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.
npx agentmods add instructions/cloudinary/cloudinary_npm/agents-mdgit clone --depth 1 https://github.com/cloudinary/cloudinary_npmWhat 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 | $0.00766 | $0.00766 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
cloudinary_npm 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributor guide for coding agents
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
node_modules/cloudinary/docs/ instead.
Commands
npm install # install dependencies
npm test # lint + unit tests + type declaration tests
npm run test:unit # mocha unit tests only (mocked, no network)
npm run lint # eslint
npm run dtslint # TypeScript declaration tests
npm run test-with-temp-cloud # full integration tests against a temporary cloud (CI)
Unit tests require a CLOUDINARY_URL in the environment or a .env file;
any syntactically valid value works for mocked tests:
CLOUDINARY_URL=cloudinary://key:secret@test-cloud.
Testing
test/unit/is mocked and must never perform network calls.test/integration/requires a real or temporary Cloudinary environment; do not run it by default and do not add tests there that consume paid add-ons without a skip guard.- Nondeterministic AI output (captions, tags, moderation verdicts) must be asserted by request shape, state transition, and response schema — never by exact output values.
Project structure
cloudinary.js— package entry point; exposes the legacy v1 API andrequire('cloudinary').v2.lib/— implementation.lib/v2/wraps the v1 modules with promise support.lib/analysis/— Analyze API (analyze_uri).types/index.d.ts— TypeScript declarations, tested bynpm run dtslint.examples/— small, runnable task examples shipped in the npm package.docs/— version-matched Markdown docs shipped in the npm package.samples/— legacy full applications; not part of the tested example set.test/—unit/,integration/, shared helpers inspechelper.jsandtestUtils/.tools/scripts/— shell entry points used by the npm scripts.
Code style
- CommonJS modules, ES6+ syntax, two-space indent; eslint config is authoritative.
- Public API methods accept an options object and an optional Node-style callback and return a Promise, following the existing pattern:
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.
- yesterday First seen · 78 lines · 766 tokens per session scan A 45bbb182c857
cloudinary_npm AGENTS.md is an instructions file published in the GitHub repository cloudinary/cloudinary_npm (666 stars, last pushed 5d ago), licensed MIT. It adds 766 tokens to every session, about $0.0038 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.
Other instructions, from other repositories
atmos CLAUDE.md
Claude Code instructions for cloudposse/atmos, covering claude.md, project overview, git worktrees (mandatory), concurrent sessions (mandatory) and hourly pr maintenance loop (recommended).
stackql AGENTS.md
Instructions for stackql/stackql, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
skills AGENTS.md
Instructions for mintuz/skills, covering agents.md, project overview, plugin architecture, repository structure and agent definition format.
pictshare CLAUDE.md
Claude Code instructions for HaschekSolutions/pictshare, covering claude.md, development commands, run locally (development), run production image and build docker image manually.
cloud-harness-mcp AGENTS.md
Instructions for bestagentkits/cloud-harness-mcp, covering cloud harness mcp collaborator guide, purpose and authority, navigation, safety-critical invariants and change workflow.