Agent skill

Agents Md

by dimetron in dimetron/pi-go

Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects.

MITAuto-check passedAgent Workflows

Install Agents Md

skills CLI
$ npx skills add dimetron/pi-go --skill agents-md -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dimetron/pi-go agents-md --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dimetron/pi-go.git skills-src && mkdir -p .claude/skills && cp -r skills-src/internal/extension/bundled_skills/agents-md .claude/skills/agents-md && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agents-md
GitHub stars
207
Token cost
~1.7k tokens
SKILL.md length
473 words
Files
3
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects.

  • Works in 5 steps: Detect languages present. Look for these… → Inspect before writing. Run the actual… → Assemble from the template. Use the… → …
  • The user asks to create
  • SKILL.md covers Purpose, When to use, Workflow and Structure (Shared Core —…, plus 4 more sections
  • Calls npm, yarn and make

What it does

Agents Md is an agent skill from dimetron/pi-go. Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo agent-friendly", "document build/test commands for Claude Code", or uploads a repo and asks Claude Code to learn its conventions. Produces a spec-loose, Claude-Code-optimized AGENTS.md with a shared core…

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `example-AGENTS.md` and `template.md`).

It sits in Agent Workflows, covering Agent instruction files. It works with Rust, TypeScript, Java and Gradle. The repository describes itself as: Go implementation of AI coding agent. The licence is MIT.

When your agent uses it

  • The user asks to create
  • Review an AGENTS.md (or agent-instructions
  • Repo guide for agents) file in a codebase
  • The user says add AGENTS.md

Example prompts

  • “add AGENTS.md”
  • “make this repo agent-friendly”
  • “document build/test commands for Claude Code”
  • “/agents-md”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Detect languages present. Look for these marker files
  2. Inspect before writing. Run the actual build/test tool to confirm commands work, read 1–2 representative source files to pick up naming…
  3. Assemble from the template. Use the structure in template.md (same directory). Fill the Shared Core always, then append only the language…
  4. Keep it short. Target ~150–300 lines total. AGENTS.md is read on every agent session — brevity matters more than completeness. Link out to…
  5. Place at repo root as AGENTS.md. If the repo already has CLAUDE.md, ask whether to replace, merge, or keep both (CLAUDE.md can be a…

What it can do on your machine

Read from SKILL.md and the folder at commit 24d1f2b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm
    • yarn
    • make
    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and yarn, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agents Md loads about 1.7k tokens when it runs. Until then it costs about 153 tokens; SKILL.md has 473 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~153
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from dimetron/pi-go at commit 24d1f2b, republished under its MIT licence (© dimetron). 473 words, ~1,695 tokens.

Download SKILL.mdSave it as .claude/skills/agents-md/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
agents-md
description
Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Use this skill whenever the user asks to create, scaffold, bootstrap, update, or review an AGENTS.md (or agent-instructions, CLAUDE.md, repo guide for agents) file in a codebase. Also trigger when the user says "add AGENTS.md", "make this repo agent-friendly", "document build/test commands for Claude Code", or uploads a repo and asks Claude Code to learn its conventions. Produces a spec-loose, Claude-Code-optimized AGENTS.md with a shared core section plus short language-specific appendices for the stacks present in the repo.

AGENTS.md Generator

Purpose

AGENTS.md is a top-level Markdown file that tells coding agents (Claude Code, Cursor, etc.) how to work inside a repository: how to build, test, lint, where code lives, what conventions to follow, and what NOT to touch. A good AGENTS.md turns a cold-start agent into a productive one in a single read.

This skill generates such files. It is loosely inspired by the agents.md open standard but optimized for Claude Code workflows.

When to use

  • User asks to create / bootstrap / scaffold AGENTS.md (or CLAUDE.md, AGENT.md)
  • User hands Claude a repo and asks it to "learn the conventions" or "make it agent-friendly"
  • User wants to update an existing AGENTS.md after a stack change
  • User asks for a template they can fill in manually

Workflow

  1. Detect languages present. Look for these marker files:

    • Go → go.mod, go.sum
    • Rust → Cargo.toml, Cargo.lock
    • TypeScript → package.json + tsconfig.json (check for pnpm-lock.yaml / yarn.lock / package-lock.json / bun.lockb)
    • Java → pom.xml (Maven) or build.gradle[.kts] / settings.gradle[.kts] (Gradle)

    If multiple, it's a polyglot repo — include an appendix for each. If none detected, ask the user which stacks to target.

  2. Inspect before writing. Run the actual build/test tool to confirm commands work, read 1–2 representative source files to pick up naming style, check .golangci.yml, clippy.toml, eslint.config.*, checkstyle.xml for lint config. Never invent commands that weren't verified.

  3. Assemble from the template. Use the structure in template.md (same directory). Fill the Shared Core always, then append only the language sections that apply.

