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/colebemis/notion-workers/agents-mdgit clone --depth 1 https://github.com/colebemis/notion-workersWhat 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 | $0.00987 | $0.00987 |
| Opus 5 | $0.00494 | $0.00494 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
notion-workers 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 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.
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notion Workers monorepo
This repo holds all of my Notion Workers. Each top-level directory (e.g. firecrawl/) is one deployed worker: a self-contained npm project with its own package.json, lockfile, src/index.ts, and workers.json.
For the full Notion Workers platform guide — capability API (tools, syncs, automations, webhooks, OAuth), sync patterns, testing, and debugging — read .agents/INSTRUCTIONS.md. Skills for sync work live in .agents/skills/, and .examples/ has one compilable reference example per capability type — when it and INSTRUCTIONS.md disagree on API shape, trust .examples/.
Conventions
- All
ntnandnpmcommands run from inside a worker's directory, not the repo root. There is no rootpackage.jsonand no shared dependencies. - Workers are named after the upstream service they wrap (
firecrawl,openlibrary), no-workersuffix. Directory name,package.jsonname, and deployed worker name (deploy --name) all match. workers.jsonis committed (it holds the workspace/worker IDs that link a directory to its deployed worker — IDs, not secrets). This deviates from the official scaffold's.gitignore. Never gitignore it here, and never delete it for an existing worker: without it,ntn workers deploycreates a new worker instead of updating.- Secrets are never committed. Local dev reads
.env(gitignored); deployed workers read env vars set viantn workers env set/ntn workers env push. If you add a new secret, push it before deploying code that needs it. - Each worker has a short
README.md: what it does, its capabilities, and required env vars. Keep it current when you change capabilities. - A worker may have its own
AGENTS.md(with aCLAUDE.mdsymlink, like the root). Worker-specific rules there OVERRIDE these norms — read it before touching that worker. Example:twitter/forbids the standard local-exec verify loop because of its token handling. - Tool schemas use the
jbuilder (import { j } from "@notionhq/workers/schema-builder"). SDK ≥ 0.4.0 no longer accepts raw JSON Schema objects intool()— some examples in.agents/INSTRUCTIONS.mdpredate this;.examples/tool-example.tsshows the current API. - Every tool input property is required. The SDK rejects schemas whose properties aren't all in
required;.nullable()means present-but-null, not omittable. Agent callers omit fields they don't need and fail validation, so keep tool inputs to fields the caller will always send. - No
"type": "module"in workerpackage.jsonfiles.ntn workers exec --local(CLI 0.16.0) fails on ESM workers withCannot read properties of undefined (reading 'run'). CJS mode works locally and deploys identically (requirestypescript≥ 5.8 to type-check importing the ESM SDK).new-worker.shstrips this from new scaffolds automatically.
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 · 49 lines · 987 tokens per session scan A d3710966d767
notion-workers AGENTS.md is an instructions file published in the GitHub repository colebemis/notion-workers (126 stars, last pushed 1mo ago), licensed MIT. It adds 987 tokens to every session, about $0.0049 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
spec-kit AGENTS.md
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.
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.
vscode buildNext.instructions.md
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).
langchain AGENTS.md
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.
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).
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.