test commands.
Why use it?
They give an agent the project context needed to make changes that fit the current codebase and avoid relying on outdated information.

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

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 retentioneering-tools AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/retentioneering/retentioneering-tools/agents-md.svg)](https://agentmods.dev/instructions/retentioneering/retentioneering-tools/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/retentioneering/retentioneering-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/retentioneering/retentioneering-tools/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,200 This file is loaded in full into every session.
When invoked 3,200 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 5.1 $0.03200 $0.03200
Opus 5 $0.01600 $0.01600
Sonnet 5 $0.00640 $0.00640
Haiku 4.5 $0.00320 $0.00320

Measured 6d ago against content hash 0c3567db0ec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

retentioneering-tools 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 6d 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.

AGENTS.md

Guidance for coding agents (Claude Code, Codex, Cursor, and others) working in this repository. Claude Code loads this file through the @AGENTS.md import in CLAUDE.md; Claude-specific instructions, if any, go in CLAUDE.md below the import.

Deep context lives in the Architecture Decision Records — see docs/adr/README.md for the index. Load the ADRs relevant to your task; ADR-0002 (DuckDB replacement scan, now superseded by engine.py — see below) documents why some historical code still carries # noqa: F841 comments on variables that look unused.

Project background

retentioneering 5.x is a ground-up rewrite of the 3.3.0 engine: the pandas-based Eventstream and the iframe/CDN-loaded widgets were replaced with a DuckDB-backed Eventstream and anywidget-based Jupyter widgets. The 3.x branch preserves the legacy engine for reference and patches. CHANGELOG.md's [5.0.0] entry documents the full delta vs. 3.3.0, including removed/added/renamed Eventstream methods and the 5.0 naming conventions. docs/ (guide pages, generated reference, ADRs) describes the current API.

Known gaps vs. 3.3.0 (deliberately not carried over, may return later — ADR-0012): the interactive Preprocessing Graph (visual no-code pipeline builder), and the Cohorts, StatTests, Sequences tools.

Commands

uv sync                    # install Python deps (+ dev group: pytest, ruff, pre-commit)
cd js && npm install       # install JS deps (npm workspaces: viz-core, widget)
# or: make install         # does both

make build                 # build JS and drop widget.js/widget-static.js into src/retentioneering/static/
make watch                 # vite --watch for js/widget, for iterating on widget UI

uv run pytest tests/ -v                          # full test suite
uv run pytest tests/data_processors/add_events_test.py -v          # single file
uv run pytest tests/data_processors/add_events_test.py::test_name -v   # single test
# or: make test            # full suite only

uv run pre-commit run --all-files    # ruff (lint+format) + gitleaks + hygiene hooks
uv run pre-commit install            # one-time, makes hooks run automatically on `git commit`
# or: make install-dev      # = make install + the pre-commit install line above

uv run python docs/scripts/render_pages.py           # regenerate reference docs from docstrings
uv run python docs/scripts/generate_widget_demos.py  # regenerate static widget demos

uv build                   # sdist + wheel; requires `make build` to have run first so the
                            # JS bundle exists on disk (hatchling force-includes it via
                            # [tool.hatch.build] artifacts in pyproject.toml even though
                            # it's gitignored)

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. 6d ago First seen · 201 lines · 3,200 tokens per session scan A 0c3567db0ec0

Subscribe to this mod's changes

retentioneering-tools AGENTS.md is an instructions file published in the GitHub repository retentioneering/retentioneering-tools (918 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,200 tokens to every session, about $0.0160 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.

Related

Other instructions, from other repositories

DeepSpeed AGENTS.md

AGENTS.md instructions for deepspeedai/DeepSpeed, covering deepspeed project rules, commit & ci requirements, code change discipline, test discipline and tool caveats.

deepspeedai/DeepSpeed · 657 tokens

spiceai copilot-instructions.md

Copilot instructions for spiceai/spiceai, covering spice.ai agent instructions, data correctness — absolute top priority, evidence — no claim without a reproduction, build, test, lint (expensive — read first) and git & prs.

spiceai/spiceai · 7,971 tokens

meme-search CLAUDE.md

Instructions for neonwatty/meme-search, covering claude.md, 📁 file organization guidelines, 🤖 task agent usage guidelines, when to use task agents and documentation lookup pattern.

neonwatty/meme-search · 2,697 tokens

cookiecutter-mlops-package AGENTS.md

Instructions for fmind/cookiecutter-mlops-package, covering agents.md, project overview, setup & core commands, definition of done and conventions & idioms.

fmind/cookiecutter-mlops-package · 1,296 tokens

worldforge CLAUDE.md

Claude Code instructions for AbdelStark/worldforge: WorldForge is a harness framework for building world-model-based workflows for physical AI. It is the application builder's counterpart to model-training stacks like Stable World Model: it helps roboticists and physical-AI builders compose, evaluate, and benchmark…

AbdelStark/worldforge · 4,109 tokens

Kiln AGENTS.md

AGENTS.md instructions for Kiln-AI/Kiln, covering project overview, project goals, tech stack, agent tools and agent prompts.

Kiln-AI/Kiln · 1,070 tokens