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/contentful/ui-extensions-sdk/claude-mdgit clone --depth 1 https://github.com/contentful/ui-extensions-sdkWrote 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.
[](https://agentmods.dev/instructions/contentful/ui-extensions-sdk/claude-md)<a href="https://agentmods.dev/instructions/contentful/ui-extensions-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/contentful/ui-extensions-sdk/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00804 | $0.00804 |
| Opus 5 | $0.00402 | $0.00402 |
| Sonnet 5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
ui-extensions-sdk CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Project Instructions — ui-extensions-sdk
You are working in the ui-extensions-sdk repo (github.com/contentful/ui-extensions-sdk). It builds the App SDK and publishes it to npm as @contentful/app-sdk (preferred) and the legacy contentful-ui-extensions-sdk alias. Read AGENTS.md and ARCHITECTURE.md before making non-trivial changes.
Identity & Scope
- This is a public, customer-facing TypeScript library. Public types are a contract: thousands of customer apps and many internal repos consume
lib/types/index.ts. - Co-owned by
@contentful/team-extensibilityand@contentful/team-marketplace. - Bundle size is policed by CI. Adding a runtime dependency is almost always wrong —
contentful-managementis currently the only one.
Working style
- Conventional Commits at PR-title level. Use
feat:,fix:,chore:(no release),docs:(no release),refactor:(no release). - Breaking changes require a
BREAKING CHANGE:footer —feat!:alone does not bump major reliably. - One unit test per module under
test/unit/<module>.spec.ts. - No
anyin public types.unknownis acceptable internally. - Squash merge. PR title becomes the commit message.
Sharp edges
- Do not edit
package.json#name—scripts/publish.jsmutates it during dual-publish. - Do not add methods to
lib/space.ts— it is deprecated since v4.0.0. - Do not reference
globalThis.contentfulExtensionin new code; it's a back-compat alias only. - Do not run
npm installif you don't have to —npm ciis the source of truth and CI uses it. - Do not skip the husky pre-commit hook with
--no-verifyunless the hook itself is broken. - Do not introduce ESM-only dependencies — the bundle is UMD-target ES5.
Verification before claiming done
npm run check-types
npm run lint
npm test
npm run build
npm run size
If any of these fail, the work is not done. Fix the root cause; do not bypass.
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.
- 4d ago First seen · 61 lines · 804 tokens per session scan A 0d3477ff3f06
ui-extensions-sdk CLAUDE.md is an instructions file published in the GitHub repository contentful/ui-extensions-sdk (131 stars, last pushed 5d ago), licensed MIT. It adds 804 tokens to every session, about $0.0040 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
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
walkerOS CLAUDE.md
Claude Code instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.
solo copilot-instructions.md
Copilot instructions for hiero-ledger/solo, covering github copilot instructions for hiero-ledger/solo and highest-frequency rules.
openmcp-client CLAUDE.md
Instructions for LSTM-Kirigaya/openmcp-client, covering claude.md, development commands, setup and installation, development and service development.
Kokoro-Engine CLAUDE.md
Instructions for chyinan/Kokoro-Engine, covering claude.md, git 规范, 项目概述, 常用命令 and 安装依赖.