  4. Keep it short. Target ~150–300 lines total. AGENTS.md is read on every agent session — brevity matters more than completeness. Link out to deeper docs rather than inline them.

  5. Place at repo root as AGENTS.md. If the repo already has CLAUDE.md, ask whether to replace, merge, or keep both (CLAUDE.md can be a symlink or short pointer to AGENTS.md).

Show full SKILL.md (173 more words)Show less

Structure (Shared Core — always include)

# AGENTS.md

> One-paragraph repo description: what it is, who uses it, what stage.

## Quick start
- Setup: <single command or 2-3 lines>
- Build: <command>
- Test: <command>
- Run locally: <command>

## Repository layout
<tree of top-level dirs with one-line purpose each>

## Conventions
- <code style, naming, formatting tool>
- <commit message format>
- <branch / PR rules>

## Do not touch
- <generated files, vendored deps, migrations, etc.>

## Testing policy
- <what must have tests, coverage expectations>
- <how to run a single test>

## Gotchas
- <known footguns, non-obvious env vars, flaky tests>

Language Appendices (include only the ones that apply)

Go appendix
## Go

- Toolchain: Go <version from go.mod>
- Module: <module path>
- Build: `go build ./...`
- Test: `go test ./...` — single test: `go test ./pkg/foo -run TestName -v`
- Race: `go test -race ./...`
- Lint: `golangci-lint run` (config: `.golangci.yml`)
- Format: `gofmt -s -w .` and `goimports -w .`
- Deps: `go mod tidy` after any import change
- Errors: wrap with `fmt.Errorf("...: %w", err)`; use `errors.Is/As`
- Logging: `log/slog` (structured, no `fmt.Println` in library code)
- Context: first arg is always `ctx context.Context`
Rust appendix
## Rust

- Toolchain: pinned in `rust-toolchain.toml` (<channel>)
- Build: `cargo build` — release: `cargo build --release`
- Test: `cargo test` — single: `cargo test <name> -- --nocapture`
- Lint: `cargo clippy --all-targets --all-features -- -D warnings`
- Format: `cargo fmt --all`
- Deps: `cargo update -p <crate>` for targeted bumps; avoid blanket `cargo update`
- Errors: `thiserror` for libraries, `anyhow` for binaries
- Unsafe: must be justified in a `// SAFETY:` comment
- MSRV: <version> — do not use features beyond this
TypeScript appendix
## TypeScript

- Package manager: <pnpm|npm|yarn|bun> — do not mix
- Node: <version from .nvmrc or package.json engines>
- Install: `<pm> install`
- Build: `<pm> run build`
- Test: `<pm> test` — single: `<pm> test -- <pattern>` (vitest/jest)
- Lint: `<pm> run lint` (eslint + <config>)
- Typecheck: `<pm> run typecheck` or `tsc --noEmit`
- Format: `<pm> run format` (prettier)
- Strict mode: `tsconfig.json` has `"strict": true` — do not disable per-file
- Imports: use path aliases from `tsconfig.json`, not deep relative paths
Java appendix
## Java

- JDK: <version> (use SDKMAN or Temurin)
- Build tool: <Maven | Gradle>
- Build: `./mvnw clean install` or `./gradlew build`
- Test: `./mvnw test` or `./gradlew test` — single: `-Dtest=ClassName#method` / `--tests "ClassName.method"`
- Lint: `./gradlew check` (checkstyle + spotbugs) or `mvn verify`
- Format: `./gradlew spotlessApply` or `mvn spotless:apply`
- Style: Google Java Format, 4-space indent, no wildcard imports
- Null-safety: annotate with `@Nullable` / `@NonNull` (JSpecify)
- Logging: SLF4J — never `System.out.println` in production code

Writing rules

  • Verify, don't guess. Every command in the file must have been run successfully (or read from an existing script). Hallucinated make test targets are the #1 failure mode.
  • Imperative voice. "Run go test ./..." not "You can run tests with...".
  • Links over prose. For anything longer than 3 lines, link to docs/ instead of inlining.
  • No marketing. Skip the "welcome to our amazing project" opener. Start with what the agent needs.
  • Stable commands only. If a script is in flux, note it: # unstable — check Makefile.
  • Secrets & env. List required env vars by name; never include values. Point to .env.example.

Example output

See example-AGENTS.md in this skill directory for a filled-in polyglot (Go + TypeScript) example.

Updating an existing AGENTS.md

  1. Read the current file end-to-end.
  2. Diff against what's actually true now (run the commands, check the tree).
  3. Propose a patch, don't rewrite wholesale — preserve the user's voice and project-specific gotchas.

© dimetron, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in internal/extension/bundled_skills/agents-md of dimetron/pi-go.

  • SKILL.md
  • example-AGENTS.md
  • template.md

Open the folder on GitHubat commit 24d1f2b

Compare with similar skills

Agents Md next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agents Md compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agents Md this skilldimetron/pi-go207—~1.7kAutomated safety check: PassMIT
Build Teaql Appteaql/teaql-agent-kit2.8k—~4.6kAutomated safety check: PassMIT
Cross-Language Coding Standardszereight/gitlab-mcp2k1 repos~1.4kAutomated safety check: PassMIT
Dbgtheodo-group/debug-that158—~2.2kAutomated safety check: PassMIT
Temporal Developertemporalio/skill-temporal-developer230—~2.5kAutomated safety check: PassMIT
Supercovsupercorp-ai/supercov1501 repos~415Automated safety check: PassMIT

Similar skills

  • Build Teaql App

    teaql/teaql-agent-kit

    Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries.

    2.8k GitHub stars~4.6k tokensUpdated 11 days ago
    MobileAuto-check passed
  • Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift.

    2k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • Dbg

    theodo-group/debug-that

    Debug applications using the dbg CLI debugger. An agent skill from theodo-group/debug-that.

    158 GitHub stars~2.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Temporal Developer

    temporalio/skill-temporal-developer

    Official

    Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust.

    230 GitHub stars~2.5k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Supercov

    supercorp-ai/supercov

    Measures test coverage and code quality in a repository with the supercov CLI, and turns what it finds into small, focused tests or fixes.

    150 GitHub starsUsed in 1 repo~415 tokens
    Testing & QAAuto-check passed
  • Upgrade Packages

    MelbourneDeveloper/dart_node

    Upgrade all dependencies/packages to their latest versions for the detected language(s).

    113 GitHub stars~2.2k tokensUpdated 24 days ago
    MobileAuto-check passed

More from dimetron/pi-go

All 21 skills in this repo
  • Vhs E2E Gif

    dimetron/pi-go

    Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit.

    207 GitHub stars~1.7k tokensUpdated 7 days ago
    Auto-check passed
  • Bubbletea Testing

    dimetron/pi-go

    A skill your agent uses whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go.

    207 GitHub stars~3.6k tokensUpdated 7 days ago
    Auto-check passed
  • Memory Index

    dimetron/pi-go

    Index a folder's contents into the MemPalace semantic memory for search and retrieval.

    207 GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed
  • Nightly Session Watch

    dimetron/pi-go

    Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still…

    207 GitHub stars~1.5k tokensUpdated 7 days ago
    Auto-check passed
  • Osx Tuning

    dimetron/pi-go

    Tune macOS resource limits and sysctls for best performance with Go development, Docker/OrbStack, and Linux VMs.

    207 GitHub stars~1.6k tokensUpdated 7 days ago
    Auto-check: notes
  • Pgo

    dimetron/pi-go

    Profile-guided optimization (PGO) for the pi binary. An agent skill from dimetron/pi-go.

    207 GitHub stars~1.4k tokensUpdated 7 days ago
    Auto-check passed

Categories

Questions about Agents Md

What does Agents Md do?

Generate AGENTS.md files for Go, Rust, TypeScript, and Java projects. Agents Md is an agent skill from dimetron/pi-go.md files for Go, Rust, TypeScript, and Java projects.

When should I use Agents Md?

Agents Md fits situations like: the user asks to create; review an AGENTS.md (or agent-instructions; repo guide for agents) file in a codebase; the user says add AGENTS.md.

How do I install Agents Md in Claude Code?

Run `npx skills add dimetron/pi-go --skill agents-md -a claude-code`. Or copy the skill folder (internal/extension/bundled_skills/agents-md in dimetron/pi-go) into .claude/skills/agents-md in your project. Claude Code loads it when a task matches its description.

How do I install Agents Md in Codex?

Run `npx skills add dimetron/pi-go --skill agents-md -a codex`. Or copy the skill folder (internal/extension/bundled_skills/agents-md in dimetron/pi-go) into .agents/skills/agents-md in your project. Codex loads it when a task matches its description.

Can I use Agents Md in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dimetron/pi-go --skill agents-md -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agents-md, .gemini/skills/agents-md, .github/skills/agents-md and .opencode/skills/agents-md in your project.

What does Agents Md need to run?

Going by SKILL.md and its folder, Agents Md needs the command-line tools its instructions call (npm, yarn, make and go).

Does Agents Md access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Agents Md safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agents Md use?

Agents Md is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agents Md use?

About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agents Md?

Skills that share tags, products or a category with Agents Md: Build Teaql App (teaql/teaql-agent-kit, 2.8k stars), Cross-Language Coding Standards (zereight/gitlab-mcp, 2k stars), Dbg (theodo-group/debug-that, 158 stars) and Temporal Developer (temporalio/skill-temporal-developer, 230 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agents Md?

dimetron (a GitHub user) maintains it in dimetron/pi-go, which has 207 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 1, 2026.

Source: dimetron/pi-go on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.