skills AGENTS.md

Repository instructions for creating and maintaining Speakeasy CLI skills for coding agents. They describe the project layout and the required format for each skill file.

In plain words
What is it for?
Adding skill directories, following the required SKILL.md structure, and working within the Speakeasy skills repository.
Why use it?
They give contributors a shared structure and required fields, making new skills easier to create and maintain consistently.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/speakeasy-api/skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/speakeasy-api/skills

Made for: Codex, OpenCode.

Per session 1,364 This file is loaded in full into every session.
When invoked 1,364 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01364 $0.01364
Opus 5 $0.00682 $0.00682
Sonnet 5 $0.00273 $0.00273
Haiku 4.5 $0.00136 $0.00136

Measured 2d ago against content hash 7cd2fd873371, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

AGENTS.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance for AI coding agents working on the Speakeasy Agent Skills repository. It covers how to create, maintain, and improve skills for the Speakeasy CLI.

Repository Structure

speakeasy-api/skills/
├── .claude-plugin/          # Claude Code plugin configuration
│   ├── plugin.json          # Plugin manifest (namespace: "speakeasy")
│   └── marketplace.json     # Marketplace metadata
├── skills/                  # Skill definitions
│   └── {skill-name}/
│       └── SKILL.md         # Skill instructions
├── templates/               # Skill templates
│   └── SKILL.template.md    # Template for new skills
├── AGENTS.md                # This file (contributor guidance)
├── CLAUDE.md                # Claude-specific contributor guidance
├── README.md                # End-user documentation
└── LICENSE                  # Apache-2.0

Creating a New Skill

1. Directory Structure

mkdir skills/{skill-name}

Use kebab-case for directory names (e.g., manage-openapi-overlays).

2. SKILL.md Format

Every skill must have a SKILL.md file with YAML frontmatter. See templates/SKILL.template.md for a complete example.

Required structure:

---
name: skill-name
description: Use when [trigger condition]. Include phrases like "X", "Y", or "Z".
---

Required sections:

Section Purpose
# skill-name Title matching the directory name
## When to Use Trigger scenarios and example phrases
## Command The speakeasy command to run
## Example Working example with explanation

Recommended sections:

Section Purpose
## Prerequisites Required setup, env vars, dependencies
## Decision Framework Table mapping situations to actions
## What NOT to Do Anti-patterns the AI should avoid
## Related Skills Links to related skills

3. Naming Conventions

  • Directory: kebab-case (e.g., start-new-sdk-project)
  • SKILL.md: Always uppercase, exact filename
  • Frontmatter name: Must match directory name exactly

Read the full file on GitHub · 183 lines

Changes

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.

  1. 2d ago First seen · 183 lines · 1,364 tokens per session scan A 7cd2fd873371

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository speakeasy-api/skills (18 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,364 tokens to every session, about $0.0068 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.