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/trycourier/courier-skills/agents-mdgit clone --depth 1 https://github.com/trycourier/courier-skillsWrote 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/trycourier/courier-skills/agents-md)<a href="https://agentmods.dev/instructions/trycourier/courier-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/trycourier/courier-skills/agents-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 5.1 | $0.00442 | $0.00442 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
courier-skills 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 6d 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.
What it actually says
Contributing to Courier Skills
For anyone, human or agent, editing this repo.
One skill, one internal boundary
Everything is the skills/courier skill. Inside it, references/ splits along server vs client:
- Server-side (most of it): sending on every channel, journeys, templates, preferences, routing, providers, delivery debugging. Lives in
references/channels/andreferences/guides/. - Client-side: rendering the in-app inbox (JWT auth, the frontend SDKs, read state, real-time). Lives in
references/inbox/, entered viareferences/inbox/rendering.md.
Sending to the inbox is a channel (references/channels/inbox.md); rendering it is client work (references/inbox/). When unsure where something belongs, ask whether the code runs on a server or in the user's browser or device.
Two rules that keep this honest
Every SDK call must exist. Any client.X.Y(...) you write in a reference must exist in the installed @trycourier/courier (Node) and trycourier (Python) packages. Don't reconstruct signatures from memory. Read the SDK's own type definitions, or use the docs MCP (https://www.courier.com/docs/mcp).
YAML frontmatter descriptions must be wrapped in double quotes; an unquoted colon-space anywhere in the value makes the file unparseable and the skill silently uninstallable. Before committing a SKILL.md, validate the frontmatter with a strict YAML parser, not by eyeballing:
node -e 's=require("fs").readFileSync("skills/courier/SKILL.md","utf8");require("js-yaml").load(s.split(/^---$/m)[1])' && echo OK
A skill's name: equals its directory name, and each SKILL.md stays lean (~5,000 tokens, ~500 lines). Depth lives in references/, pulled on demand; the entry point routes, it doesn't document everything.
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.
- 6d ago First seen · 25 lines · 442 tokens per session scan A a8bdc7d82a3d
courier-skills AGENTS.md is an instructions file published in the GitHub repository trycourier/courier-skills (13 stars, last pushed 2d ago), licensed MIT. It adds 442 tokens to every session, about $0.0022 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 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).
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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 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).
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.