Cottontail AGENTS.md

Repository-specific instructions for working on the Cottontail project, a library with a Python wrapper that explores indexing structures. They tell an AI coding assistant which project documents to read and what rules to follow before editing.

In plain words
What is it for?
Use them when modifying Cottontail: read the architecture and plan documents, follow the project’s documentation conventions, and treat the repository’s verification requirements as part of the work.
Why use it?
They provide project context and safety constraints that general coding advice would not know, including the requirement to discuss and confirm changes before coding.

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/claclark/cottontail/agents-md
Clone the repo
git clone --depth 1 https://github.com/claclark/Cottontail

Made for: Codex, OpenCode.

Per session 574 This file is loaded in full into every session.
When invoked 574 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 $0.00574 $0.00574
Opus 5 $0.00287 $0.00287
Sonnet 5 $0.00115 $0.00115
Haiku 4.5 $0.00057 $0.00057

Measured 2d ago against content hash c2367b81e3dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Cottontail 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 2d 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 · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cottontail Agent Notes

Be a little chill. This repo started life as a research project exploring novel indexing structures. Now we are moving toward a more generally usable library, along with a Python wrapper. We want the code to be solid and usable. There is no rush. We want people to have a good experience when we release.

This file is mostly intended for an AI coding assistant working on the development of Cottontail, but of course anyone is free to look around. Annotative indexing is particularly useful for agents: it lets them turn natural-language intent into precise structural queries over code, text, JSON, and metadata, then retrieve only the local context they need. When a collection records paths, fields, symbols, spans, provenance, and transactions, the resulting evidence remains exact and inspectable.

All agent documentation lives in the ai/ directory.

No coding before discussion and confirmation with the user. If you ever find yourself calling something a "side car" you are probably breaking an abstraction. Stop and talk with the user.

Before Doing Any Work

Read:

  • ai/architecture.md

If it exists, also read:

  • ai/plan.md

ai/plan.md records the current planned next coding step. Use it to continue planned work instead of restarting the design discussion.

We are dogfooding apps/cgrep as a local text-search tool. Read ai/cgrep.md, and use cgrep for repository text searches when it is suitable. Other search tools are still allowed, but when cgrep cannot be used for a search, add a concise note to ai/cgrep-improvements.md explaining why.

Verification Rule

Unless the user explicitly asks for runtime experiments, ranking runs, evals, or benchmarks, only run compile/build checks.

Files In ai/

ai/architecture.md

Overview of the core architecture. This file is authoritative and should not be modified unless explicitly authorized. You may, however, suggest when changes are appropriate.

ai/plan.md

Current plan for the next coding step, when one has been materialized.

Read the full file on GitHub · 73 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. 2d ago First seen · 73 lines · 574 tokens per session scan A c2367b81e3dd

Subscribe to this mod's changes

Cottontail AGENTS.md is an instructions file published in the GitHub repository claclark/Cottontail (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 574 tokens to every session, about $0.0029 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.