pycloudinary: Instructions file for Codex

AGENTS.md

pycloudinary AGENTS.md is an instructions file for Codex, OpenCode from cloudinary/pycloudinary. It costs 1,554 tokens per session, scanned A, original, MIT.

A repository instruction file for the Cloudinary Python package, which manages images and other media through Cloudinary. It documents the project's commands, tests, supported environments, and coding expectations.

In plain words
What is it for?
Use it when developing or testing this package, including running pytest, Django tests, tox, builds, and Cloudinary-backed test setups.
Why use it?
It gives coding agents the project-specific information needed to run checks and make compatible changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is cloudinary/pycloudinary's own configuration. It tells Codex and OpenCode how to work on pycloudinary itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pycloudinary configures →

Reuse

Borrowing it

Nothing to install: this file belongs to cloudinary/pycloudinary. 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/cloudinary/pycloudinary/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cloudinary/pycloudinary

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 pycloudinary AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cloudinary/pycloudinary/agents-md/github.svg)](https://agentmods.dev/instructions/cloudinary/pycloudinary/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cloudinary/pycloudinary/agents-md"><img src="https://agentmods.dev/badge/instructions/cloudinary/pycloudinary/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.

agentmods 80×15 button for pycloudinary AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cloudinary/pycloudinary/agents-md"><img src="https://agentmods.dev/badge/instructions/cloudinary/pycloudinary/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,554 This file is loaded in full into every session.
When invoked 1,554 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01554 $0.01554
Opus 5.5 $0.00622 $0.00622
Sonnet 5.5 $0.00311 $0.00311
Haiku 4.5 $0.00155 $0.00155

Measured today against content hash 1dfbf416f7c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pycloudinary 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 today.

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 · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is for agents contributing to this repository. If you are using the installed cloudinary package in another project, read the bundled docs in the installed package's cloudinary/docs/ directory instead.

Commands

pip install -e .                                  # install for development
pip install tox pytest                            # test tooling
python -m pytest test                             # core test suite
python -m pytest test/test_uploader.py             # a single module
tox                                               # full matrix (Python 3.10-3.14, Django 4.2-6.0)
tox -e py312-core                                 # one environment, as CI runs it
DJANGO_SETTINGS_MODULE=django_tests.settings \
  django-admin test -v2 django_tests              # Django integration suite
python -m build                                   # build sdist + wheel

Every suite needs a working CLOUDINARY_URL in the environment — there is no offline or mocked tier. CI allocates a throwaway cloud per job via tools/get_test_cloud.sh; locally, export your own or provision one with python -c "from cloudinary.provisioning import create_cloud; print(create_cloud())".

Testing

  • test/ is the core suite and hits the live API. Tests namespace their assets with UNIQUE_TEST_ID from test/helper_test.py and clean up after themselves — follow that pattern rather than leaving fixtures behind.
  • django_tests/ runs as a real Django app (django_tests.settings, in-memory sqlite). It covers CloudinaryField, the form fields, and migrations; the templatetags have no coverage yet.
  • Provisioning tests (test/test_provisioning_api.py) additionally need CLOUDINARY_ACCOUNT_URL; they are skipped without it.
  • Add-on tests (test/addon_types.py) require paid add-ons. Guard anything new with the existing skip decorators rather than making the default suite fail.
  • Nondeterministic AI output (auto-tagging, captioning, moderation verdicts) must be asserted by request shape, state transition, and response schema — never exact values.
  • There is no lint tooling in this repo. Do not add a linter or reformat files wholesale as part of an unrelated change.

Read the full file on GitHub · 128 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. today Changed · +14 lines · +228 tokens per session 1dfbf416f7c6
  2. 2mo ago First seen · 114 lines · 1,326 tokens per session scan A 9a90b751ab74

Subscribe to this mod's changes

pycloudinary AGENTS.md is an instructions file published in the GitHub repository cloudinary/pycloudinary (262 stars, last pushed yesterday), licensed MIT. It adds 1,554 tokens to every session, about $0.0062 per session on Opus 5.5. 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

pycloudinary AGENTS.md compared with instructions from other repositories

pycloudinary AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pycloudinary AGENTS.mdcloudinary/pycloudinaryInstructions file262yesterdayMITA1,554Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode