Skip to content
Agentmart
Submit a tool

AGENTS.md · hashicorp/agent-skills

AGENTS.md from hashicorp/agent-skills: 56 lines covering Canonical structure, Skill requirements, Ownership and review, Contributions and more.

Template by hashicorp

IndexedMPL-2.0★ 907
Write a review

Chalk Labs

Need help deploying AGENTS.md · hashicorp/agent-skills?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code. Read the repository before you give any tool access to your data.

curl -fsSL https://raw.githubusercontent.com/hashicorp/agent-skills/main/AGENTS.md -o AGENTS.md

Read it and adapt it to your project before use.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

The AGENTS.md file that hashicorp/agent-skills (907 stars) keeps for coding agents. It has 56 lines in 5 sections: Canonical structure; Skill requirements; Ownership and review; Contributions; Validation. Use it as a model for your own project's instructions.

Use cases: prompt-engineering

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

What's in it

An AGENTS.md file: instructions coding agents (Codex, Cursor, Copilot, Gemini CLI and others) read before working in a repo.

For
Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Claude Code
Length
56 lines
File
AGENTS.md

Sections

  1. Canonical structure
  2. Skill requirements
  3. Ownership and review
  4. Contributions
  5. Validation

First lines (shown under the repo's MPL-2.0 license)

# Agent Instructions

This repository contains public HashiCorp Agent Skills and the Terraform and
Packer product plugins that distribute them.

## Canonical structure

- Put Terraform Skills in `plugins/terraform/skills/<skill-name>/`.
- Put Packer Skills in `plugins/packer/skills/<skill-name>/`.
- Keep Claude Code and Codex plugin manifests at each product root.
- Keep the Claude Code and Codex marketplaces aligned to exactly the
  `terraform` and `packer` bundles.
- Keep individual Skill installation paths in `SKILLS.md` aligned with disk.

## Skill requirements

- Every Skill directory must contain `SKILL.md`.
- Every `SKILL.md` frontmatter must contain `name`, `description`, and
  `metadata.lifecycle-status`.
- Skill names must match their directory names.
- Supported lifecycle states are `active`, `deprecation-candidate`,
  `deprecated`, and `retired`.
- Keep detailed material in directly linked `references/`, `scripts/`, or
  `assets/` resources when that improves progressive disclosure.

## Ownership and review

`CODEOWNERS` is canonical. Every Skill must have an explicit Skill-level entry
that includes `@hashicorp/team-agent-skills-ecosystem`. Product-aligned owners
may be added only after their participation is confirmed. The ecosystem team
owns repository conventions, evaluation integration, distribution, supported
model consistency, and final repository decisions.

Review or reevaluate a Skill whenever the Skill changes or the supported model
matrix changes. Structural validation, Skill review, private Waza evaluation,
CODEOWNERS review, and maintainer judgment are complementary inputs.

## Contributions

The repository is in an internal-contribution-only phase. Follow
`CONTRIBUTING.md` and use the proposal template for a new Skill or substantial
rewrite. Do not add public evaluation fixtures or raw evaluation results.

## Validation

Run these checks before proposing a change:

```bash
./scripts/validate-structure.sh
git diff --check
```

Run relevant example, link, installation, and harness checks for the changed
surface. Never run infrastructure-creating examples against real credentials as
part of repository validation.

Signals

Stars
907
Forks
134
Open issues
12
Last commit (this folder)
Aug 10, 2026 (2 months ago)
Last release
Aug 4, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MPL-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from hashicorp

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get AGENTS.md · hashicorp/agent-skills running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying AGENTS.md · hashicorp/agent-skills?

CallGet help
Cite this page

AGENTS.md · hashicorp/agent-skills. Agent Mart. https://agentmart.dev/templates/hashicorp-agent-skills-agents-md (last updated 2026-10-24)