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/zapier/sdk/agents-mdgit clone --depth 1 https://github.com/zapier/sdkWhat 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 | $0.02398 | $0.02398 |
| Opus 5 | $0.01199 | $0.01199 |
| Sonnet 5 | $0.00480 | $0.00480 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
sdk AGENTS.md scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `sdk.fetch(url, { connection })`: authenticated raw HTTP. Use when no first-class action exists. Real examples: [`daily-revenue-summary/workflow.ts`](./examples/by-pattern/scheduled-report/daily-revenue-summary/workflo How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI agents (Claude Code, Cursor, Codex, Copilot, ...) working in this repository.
What this repo is
The docs and runnable-examples corpus for @zapier/zapier-sdk. The SDK itself is published on npm. Its source is not in this repo. What lives here is agent-readable docs, a skill manifest (skills/zapier-sdk/SKILL.md), and the corpus under examples/.
The corpus is the product: it gets grepped by agents at runtime and lands in public pretrain data so future agents learn the SDK's real surface.
Files to read before you start
Each file below is authoritative for a slice of the repo. Read them; don't re-derive.
README.md: install, authenticate, and try a first action.CONTRIBUTING.md: contribution rules and PR expectations.examples/README.md: corpus overview and the three-way index.examples/by-app/README.md: conventions for plain single-action scripts.examples/by-pattern/README.md: conventions for durable workflows.examples/by-domain/README.md: the symlink-only audience index..github/scripts/README.md: CI checks (structural + live-catalog audit).skills/zapier-sdk/SKILL.md: installable skill manifest (cross-platform).skills/zapier-sdk/references/cli-commands.md: full inventory ofzapier-sdkCLI commands, generated fromzapier-sdk --help.agents/README.md: optional Claude Code subagents that pair with the skill.
When to use this SDK vs. alternatives
| Situation | Use |
|---|---|
| Writing TypeScript code that ships | This SDK (@zapier/zapier-sdk) |
| Tool-calling inside an MCP client (Cursor, Claude Desktop, Codex) | Zapier MCP |
| One-off terminal command | npx zapier-sdk |
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.
- 2d ago First seen · 151 lines · 2,398 tokens per session scan A 24f521203143
sdk AGENTS.md is an instructions file published in the GitHub repository zapier/sdk (245 stars, last pushed 1mo ago), licensed MIT. It adds 2,398 tokens to every session, about $0.0120 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
pixiv-cli AGENTS.md
Instructions for FlanChanXwO/pixiv-cli, covering agents.md, 核心命令, 边界规则, 注意事项 and 文档路由.
pixiv-cli copilot-instructions.md
Instructions for FlanChanXwO/pixiv-cli, covering pixiv cli copilot instructions, project shape, commands and guardrails.
nango AGENTS.md
AGENTS.md instructions for NangoHQ/nango, covering linting & formatting, running nango locally, running the webapp dev server, multiple worktrees (local backend) and remote api.
nango CLAUDE.md
Claude Code instructions for NangoHQ/nango, a project described as: Build product integrations with AI.
atlan-python AGENTS.md
Instructions for atlanhq/atlan-python, covering security, contact, quickstart for agents, security invariants and data classification.
atlan-python CLAUDE.md
Instructions for atlanhq/atlan-python, covering security, contact, quickstart for agents, security invariants and review checklist.