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/firework-labs/airtable-interface-extension-kit/claude-mdgit clone --depth 1 https://github.com/Firework-Labs/airtable-interface-extension-kitWrote 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/firework-labs/airtable-interface-extension-kit/claude-md)<a href="https://agentmods.dev/instructions/firework-labs/airtable-interface-extension-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/firework-labs/airtable-interface-extension-kit/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 | $0.01163 | $0.01163 |
| Opus 5 | $0.00581 | $0.00581 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
airtable-interface-extension-kit 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airtable Interface Extension Kit
Project Overview
This is a starter kit, not a working app. It packages the project-agnostic SDK gotchas, antd-iframe rules, and reusable React/antd scaffolding from a production Airtable Custom Interface project, so a new project can clone, brand, and build a working extension in one sitting. When this kit is cloned for a real project, the consuming project should rewrite this file from scratch (don't diff against the kit's version).
Tech Stack
Airtable Custom Interface (Edit Source path), React 16.14.0 (SDK constraint), antd 5.22.7 + dayjs + marked + DOMPurify via CDN runtime injection, bash concatenation builds. No npm.
Critical reading
Before adding code, read airtable-sdk-gotchas.md. Many of the SDK's failure modes are silent — wrong behavior with no error.
| Doc | When to read |
|---|---|
| airtable-sdk-gotchas.md | Before any code that touches useRecords, useBase, getCellValue*, createRecordAsync, updateRecordAsync |
| airtable-api-patterns.md | Before writing linked-record updates, formula fields, or automation scripts |
| antd-in-iframe-canon.md | Before adding any antd component that uses popups, modals, messages, or layouts |
| build-and-deploy.md | When the build/concat order doesn't match what you expect, or when adding new shared deps |
| ux-conventions.md | When designing a new view (filter semantics, persistence, drawer keys, etc.) |
| lessons-learned-airtable.md | For deeper context on why specific gotchas exist (cite the original session date for traceability) |
| porting-checklist.md | First-time clone: clone → brand → build → paste workflow |
| hello-world-airtable-setup.md | What table schema the demo expects |
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.
- 5d ago First seen · 68 lines · 1,163 tokens per session scan A ca419a9d3957
airtable-interface-extension-kit CLAUDE.md is an instructions file published in the GitHub repository Firework-Labs/airtable-interface-extension-kit (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,163 tokens to every session, about $0.0058 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.
Other instructions, from other repositories
baserow AGENTS.md
AGENTS.md instructions for baserow/baserow, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and localization.
baserow CLAUDE.md
Claude Code instructions for baserow/baserow, a project described as: Build databases, automations, apps & agents with AI — no code. Open source platform available on cloud and self-hosted. GDPR, HIPAA, SOC 2 compliant. Best Airtable alternative.
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.