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/cloudflare/kumo/agents-mdgit clone --depth 1 https://github.com/cloudflare/kumoWhat 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 | $0.02265 | $0.02265 |
| Opus 5 | $0.01132 | $0.01132 |
| Sonnet 5 | $0.00453 | $0.00453 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
kumo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KUMO KNOWLEDGE BASE
Generated: 2026-03-18 | Commit: 38518e34 | Branch: rozenmd/fix-preview
OVERVIEW
Cloudflare's React component library (@cloudflare/kumo). pnpm monorepo: component library (Base UI + Tailwind v4), Astro docs site, Figma plugin, screenshot worker. ESM-only, Node 24+.
STRUCTURE
kumo/
├── packages/
│ ├── kumo/ # Component library → see packages/kumo/AGENTS.md
│ ├── kumo-docs-astro/ # Astro docs site → see packages/kumo-docs-astro/AGENTS.md
│ ├── kumo-figma/ # Figma plugin → see packages/kumo-figma/AGENTS.md
│ └── kumo-screenshot-worker/ # Visual regression Worker → see packages/kumo-screenshot-worker/AGENTS.md
├── ci/ # CI/CD scripts → see ci/AGENTS.md
├── lint/ # Custom oxlint rules (5 rules in package, 4 at root)
├── .changeset/ # Changeset files
├── .github/workflows/ # 6 workflow YAMLs (release, pullrequest, preview, etc.)
└── .vite-hooks/ # Git hooks (Vite+): pre-commit codegen+staged, pre-push changeset validation
WHERE TO LOOK
| Task | Location | Notes |
|---|---|---|
| Component API | packages/kumo/ai/component-registry.{json,md} |
Source of truth. Query with jq or CLI |
| Component source | packages/kumo/src/components/{name}/{name}.tsx |
Standard pattern |
| Blocks (installable) | packages/kumo/src/blocks/ |
NOT library exports; installed via CLI |
| Semantic tokens | packages/kumo/src/styles/theme-kumo.css |
AUTO-GENERATED; edit scripts/theme-generator/config.ts |
| Custom lint rules | lint/ (4 rules) + packages/kumo/lint/ (+1) |
Package copy adds no-deprecated-props |
| Demo examples | packages/kumo-docs-astro/src/components/demos/ |
Feed into registry codegen |
| CI scripts | ci/ |
Reporter system, versioning, deployment |
| Figma generators | packages/kumo-figma/src/generators/ |
37 component generators |
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 · 163 lines · 2,265 tokens per session scan A badf1cc4f83c
kumo AGENTS.md is an instructions file published in the GitHub repository cloudflare/kumo (3,765 stars, last pushed 3d ago), licensed MIT. It adds 2,265 tokens to every session, about $0.0113 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
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.
buildNext
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.